arXiv Papers

GNSS-denied unmanned aerial vehicles require occasional absolute position fixes to bound the drift of visual-inertial odometry. Cross-view image retrieval can provide such fixes, but raw appearance is sensitive to season, illumination, viewpoint, map age, and sensor modality. We propose \sas, a semantic map-localization framework that represents the environment through persistent structures such as roads, buildings, waterways, railways, intersections, and field boundaries. The method combines semantic raster alignment, relational graph evidence, feature stability and geographic distinctiveness, explicit positive/contradictory/unknown observations, and integrity-aware rejection of ambiguous fixes. Unlike a broad architecture-only proposal, this paper specifies concrete weighting and decision models and reports a reproducible synthetic proof of concept. In 220 randomized retrieval trials with rotation, scale changes, partial crops, occlusion, simulated map changes, and hard semantic decoys, a global semantic descriptor achieved 58.6\% Recall@1, while spatial semantic matching variants achieved 94.5-95.5%. Wilson 95\% intervals separate the global descriptor from the spatial variants but overlap among the spatial variants, so the experiment supports semantic geometry rather than a definitive benefit from each proposed module. The preliminary experiment does not validate real-flight navigation; rather, it demonstrates that structured semantic geometry can discriminate locations under controlled cross-view perturbations and identifies the harder aliasing, map-aging, and rejection tests required next.

Model-free reinforcement learning has enabled impressive humanoid locomotion; however, control on steep slopes remains largely unexplored. Unlike flat or discrete terrains, sloped terrains impose a persistent gravitational bias that demands simultaneous stability and posture control. Consequently, under generic reward formulations, policies can converge to slow, conservative low-center-of-mass (CoM) crouched gaits. In this work, we propose a novel two-stage physics-guided framework, dubbed HumoSlope, dedicated to robust humanoid locomotion on diverse sloped terrains. Specifically, Stage I establishes a terrain-consistent balance prior by introducing a slope-adaptive Zero Moment Point (ZMP) regularizer evaluated directly on the local inclined support plane rather than a world-horizontal reference. To prevent the resulting policy from defaulting to a crouched posture, Stage II introduces the Biomechanical Slope Gait Adapter (BSGA). Utilizing extracted macroscopic terrain descriptors as privileged, training-only signals, BSGA dynamically gates soft reward priors to modulate CoM height and lower-limb coordination based on the estimated slope geometry -- encouraging hip-dominant uphill propulsion and knee-oriented downhill braking. Crucially, the deployed actor remains entirely proprioceptive, requiring no online exteroceptive sensing. Extensive Sim-to-Real experiments demonstrate that our framework effectively mitigates posture degeneration and enables blind, continuous traversal of outdoor grass slopes up to 62.7% ($32.1^\circ$), validating a physics-guided approach to challenging slope terrain adaptation.

While closed-loop motion planners trained on large-scale, object-level datasets, e.g., nuPlan, demonstrate strong in-distribution (ID) performance, their generalization to novel urban topologies and recovery mechanisms following execution perturbations remain under-explored. To address this, we present Shift & Drift, a novel dual-track benchmark designed to rigorously stress-test motion planners across two critical axes of distribution shift: (1) The Semantic Shift Track leverages a novel conversion pipeline that transforms the aerial, DeepScenario Open 3D dataset into the nuPlan simulation framework. This enables zero-shot evaluation of planners trained on North American and Singaporean data against 1,182 scenarios spanning four German cities and the US city of San Francisco featuring dense pedestrian-cyclist interactions. (2) The State-Distribution Drift Track injects stochastic perturbations into the ego vehicle's dynamics to quantify robustness against compounding execution errors. Based on this, we systematically evaluate the failure modes of diverse planning paradigms under semantic and state-distribution shifts. While imitation learning methods achieve high scores in ID benchmarks, they exhibit significant failures under semantic shift, particularly in pedestrian-dense environments, and suffer from persistent drift when subjected to temporally correlated actuation noise. In contrast, the evaluated reinforcement-learning-based planner demonstrates more graceful degradation, maintaining higher safety and progress metrics across both tracks. Our findings reveal an empirical trade-off between imitation fidelity and closed-loop resilience, providing the community with a rigorous benchmark to evaluate progress toward reliable deployment.

The scalability of organic agriculture is partially limited by the labor costs associated with monitoring for pests. While drones and rovers are well-suited for agricultural monitoring from above or next to plants, many pests live on the underside of leaves or on plant stems, making them detectable only after they have caused significant damage. To enable early pest detection we present STEMbot, a miniature climbing robot system designed for autonomous navigation under plant canopies. Unlike existing climbing platforms that lack on-board perception or are restricted to unbranched vertical trunks, STEMbot integrates a fully geometric PIN-SLAM pipeline with a semantic OcTree to achieve robust localization and mapping while climbing the plant. To plan STEMbot's motion we propose a manifold-constrained A* planner along with ray-tracing goal specification to enable branch-aware traversal and the inspection of occluded targets. We validate our system through hardware experiments, demonstrating reliable traversal of stems ranging from 7-33mm and autonomous navigation across four distinct plant specimens. Quantitative evaluations show that our system achieves high-fidelity geometric reconstructions with an average Chamfer distance of less than 1cm relative to an offline photogrammetry baseline, confirming that STEMbot maintains the globally consistent odometry needed for autonomous navigation.

Dynamic obstacle avoidance in unstructured outdoor environments remains a critical challenge for autonomous mobile robots, particularly when large-scale robot-specific training data and simulation-based policies are impractical. We present a data-efficient, interpretable method for vision-based dynamic obstacle avoidance that operates entirely on real-world data, avoiding the sim-to-real transfer problem inherent in simulation-trained policies. Our approach leverages UniDepth, a large pretrained monocular depth estimation model, to produce dense depth maps from RGB video without requiring stereo cameras or LiDAR at inference time. Dynamic obstacle avoidance is achieved by extending the SuperPoint and SuperGlue feature correspondence pipeline to track keypoints across long frame sequences, projecting their 2D pixel-space positions into 3D using camera intrinsics and predicted depth, running bundle adjustment initialized from these 3D keypoints, and computing per-keypoint time-to-collision (TTC). A 2D motion primitive in the ground plane is then selected to move the robot away from the closest point of approach of the minimum-TTC keypoint. Evaluated on real-world data from the M3ED dataset, our pipeline achieves a precision of 0.49 and a recall of 0.38 in identifying frames with a ground truth TTC below 1 second, and correctly generates the evasive motion direction in 84\% of true positive detections. Crucially, it detects at least one frame with TTC less than 1 second for 20 out of 22 unique physical obstacles present in our test sequences. Unlike end-to-end learned methods that demand thousands of hours of robot-specific training data, our approach eliminates model training entirely, requiring only 74 seconds of data for hyperparameter tuning. This demonstrates exceptional data efficiency while preserving interpretable and generalizable behavior across diverse obstacle types.

Grasping in unstructured environments requires handling objects with widely different mechanical properties, from soft and deformable items to rigid everyday objects. Most existing approaches address these categories separately and often rely on tactile sensing, object-specific models, or specialized grippers. In this paper, we present a unified monocular vision-based grasping framework that targets both soft and rigid objects within a single control pipeline, using only RGB input and a position-controlled gripper. The proposed system combines open-vocabulary object detection, image segmentation, boundary-aware point assignment, real-time point tracking, and monocular depth estimation to recover object motion and geometry from visual observations. A key component of the framework is a language-based stiffness estimation model that infers an object's expected compliance from its semantic description and provides an object-level prior for selecting the grasping strategy before contact. For deformable objects, grasp adaptation is governed by a Procrustes-based dissimilarity measure computed from tracked keypoints, which acts as a visual proxy for deformation. For rigid objects, the gripper width is regulated through the scaling of tracked point distances. We validate the proposed method in real-world pick-and-place experiments on a Franka Emika Research 3 arm using objects with substantially different mechanical properties, including lettuce, fresh mozzarella cheese, croissants, paper towels, and hard plastic bottles. Results demonstrate that the framework achieves stable grasping across both soft and rigid objects using visual feedback alone, highlighting a practical, sensor-efficient, and generalizable approach for food handling and household manipulation.

Hand spasticity and resulting pain affect 12 million people worldwide, including stroke survivors, arthritis patients, and those with other muscle and nerve deficiencies. Soft robotic exogloves are being introduced to help patients enhance mobility or manage pain; however, there are no current solutions that address both pain and mobility. We present preliminary development of a soft robotic exoglove that both aids in mobility and administers massage-like compression to relax spastic muscles. The glove consists of soft pneumatic actuators that are personalized to an individual's hand topology and kinematics, allowing for optimal conformability and targeted mobility. Novel soft actuators were designed, analyzed, fabricated, assembled into an exoglove, and experimentally tested. Actuators were 3D modeled and analyzed with finite element modeling under pressures of 100 and 200 kPa. Geometries were optimized to minimize stress before fabrication and testing. A dorsal finger actuator was successfully customized to a participant's hand topology, providing full conformal contact and maximal force distribution. A ventral finger actuator was successfully fabricated that can be drastically compressed in size to fit into the tight space of a hyperflexed spastic finger. A palmar actuator was successfully printed with stereolithography, showing potential for 3D-printed soft actuators with more complex geometries. The glove was assembled and successfully worn by a pilot user to validate initial findings in comfort and effectiveness.

Soft robotic exogloves can provide hand rehabilitation and assistance. Fitting these gloves often relies on standardized measurements not tailored to the individual, limiting their effectiveness, especially for fine articulation necessary for dexterous manipulation. We present the design, fabrication, modeling, and testing of a personalized pneumatically-actuated soft robotic exoglove. The glove was fit to a user's hand with topological scans and fabricated with silicone mold casting. Finite element analysis (FEA) was performed to evaluate actuator bending and forces from physical human-robot interaction (pHRI) between an actuator and a simplified personalized biomechanical finger model. Pneumatic pressure control experiments were conducted to flex the user's finger with static and dynamic references. Fabrication results show that topological scans enable precise tailoring to hand anatomy. Simulations showed that anatomical personalization enables analysis of pHRI contact forces, and results indicate sufficient joint mobilization with non-ideal compression on the proximal phalanx. Pneumatic testing indicates that pressure control allows accurate and targeted mobility of the metacarpophalangeal (MCP) and proximal interphalangeal (PIP) joints with intrinsic stiffness. Testing of multiple designs showed that relaxing the strain-limiting layer improves actuator-to-finger joint alignment during actuation. This work presents personalization to the human hand in structural conformability, joint topology, modeling of pHRI contact, and time-dependent actuation-deformation profiles. This lays a groundwork for informing exoglove design optimization to enable assistance in dexterous manipulation and neuromuscular rehabilitation of fine motor skills.

Recent advances in actuation, control and learning have rapidly pushed humanoid robots from a distant vision towards near-term real-world deployment. Healthcare is a particularly pressing domain, in which staffing shortages and increasing care demand are widening the gap between clinical workload and available skilled labour. Although current automation has largely focused on digital and logistical tasks, much hospital work remains embodied, requiring mobility, manipulation and safe interaction in human-designed environments. Humanoid form factors offer unique potential, particularly for assisting with surgical tasks. Traditionally, robotic systems for surgery are purpose-built platforms such as Intuitive Surgical's da Vinci Surgical System, and it remains unclear how close current humanoid systems are to meeting the precision, control and safety requirements of minimally invasive surgery. Here we present a systematic evaluation of contemporary humanoid technology for laparoscopic surgical tasks. We develop a humanoid-based laparoscopic teleoperation framework using general-purpose instruments and assess its abilities through benchtop characterization, dry-laboratory user studies spanning diverse surgical experience levels and in vivo porcine studies. Across these evaluations, we quantify technical feasibility, task performance and clinical readiness relative to established surgical platforms. Together, our study provides an evidence-based assessment of current humanoid abilities and limitations for surgical applications, highlighting both their promise and key technical challenges that must be addressed before clinical deployment.

Multi-robot localization that is accurate and consistent is imperative for downstream tasks such as planning and control. Centralized filtering approaches optimally fuse all available sensor measurements of the team. However, a centralized solution is rarely implementable due to hardware, communication, and computational constraints. Distributed approaches deploy a filter on each robot to estimate their own state and neighbours' states using inter-robot communication. This paper proposes a consistent, communication-efficient, and consensus-based distributed filtering framework that shares both preintegrated odometry and relevant shared states among communicating robots. The proposed method is validated in simulated and experimental scenarios, showing near centralized performance in accuracy, and especially in consistency, compared to the current state-of-the-art decentralized approach.

Social robots offer a promising means of supporting cognitive therapies for dementia care by guiding structured conversation and therapeutic activities. However, little is known about the conversational dynamics that emerge during robot-delivered cognitive stimulation therapy (CST) sessions. This study analysed the interaction patterns from robot-delivered individual CST (iCST) sessions conducted with people living with dementia in home settings. Our Co-STAR (Cognitive Stimulation Therapy by an Autonomous Robot) system was deployed in the homes of eight PwDs for one week, who completed 30-minute sessions. Conversational metrics, including words per turn, speech production rate, response duration, response latency, and self-referential language, were analysed to examine how conversational engagement is shaped by prompt personalisation, interaction phase, and participant characteristics. The findings highlight three key interactional properties of robot-delivered iCST. First, personalised prompts significantly increase response duration, self-referential language, and overall engagement compared to generic prompts. Second, conversational behaviour changes within sessions, with a reduction in the verbal output and autobiographical engagement observed during later interaction phases, which suggests cognitive fatigue. Third, first-session conversational metrics were associated with long-term participation, while living situation influenced conversational engagement patterns. These findings provide empirical insights into the factors that shape conversational engagement in robot-delivered iCST. They inform the design of adaptive conversational robots for dementia therapy.

While global localization using spinning radar has gained attention for its robustness to adverse weather and challenging environments, many studies have focused on individual components such as place recognition or pose estimation. In this paper, we take a holistic view of radar sensor-based global localization and present RadLoc, a fast, robust, and lightweight end-to-end pipeline from place recognition to 3-DoF pose estimation. RadLoc accelerates pre-processing using 1D CA-CFAR filtering and leverages the near-range dominance in spinning radar images to design a compact descriptor and an efficient hierarchical coarse-to-fine retrieval strategy. Moreover, coupled with phase correlation-based 3-DoF pose estimation, it forms a versatile global localization module applicable to SLAM and multi-session SLAM systems. Extensive experiments on 15 sequences across 5 datasets demonstrate that RadLoc achieves robust performance while maintaining the smallest descriptor size and fastest retrieval time among state-of-the-art approaches. The supplementary materials are available at https://sparolab.github.io/research/radloc/.

Steering Cable-Driven Parallel Robots (CDPRs) beyond their Wrench-Feasible Workspace (WFW) augments their capabilities in challenging scenarios such as during aggressive maneuvers or following a cable failure. In this context, although the determination of cable tensions is a well-studied topic, only a few approaches address these scenarios. Therefore, this paper introduces an extended version of the Analytic Center method as a criterion for selecting cable tensions outside the WFW while maintaining differentiability and including non-linear constraints. Notably, the proposed method maintains continuous and differentiable tension profiles, ensures fast real-time convergence to a unique solution, and, in contrast to other slack-based formulations, relegates wrench errors to a negligible area of the WFW. Its superiority in terms of smoothness and wrench error is confirmed via Pareto dominance with respect to the leading state-of-the-art method. Lastly, the effectiveness of the method is demonstrated through numerical experiments.

Vision--Language--Action (VLA) policies such as $\pi_{0.5}$ and OpenVLA perform well on many manipulation tasks, but they are often reactive: the next action is predicted from the current observation, instruction, and proprioceptive state. This assumption breaks down in stage-dependent manipulation, where visually similar states may require different actions depending on latent task progress and previous interaction outcomes. We argue that such tasks require not only memory, but dynamics-aware belief updates: the policy should preserve task progress during stable or occluded phases and revise its belief near contact, release, or subgoal transitions. We introduce Temporally Conditioned Memory-Fusion Policies (TFP), a lightweight memory-action framework for VLA backbones. TFP maintains an episode-local task-progress belief with Liquid Time-Constant dynamics and injects the updated belief directly into the flow-matching action decoder through adaptive modulation. This lets temporally accumulated context shape the generated action chunk, rather than serving only as passive history context. With a 3.3B-parameter model, TFP improves the average success rate from \(96.9\%\) to \(98.75\%\) on LIBERO and from \(91.4\%\) to \(93.77\%\) on LIBERO-plus. On the memory-focused MIKASA ShellGameTouch diagnostic, TFP achieves success up to \(75.0\%\). Mechanistic analyses show that write-gain changes near manipulation events are about \(6\times\) larger than far non-event phases, and hidden-state interventions show that the belief causally modulates generated action chunks. These results suggest that compact, event-sensitive memory dynamics can improve VLA policies under occlusion, visual perturbation, and stage-dependent task structure.

Teleoperation is a key interface for controlling dexterous robotic hands and collecting demonstrations for imitation learning. Its effectiveness largely depends on kinematic retargeting, which maps operator hand motions to feasible and intuitive robot hand motions. Existing methods often require hand-crafted objectives, precise calibration, or global shape matching between human and robot hand spaces, making them sensitive to hand-specific tuning and less reliable across different dexterous hands. We propose AnyDexRT, a calibration-free retargeting method for intuitive dexterous teleoperation across human-like dexterous hands. AnyDexRT combines self-supervised fingertip correspondence learning with few-shot human guidance to anchor the mapping in task-relevant regions, and further refines pinch-related poses using a contact classifier. Experiments on diverse dexterous hands and real-world teleoperation tasks show that AnyDexRT improves retargeting quality, reduces manual tuning, and provides more intuitive and efficient control than prior retargeting methods. Project website: https://chenxi-wang.github.io/projects/anydexrt

Learning transferable visuomotor imitation policies that generalize across diverse manipulation tasks and adapt rapidly to new tasks from only a handful of demonstrations remains challenging. Most modern policies are trained end-to-end to map observations directly to low-level actions, offering little explicit structure for reusing and recombining behaviors across tasks and making transfer data-inefficient under limited supervision. We propose SkillPlug, a plug-in framework that augments an existing visuomotor policy with a skill-conditioning module and mines a shared, transferable skill library from raw multi-task demonstrations. SkillPlug learns skills via self-supervised objectives that promote compact, reusable, and non-redundant behavior-level primitives, forming a task-shared prior for compositional control. After skill mining, we keep the learned skills fixed and specialize to unseen tasks by fine-tuning only lightweight router and action head, enabling efficient adaptation without full end-to-end retraining. We evaluate SkillPlug on two simulation benchmarks and on a real robot, and observe that the mined transferable skills consistently improve both multi-task performance and few-shot adaptation. Overall, SkillPlug offers a scalable way to mine reusable skills that improve data-efficient generalization in robotic manipulation.

Vision-Language Navigation (VLN) enables UAV autonomous navigation in unknown environments by mapping language instructions to real-time visual inputs. Compared with GPS-dependent or pre-programmed navigation, VLN supports intuitive human-machine interaction and stronger environmental adaptability, requiring tight integration of high-level semantic reasoning and low-latency flight control.Existing methods suffer from structural misalignment between global multimodal understanding and sequential action generation, causing jittery trajectories and severe decision latency for long-horizon aerial navigation. To solve this issue, we propose FSD-VLN, a fast-slow dual-system architecture disentangling semantic reasoning and low-latency flight command generation.The framework has two asynchronous branches: a slow stream extracting stable semantic priors from pre-trained vision-language models, and a Diffusion Transformer (DiT) fast stream modeling cross-temporal action distributions to produce consistent flight outputs. We further introduce a time-aware adaptive optimizer to stabilize long-sequence training and reduce gradient oscillation.Large-scale low-altitude simulation experiments show FSD-VLN achieves up to 2X higher navigation success rates on unseen scenes than SOTA methods, while cutting single-action inference delay and total task runtime by over 50%. Our work validates the benefit of decoupled semantic-control modeling and provides a practical paradigm for long-horizon aerial VLN.

Making tradeoffs between execution latency and result utility (i.e., anytime computing) for adapting to dynamic operational requirements has been shown to enhance the performance of cyber-physical systems. In this work, we focus on enabling anytime computing for deep neural networks (DNNs) that process LiDAR point clouds for 3D object detection. We propose a novel method that enables multi-resolution inference for models that process point clouds as pillars or voxels, allowing the input to be dynamically scaled and processed at the resolution needed to meet timing requirements. Importantly, our memory-efficient approach requires the deployment of only a single DNN model, avoiding the need to deploy multiple models, each trained for a different input resolution. We also introduce a deadline-aware scheduler that selects the highest possible resolution for any given input by accurately predicting the execution time for all possible resolutions at runtime, which is challenging due to the irregularity of LiDAR point clouds. Experimental results on the nuScenes autonomous driving dataset demonstrate that our method significantly outperforms existing anytime computing approaches for LiDAR object detection. Finally, we deploy our approach in a simulated autonomous driving system, where it consistently enables collision-free navigation while avoiding unnecessary stalls caused by environmental complexity.

Egocentric human data offers scalable supervision for robot manipulation. However, behavior cloning entangles transferable content like objects, scenes, and task semantics, with non-transferable factors like human morphology, head motion, and behavioral style. We study whether World Action Models (WAMs) provide a better training signal by requiring policies to predict not only actions, but also how the scene evolves. The central question is what world representation best enables human-to-robot transfer. We hypothesize that an effective world target should abstract appearance, capture agent-invariant physical effects, and separate camera motion from environment change. We introduce EgoWAM, a controlled human-robot co-training framework that fixes the policy backbone, action head, and data mixture while varying only the world prediction target, comparing Pixel, DINO, and 3D motion flow. Across three real-world bimanual tasks, WAM co-training scales more effectively with in-the-wild egocentric human data than behavior cloning. Pixel-based prediction transfers weakly, while DINO and 3D flow yield substantial gains: DINO improves out-of-distribution object and scene generalization by up to 4x, and 3D flow improves in-domain performance by 20-30%. More details: https://gatech-rl2.github.io/egowam.github.io

Language-conditioned manipulation requires both precise contact-rich control and robust reasoning over language, scenes, and long horizons. End-to-end Vision-Language-Action (VLA) models provide strong local visuomotor skills, but they are trained on in-distribution task trajectories and often fail under deployment perturbations such as semantic retargeting, goal re-binding, spatial-layout shifts, and unstable local contacts. LLM coding agents provide complementary semantic and compositional reasoning, but purely analytic primitives struggle with irregular grasping, constrained placement, and articulated-object interaction. We present Harness VLA, a memory-augmented agentic framework that exposes a frozen VLA as a retryable contact-rich primitive and composes it with a small fixed library of analytic primitives for grounding, staging, transport, navigation, and release. Rather than expanding the skill library, the harness learns the operating range of these fixed primitives from task-specific execution traces, global success rules, and failure models. By lifting semantic re-grounding, non-contact execution, and VLA re-staging to the planner while reserving the frozen VLA for local contact-rich phases, Harness VLA extends pretrained VLAs beyond their original trajectory distribution without finetuning. Across perturbed tabletop, household kitchen, and clean-to-randomized bimanual manipulation, Harness VLA improves over the strongest relevant baselines by 38.6 and 25.4 percentage points on LIBERO-Pro and RoboCasa365, respectively, and reaches 58.4% on RoboTwin C2R.

We present FabriVLA, a lightweight Vision-Language-Action model for Precise Multi-Task Manipulation. FabriVLA combines an InternVL3.5 vision-language backbone with a flow-matching action head featuring gated self-attention across action tokens and shallow VLM layer fusion for enriched spatial context. The model is trained via single stage joint optimization from a pretrained VLM and randomly initialized action head. On the Meta-World MT50 benchmark spanning 50 diverse manipulation tasks, FabriVLA achieves a tier-average success rate of 90.0%, demonstrating that a compact VLA built on a 1B scale VLM can achieve strong performance without relying on multi billion parameter VLA backbones.

As human-robot interaction rapidly spreads in numerous fields, the subject of robot acceptance gains increasing importance. Visual similarity to the human body, as occurs for humanoids, is generally not enough to ensure acceptance in physical interaction, as acceptance directly links to comfort and ergonomics, which are measured in terms of the quality of the robot movement perceived by the human. This paper discusses the connection between comfort and similarity of the robot movement to the human one. By considering the kinematic characterization of human movement, this paper focuses on the time laws of such movements, wherein the end-effector path is prescribed. Based on the lognormality principle for modeling human movements, a human-likeness index is defined and used to provide an a priori characterization of trajectories. Such an index can be used to evaluate the performance of trajectory generation algorithms in producing human-like movements before they are actually executed. For validation purposes, 68 subjects are required to judge their comfort. The results of three experimental campaigns involving a physical interaction with a robot demonstrate a globally consistent trend between the preference in terms of perceived comfort and the distribution of the suggested human-likeness index.

The advent of video-action models offers a promising path for robot control. Nevertheless, we argue that repurposing video generative models designed for digital content creation is inherently inadequate for physical environments. To bridge this gap, we present LingBot-VA 2.0, a video-action foundation model built from the ground up for embodiment. Four core design principles showcase its evolution from LingBot-VA. (1) Departing from traditional reconstruction-focused VAEs, we introduce a semantic visual-action tokenizer, which aligns visual representations with both semantics and actions, improving instruction following and action precision in subsequent policy learning. (2) Given the strictly causal nature of temporal dynamics, we adopt a causal pretraining paradigm, training from scratch to circumvent the catastrophic forgetting that frequently occurs when adapting bidirectional architectures. (3) To meet the demands of high-frequency inference, our model employs a sparse MoE backbone, expanding model capacity without compromising efficiency. (4) Real-time closed-loop control is realized through an enhanced asynchronous inference scheme, which predicts future latents in parallel with action execution while re-grounding each rollout on the latest observation via learned forward dynamics. Real-world deployment validates LingBot-VA 2.0 as a robust foundation model, as evidenced by its few-shot generalization across complex manipulation tasks.

Modern robotic perception increasingly involves large-scale geometric optimization problems distributed across multiple robots or sessions. However, existing distributed solvers often depend on brittle hand tuning and primarily target rigid body pose graphs. To address this, we present DeepCORD, a learning-augmented framework for distributed factor graph optimization on general matrix Lie groups. By unfolding a parallel and accelerated Riemannian optimizer into differentiable iterations, DeepCORD learns a self-supervised feedback policy that dynamically adapts solver parameters according to the optimization phase and communication status. The resulting method enables adaptive distributed optimization over matrix Lie groups under both synchronous and asynchronous communication regimes. Extensive experiments on real-world $\mathrm{SE}$(3) pose graph optimization and $\mathrm{SL}$(4) projective submap alignment show that our method achieves lower objective values than existing distributed baselines on most benchmarks across realistic operating scenarios.

Keypoint tracking alone is insufficient for object interaction tasks such as sitting on a chair, wiping a board, or pushing furniture, where the robot can reach the correct pose without making meaningful physical contact with the object. We present CONTACTMIMIC, a learning framework that tracks explicit partlevel binary contact commands alongside keypoint trajectories. CONTACTMIMIC is made possible through the use of contact-following rewards and a trajectory augmentation scheme aimed at breaking the correlations between keypoint trajectories and contact labels. The resulting policy successfully decouples contact behavior from keypoint geometry, and achieves precise physical contact as well as contact-controllability (produce or suppress contact during deployment as desired). Simulation experiments across 10 diverse human-object interaction motions confirm that CONTACTMIMIC exhibits contact controllability that enables it to complete manipulation tasks without task-specific rewards, while also outperforming keypoint-only trackers on contact-relevant tasks. Ablations confirm the necessity of the proposed trajectory augmentation scheme and sim2real deployment validates contact controllability in the real world across 5 different motions. Video results are available on https://lixinyao11.github.io/contactmimic-page/.

Building general-purpose dexterous manipulation policies requires benchmarks that go beyond isolated tasks to systematically evaluate policies across diverse interaction modes, sensory conditions, and robot embodiments. However, existing benchmarks remain limited in task and data diversity, embodiment coverage, or controllable visual variation, hindering studies of cross-task and cross-embodiment generalization. We present DexVerse, a large-scale and modular benchmark for dexterous manipulation. DexVerse includes 100 tasks spanning a broad range of manipulation skills, including object grasping and relocation, articulated-object interaction, functional tool use, bimanual coordination, non-prehensile control, contact-rich behaviors, multi-goal execution, and long-horizon multi-stage task completion. It supports 3 robot arms and 6 dexterous hands, and is extensible to new tasks, assets, and embodiments. To evaluate visuomotor generalization, DexVerse provides configurable visual variations in textures, background, lighting, and camera viewpoints. We further provide a VR-based teleoperation interface and 3,180 demonstrations with synchronized proprioceptive, RGB, depth, point-cloud, and state observations. We benchmark representative methods, including Diffusion Policy, DP3, OpenVLA, and $\pi_{0.5}$, across 19 tasks. Results reveal substantial challenges in task generalization and visuomotor robustness, establishing DexVerse as a promising testbed for general-purpose dexterous manipulation. Project page: https://ycyao216.github.io/DexVerse.site

We present DreamCharacter-1, a lightweight post-adaptation framework that calibrates pretrained 3D foundation models toward high-fidelity, production-ready 3D character generation. Building upon a 3D foundation backbone, our pipeline incorporates three task-oriented components: (1) geometry post-training, which enhances fine-grained surface details through geometric preference optimization; (2) texture post-training, which synthesizes high-resolution textures and refines the appearance of occluded regions; and (3) inference acceleration, which enables scalable deployment. Extensive quantitative and qualitative experiments demonstrate that DreamCharacter-1 produces visually compelling and structurally robust 3D character assets, consistently surpassing state-of-the-art character generation methods.

Synthesizing realistic full-body human interactions with articulated objects is a fundamental challenge for embodied AI and graphics, with applications in robotics training and virtual agents. Existing models remain limited: some focus on simple activities with static objects, while others restrict attention to hand-only manipulation. This leaves open the problem of generating coordinated full-body motion that approaches, manipulates, and moves articulated objects in a realistic and generalizable way. The key difficulty lies in reasoning jointly about locomotion, fine-grained contact, and object articulation. Models must capture subtle hand-object correspondences that transfer across object geometries, while also producing seamless transitions from navigation to manipulation. At the same time, the scarcity of large-scale paired motion-scene data makes it difficult to generalize across diverse object positions and shapes. We introduce a text-conditioned diffusion model that addresses these challenges through three core ideas: an object-centric representation that unifies hand-object contact with object surfaces, a mixed-domain training strategy that balances locomotion and interaction, and a contact-based augmentation scheme that expands training diversity. Through experiments, our method demonstrated strong generalization to unseen object configurations, surpassing current state-of-the-art methods.

Tree growth determines how much CO2 is sequestered from the atmosphere and temporarily stored in woody biomass. At the same time tree growth is affected by increasing temperatures, more frequent drought periods, late frosts and other extreme events associated with climate change. While continuous measurements of radial (secondary) tree growth using dendrometers are well established, monitoring of shoot elongation (primary growth) has largely been neglected because suitable measurement techniques are lacking. As a result, the effects of climate change on primary tree growth remain insufficiently understood. This work aims at reconstructing native deciduous trees in 3D as a basis for measuring and monitoring shoot elongation over entire tree canopies. Here we explored the use of low-cost UAV photogrammetry and of a multi-camera CraneCam system under real-world conditions. Data were collected in two study areas over an entire growing season. We present sensor evaluations, photogrammetric data acquisition and processing strategies. A special focus is placed on the analysis of the resulting photogrammetric 3D point clouds in terms of accuracy, resolution and completeness. Results demonstrate 3D point accuracies of 5-6 mm for entire trees using consumer-grade UAVs weighing less than 250 g and a 3D reconstruction completeness between 92% and 98% depending on the UAV type. The paper introduces a novel 3Dprinted ground-truth branch to evaluate the capability to reconstructing fine-detail structures such as thin tree shoots. Finally, we discuss operational challenges and initial experiments towards a skeletonization of entire trees based on photogrammetric point clouds.

Vision Transformers (ViTs) remain vulnerable to localized adversarial attacks, e.g., adversarial patches, while recent test-time defenses mitigate them by suppressing image tokens with abnormally high attention scores. These defenses exploit a strong coupling between attention and adversarial effectiveness: adversarial tokens often need to attract substantial attention to influence the prediction. We introduce adversarial decoys, independently optimized image patches that redirect the attention, and therefore related defenses, toward selected target tokens. Rather than jointly optimizing misclassifications and defense evasion, our approach decouples the two objectives: the original adversarial region induces the incorrect prediction, while a separate decoy manipulates the attention ranking used by the defense. A layer-wise objective increases target-token attention and promotes these tokens above competing non-target ones. Since the decoy is optimized independently of the underlying attack, the method is attack-agnostic and can be easily integrated with any existing adversarial patch attack. Experiments on ImageNet across multiple ViT architectures and attacks show that decoys can redirect high attention scores away from the true adversarial region while preserving much of the attack effectiveness. These results reveal a fundamental limitation of using attention magnitude as an indicator of adversarial relevance.

Inferring latent physical properties from sensory observations is a fundamental challenge in machine perception. Among available sensing modalities, thermal imaging is particularly promising because temperature evolution is directly governed by heat-transfer physics and therefore encodes information about underlying thermophysical properties of a scene. Recovering spatially resolved thermophysical properties from thermal observations could transform applications ranging from digital twins and infrastructure monitoring to robotics and scientific imaging. However, existing thermal scene reconstruction methods can recover temperature fields in complex 3D environments without identifying the thermophyiscal properties that govern thermal evolution, whereas inverse methods provide physically interpretable parameter estimation but typically rely on simplified geometries and controlled experimental conditions. Here we introduce ThermoField, a framework that unifies thermal scene reconstruction and thermophysical parameter estimation through differentiable heat-transfer simulation. The proposed framework represents these quantities as spatially varying neural fields and constrains them through scene geometry, governing heat-transfer physics, and temporal thermal observations. We demonstrate that ThermoField jointly reconstructs geometry, estimates spatially varying thermal diffusivity, and predicts thermal evolution under previously unseen environmental conditions. By integrating neural scene representations with differentiable heat-transfer solver, the framework enables physically interpretable parameter inference in complex 3D scenes. Our results establish a bridge between thermal scene reconstruction and inverse heat-transfer analysis, providing a unified approach for geometry reconstruction, thermophysical property estimation, and predictive thermal simulation from thermal observations.

Object detection in geospatial scenes, such as satellite and aerial imagery, poses significant challenges due to the varying orientations and densities of objects, as well as the complex backgrounds inherent to remote sensing imagery. Traditional methods for oriented object detection have struggled to address issues such as angular discontinuity, fixed query sizes, and inefficiencies in handling sparse or cluttered scenes. In this paper, we propose LOGOS, a novel transformer-based approach that leverages textual prompts to guide the detection of oriented objects in aerial scenes. In particular, our proposed approach incorporates prompt-modulated content queries to dynamically adjust the model's focus based on the provided text, thereby improving object detection accuracy in complex environments. Empirically, extensive experiments on the DOTA dataset demonstrate that LOGOS outperforms existing state-of-the-art methods, particularly in densely packed and rotated object scenarios. Our approach offers a significant step forward in improving the robustness and scalability of oriented object detection in remote sensing applications.

Federated learning (FL) is a collaborative learning scheme to train deep learning models, where collaborating parties can consolidate their models without sharing local data with other parties, hence preserving data privacy. Nevertheless, when implementing FL in Industrial visual inspection (IVI), the constraints posed by limited data availability and the intricate nature of the inspection tasks significantly impact the performance of the resulting model. This paper introduces FedTR, a novel FL framework incorporating transfer learning designed for Autonomous IVI, focusing on the challenging task of identifying label defects through end-to-end text recognition. Transfer learning is a method that leverages the knowledge of a pre-trained model to adapt to a different dataset. FedTR initially trains the model using a publicly available dataset, after which performs the essential federated learning process with model fine-tuning on the distributed and limited private data. Extensive experiment results demonstrate the effectiveness and feasibility of FedTR on private ink cartridge datasets for label defect identification. FedTR achieves an end-to-end text recognition word-level accuracy of 95.5% and 94.2% on homogeneous and heterogeneous data respectively. Additionally, it attains performance levels that are on par with those achieved through centralized training.

Video relighting requires balancing long-form temporal consistency with a physically grounded understanding of light transport, which depends on accurate estimation of intrinsic scene properties such as materials, geometry, and illumination. Existing methods follow two paradigms: (1) reconstruct a video's photometric properties via inverse rendering and relight them to a target illumination via forward rendering, using physically-based rendering (PBR) or a neural renderer; these suffer from noisy reconstructions and struggle with hard-to-model effects such as global illumination. (2) Frame the task as generative video-to-video translation conditioned on relighting targets (a target environment map or text); this limits relighting control and temporal stability, since diffusion models struggle to translate long-form videos, and is constrained by the availability of input/relit training pairs. We propose LightCrafter, a hybrid pipeline that reformulates video relighting as video translation of a proxy video: rather than translating the input video directly to the target, we translate a PBR rendering of the input under the target illumination to the final target. This bakes illumination targets into the PBR proxy, removing the need to teach the diffusion model illumination concepts like environment maps, and enables more intricate lighting control while naturally providing long-form temporal consistency. We show PBR renders alone already outperform some prior art but struggle with effects like global illumination; to capture these, we leverage photometric priors in video generation models by post-training CogVideoX on synthetic video pairs and real-world unpaired videos. We outperform prior state-of-the-art on existing real-world relighting benchmarks and contribute a synthetic benchmark for further analysis. We will release our dataset, benchmark, metrics, and code.

Autoregressive video diffusion enables efficient streaming and long-horizon video generation, but repeatedly reusing generated latents as causal context can amplify temporal errors, resulting in flickering, motion jitter, and structural drift. In this paper, we investigate this failure mode from a spectral kinematic perspective and identify discrete latent acceleration as an effective signal for revealing unstable high-frequency temporal perturbations. To this end, we propose SAGA, a training-free \textbf{\textit{s}}table \textbf{\textit{a}}cceleration \textbf{\textit{g}}uidance approach for \textbf{\textit{a}}utoregressive video generation. SAGA integrates an acceleration domain spectral guidance objective based on finite-window Slepian projections with a structured autoregressive noise initialization strategy that suppresses short-range temporal correlations while preserving long-range motion structure. Without retraining or modifying the backbone, SAGA can be directly applied to existing chunk-wise autoregressive diffusion models, which is the prevalent setting for high-quality generation. Extensive experiments show that SAGA consistently improves temporal quality across multiple autoregressive diffusion models. On Self-Forcing, SAGA improves Temporal Quality from 97.30 to 97.91 and Image Quality from 69.60 to 70.51. Moreover, spectral analysis and human preference studies demonstrate that SAGA reduces temporal instability while maintaining visual fidelity.

Long-horizon robot planning requires jointly reasoning over semantic task structure and geometric feasibility. To successfully execute a task, a robot must decompose goals, select task-relevant objects, and sequence actions, while ensuring that plans satisfy spatial constraints such as limited free space and object collisions. In this work, we propose APIVOT, a VLM-based planner that adaptively interleaves language and visual thoughts for long-horizon planning. APIVOT learns to leverage language for semantic reasoning, while using visual thoughts as imagined future states for internal verification of geometric feasibility. On long-horizon kitchen tasks, APIVOT outperforms general-purpose VLMs and prior planning frameworks, achieving the largest gains in spatially constrained settings. We find that APIVOT learns meaningful modality selection behavior, demonstrating that adaptive interleaving of vision-language thoughts improves both planning success and reasoning efficiency.

End-to-end models that map multimodal inputs directly to future trajectories/maneuvers have emerged as an increasingly prominent research paradigm in autonomous driving. This class of models includes both Vision-Language-Action models and trajectory-generative planners. Unlike classic machine learning applications, autonomous vehicles operate in safety-critical and interaction-intensive environments where traditional open-loop imitation of expert demonstrations is not sufficient to ensure reliability. In particular, small execution errors can accumulate over time, while recovery behaviors are scarce in training data. In addition, long-horizon objectives such as safety and driving comfort are not captured by pointwise labels either. These limitations have motivated a shift toward post-training techniques, which further refine driving policies beyond pure imitation. This survey presents a unified view of post-training for autonomous driving by defining its scope and organizing the existing literature into four major families based on the form of supervision they use. For each family, we discuss its capabilities, limitations, and open challenges. We aim to facilitate a systematic understanding of this emerging area and stimulate future research on reliable and efficient post-training for autonomous driving.

Unmanned Aerial Vehicle (UAV) videos are widely used in traffic monitoring, urban management, and emergency rescue. However, existing UAV video perception mainly relies on box-level localization and trajectory association under predefined categories, making it difficult to simultaneously support flexible queries and fine-grained instance-level dynamic understanding in open scenarios. To this end, we introduce a new task, UAV Open-Vocabulary Video Instance Segmentation (UAV-OVVIS), which discovers targets in UAV videos according to open-vocabulary queries and outputs instance-level segmentation trajectories with globally consistent identities. Considering the scarcity of instance-level annotations in UAV scenarios, we propose AeroTrack, a training-free unified framework. AeroTrack centers on periodic open-vocabulary detection, short-segment mask propagation, and cross-segment identity unification, reusing existing visual foundation models to enable UAV-OVVIS. Based on this framework, we instantiate five AeroTrack variants and construct AeroVIS, an evaluation benchmark for UAV-OVVIS containing 9 UAV object categories and 8,279 trajectories. Experiments show that AeroTrack substantially outperforms existing general video instance segmentation methods in UAV scenarios and demonstrates strong open-vocabulary robustness and generalization. To support future research, we release AeroTrack and AeroVIS as a unified framework and benchmark for UAV-OVVIS.

The complementary information between RGB and IR images can significantly enhance object detection performance under extreme conditions. Existing methods prefer dual-stream CNN backbones built upon YOLO for feature extraction and focus on the design of feature fusion. In this paper, we introduce the Laplacian Decoupled Feature Enhancement block (LDFE) to fuse features from different stages of the dual-stream CNN backbone. By design, LDFE simultaneously considers the characteristics of modalities and structures for feature fusion by employing global-local decomposition, denoising, fusion, and reconstruction, sequentially. The LDFE first separates features into global and local components based on Laplacian Pyramid, and then performs denoising and fusion based on Global State Space Enhancement module (GS2E) and Local Convolutional Correlation Enhancement module (LC2E) separately. Specifically, the GS2E conducts a two-branch architecture for the main and auxiliary modalities. It dynamically suppresses noise in the main modality through cross-modal attention derived from the auxiliary modality, while employing a State Space Model to capture long-range dependencies within the global feature representations of the main modality. To obtain bidirectional interaction, the two modalities systematically alternate their main/auxiliary roles. Moreover, the LC2E suppresses noise in local features and leverages spatial and channel dimension along with triple convolution to extract fine-grained details for fusion. These innovative designs achieve a significant performance improvement, with mAP surpassing the SOTA methods 6.2%, 3.7%, 4.7%, 2.3%, 4.1% and 2.0% on M3FD, DroneVehicle, LLVIP, FLIR-Aligned, KAIST and VEDAI datasets,respectively.

Multi-query vehicle ReID aims to leverage complementary information from diverse views for robust feature learning. However, current methods suffer from simplistic feature fusion and thus easily ignores some important view information and cross-view relationships. To handle these problems, this work presents a novel approach called Mixture of Enhanced-View Experts (EV-MoE), which enhances the feature representation of each view and efficiently integrate the view-specific enhanced features by MoE, for robust multi-query ReID. In particular, we design a mixture of enhanced-view experts module, which consists of two parts including view-specific feature enhancement sub-Module (VFEM) and dynamic multi-view fusion sub-Module (DMFM). Moreover, we further introduce Multi-view Alignment Loss (MAL), which aligns features through bidirectional crossview contrastive learning and reconstruction constraints, addressing the challenges of consistency between multi-query features and single-image features. In addition, to evaluate multi-query ReID in real-world environments, we collect LCRI-1K, a largescale vehicle ReID dataset with 1,090 identities, 107,805 images, across 23,637 cameras, where each vehicle appears in an average of 67.5 cameras, providing a comprehensive benchmark to test the robustness in complex environments. Extensive experiments demonstrate the robustness of CAFNet in addressing the multiquery vehicle ReID problem. The code is available at https: //github.com/xiaozhen28/CAFNet.

Designing functional and aesthetically coherent floor plans requires exploring a vast space of possible room arrangements, a task that quickly becomes overwhelming for human designers. In this paper, we propose GRE-Diff, a controllable and interactive diffusion-based framework that automates the creation and editing of apartment floor plans under user-specified constraints. By combining AI-generated suggestions with real-time, human-in-the-loop editing, the system enables users to specify room types, room counts, boundary shapes, and editing operations through LLM-parsed instructions or GUI-based interaction. It then generates a diverse set of plausible and well-structured designs for refinement. At the core of our approach is Gaussian Room Embedding (GRE), a continuous latent representation that models each room as a spatial Gaussian distribution capturing its location and extent. Extensive experiments on the RPLAN dataset show that GRE-Diff produces high-quality, constraint-aware, and editable polygonal layouts, offering a practical step toward bridging AI-driven automation and human creativity in spatial design.

Event cameras offer microsecond temporal resolution, low latency, and high dynamic range, making them attractive for robotics. However, labeled event-camera data for a specific robot and scene is scarce and expensive to collect, which slows the development of event-based perception and control. We present EVIS: a physics-grounded event camera plugin for NVIDIA Isaac Sim that generates high-rate, fully labeled event streams directly inside a physics simulator. The plugin implements a faithful log-intensity contrast event model with per-pixel asynchronous reference updates; it migrates from a normal RGB camera with few changes and integrates into any Isaac Sim / Isaac Lab scene, inheriting the simulator's physics and frame-perfect ground truth. It is fully configurable, and offers an interpolation option that renders only sparse keyframes and synthesizes the in-between frames through bidirectional motion-vector warping, making real-time generation on a single GPU possible. Optional sensor noise and motion blur further narrow the gap to real cameras. The generated streams are directly usable by pretrained event networks for downstream tasks. Code repository: https://github.com/spikelab-jhu/isaac-sim-event-camera-plugin

We introduce VSRo-200, the first large-scale dataset for visual speech recognition (lip reading) in Romanian, comprising 200 hours of real-world podcast videos. All samples are annotated with pseudo-labels generated by a fine-tuned Romanian ASR model, while a subset of 100 hours is additionally transcribed by humans, enabling controlled analysis of supervision quality under a unified framework. Building on this dataset, we establish a benchmark for visual speech recognition in low-resource settings. We systematically study the impact of supervision quality, showing that while human annotations provide better performance at fixed data scales, pseudo-labels enable continued improvements through scalability. We further evaluate robustness under domain shift using curated out-of-distribution (OOD) test sets, and analyze audio-visual speech recognition (AVSR) under noisy conditions, where multimodal fusion significantly improves robustness compared to audio-only models. Finally, we demonstrate that representations learned on VSRo-200 transfer effectively to the LRRo benchmark for isolated word recognition, substantially outperforming previously reported results. Overall, VSRo-200 provides a new testbed for studying supervision, domain generalization, and multimodal fusion in low-resource visual speech recognition.

Generative video foundation models exhibit strong compositional priors, yet world-action models (WAMs) and video-action models (VAMs) often lose these priors after finetuning on robotic action data. We refer to this discrepancy as the video-action generalization gap. In this paper, we systematically investigate this gap by evaluating a comprehensive design space of VAMs, demonstrating that standard design choices yield no emergent explanation pattern. To explain this behavior, we introduce the Temporal Ratio (TR), an attention-based measure of how strongly the action head relies on future latent rollouts relative to the anchored current frame. TR has two key properties: first, a model's structural reliance on future-predictive latents, measured via TR, acts as a predictor of its compositional generalization capacity; second, it natively fluctuates based on task phase, shifting attention to future frames during planning and reverting to the present frame for precise manipulation. Finally, based on these findings, we propose an inference-time adaptive guidance method, which exploits this intrinsic feature attention pattern to dynamically amplify compositional video conditioning signals precisely when the policy relies on future rollouts. Evaluated on the LIBERO benchmark and real-world tasks, our approach mitigates the OOD-ID compositional generalization gap. More details: https://umishra.me/temporal-ratio/

The growing applications of facial recognition systems are accompanied by increasingly diverse security threats. Existing datasets lack detailed textual descriptions of forgery cues, leading most prior methods to treat face attack detection primarily as a visual recognition task. In this paper, building upon the large-scale MS-UFAD dataset which contains over 8 million attack images, we enrich each image with a fine-grained textual description of forgery cues. Furthermore, we propose a Dual Alignment Forgery Network(DAF-Net) to better leverage these textual information. Extensive experiments demonstrate that our approach extracts more generalizable and semantically meaningful forgery representations from attack images, outperforming both vision-only methods and approaches based on coarse-grained descriptions.

Whole slide images (WSIs) provide rich diagnostic information for computational pathology, but their gigapixel scale, stain variation, scanner differences, tissue artifacts, and limited expert annotation make robust model training challenging. This paper presents a multi-source Masked Autoencoder (MAE) framework, named ProsMAE, for histopathology representation learning. Tiles from Prostate cANcer graDe Assessment (PANDA), CAncer MEtastases in LYmph nOdes challeNge 2017 (CAMELYON17), and BReAst Carcinoma Subtyping (BRACS) are used for ProsMAE pretraining to expose the encoder to diverse tissue morphology and acquisition conditions. The learned encoder is transferred for International Society of Urological Pathology (ISUP) grade classification through ProsCLS, using a frozen encoder and a linear classification head. ProsMAE achieved a higher mean validation quadratic weighted kappa (QWK) than the vanilla MAE frozen linear-probe baseline under the evaluated disjoint PANDA split. Repeated-split evaluation remains necessary to further establish robustness across split compositions.

Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts. Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly, without access to source data or labeled targets, while mitigating two critical failure modes: catastrophic forgetting of source knowledge and error accumulation from noisy pseudo-labels over extended time horizons. In this comprehensive survey, we formally define the CTTA problem, analyze the diverse continual domain shift patterns that characterize different evaluation protocols, and propose a hierarchical taxonomy that categorizes existing methods into three families: optimization-based strategies (entropy minimization, pseudo-labeling, parameter restoration), parameter-efficient methods (normalization layer adaptation, adaptive parameter selection), and architecture-based approaches (teacher-student frameworks, adapters, visual prompting, masked modeling). We systematically review representative methods within each category and present comparative benchmarks and experimental results across standard evaluation settings. Finally, we discuss limitations of current approaches and highlight emerging research directions, including adaptation of foundation models and black-box systems, providing a roadmap for future research in robust continual test-time adaptation. We encourage visiting our repository at [https://github.com/sarthaxxxxx/Awesome-Continual-Test-Time-Adaptation](https://github.com/sarthaxxxxx/Awesome-Continual-Test-Time-Adaptation)

White Matter Hyperintensities (WMHs) are commonly observed in brain Magnetic Resonance Imaging (MRI) scans. They are associated with various neurological conditions, including vascular and inflammatory demyelinating diseases. Despite differing in etiology, WMHs from these conditions often appear similar on Fluid Attenuated Inversion Recovery (FLAIR) images. This similarity makes differential diagnosis challenging. In this work, we highlight the potential of combining attention-based segmentation with feature-driven classification. This approach supports more accurate and efficient classification between vascular and demyelinating white matter pathologies. For segmentation, we evaluate the effectiveness of attention mechanisms, specifically the Bottleneck Attention Module (BAM) and the Convolutional Block Attention Module (CBAM). We also test different architectures, particularly Attention U-Net. In addition, we explore advanced training strategies, such as patch-based learning and a 2.5D approach, to enhance lesion detection. After segmentation, we extract morphological features from the lesion masks. We then use them to classify WMHs based on their underlying cause. Our experiments utilize five publicly available datasets with diverse imaging protocols to promote model generalizability, despite limited sample sizes. The results suggest that attention-based segmentation and feature-driven classification offer a promising direction for discriminating vascular and demyelinating white matter lesions. Further validation in larger clinical cohorts is still needed.

Vision-language-action (VLA) models aim to map multimodal inputs to robot actions. However, most existing approaches struggle to cover complex dynamic scenarios due to treating all visual tokens uniformly and reasoning with human-selected factors, which lack mechanisms to emphasize task-critical evidence and ignore underlying factors. To address this issue, we propose LEEVLA, a VLA architecture for seeing what matters in Latent Environment Evolution that explicitly guides the model toward informative regions while preserving the structured evolution of latent world representations. To identify salient and instruction-relevant regions, we introduce drift-guided dynamic prioritization (DGDP), which combines dynamic position prioritization (DPP) with semantic drift guidance (SDG) to guide the VLA agent where to attend during training. On top of this, we introduce structured feature flow generation (SFFG), which models how these prioritized features should evolve in latent space via prototype-to-periphery (P2P) prediction, and a mutual-neighborhood contrastive (MC) loss to maintain topological consistency among neighborhoods. Together, DGDP and SFFG form a task-aware "where-how" training framework. Extensive experiments on VLA benchmarks show that LEEVLA consistently outperforms prior methods, confirming that explicit task-evidence guidance and structured latent reasoning are both crucial for scalable VLA. Our code is available at https://github.com/LyuQi127/LEEVLA.

Enhancing images to make them visually appealing is a persistent challenge in computer vision. Many deep-learning methods train models on paired datasets to replicate expert editing styles. However, these approaches struggle with two key issues: (1) interpretability and (2) a parametrization suitable for user adjustments. To address these challenges, we present NamedCurves+, an approach inspired by the concept of Color Naming, a universal set of familiar colors widely used in software tools for intuitive editing. Our method integrates color names into a learning-based framework, enabling global adjustments for each named color through tone curves. To address local image variations, we incorporate a transformer block that captures spatial dependencies, enabling context-aware edits across the image. NamedCurves+ enhances the retouching process's interpretability and supports user interaction, allowing flexible modifications of individual tone curves to refine the retouched image according to personal preferences. Extensive experiments on tasks such as image retouching, tone mapping, and exposure correction demonstrate that NamedCurves+ outperforms state-of-the-art methods. Notably, our approach is both explainable, as the tone curves explicitly represent how each color name contributes to the enhancement, and interactive, allowing users to customize the retouching process and achieve results tailored to their liking.

RGB-Thermal (RGBT) Video Object Detection (VOD) has gained significant traction due to its ability to overcome the limitations of conventional RGB-based VOD under challenging conditions. However, spatial misalignment commonly exists between RGBT image pairs. To address this, we propose a Dual-Correlation Hypergraph Network (DHNet) that captures high-dimensional complementary information by explicitly modeling two types of correlations: temporal correlation across consecutive frames and spatial correlation from cross-modal features. Specifically, we first design a Patch-based Spatial Alignment Module (PSAM) to sequentially align the multimodal features at the local region level. Subsequently, we introduce a Dual Hypergraph Fusion Module (DHFM), which constructs separate temporal and multimodal hypergraphs to enhance object discriminability through dual-correlation learning. Furthermore, the field currently lacks a large-scale, scene-diverse benchmark dataset for comprehensive evaluation. To address this gap, we construct DVT-VOD1000, a large-scale RGBT VOD dataset containing 1,000 video sequences with 103,464 RGBT image pairs. The dataset covers diverse scenarios, including campuses, parks, transportation, rural areas, night scenes, rain, and snow. Comprehensive experiments on VT-VOD50 and our DVT-VOD1000 demonstrate that DHNet achieves state-of-the-art detection accuracy. The dataset and source code will be made publicly available on https://github.com/tzz-ahu/ to support academic research.

Vision-language alignment, the stage that bridges pretrained vision encoders and large language models, is widely treated as a form of pretraining requiring full-parameter updates. We challenge this view and investigate what happens when low-rank adaptation is applied to the LLM during this stage instead. We find that low-rank alignment not only reduces computational costs but also outperforms full-parameter alignment on most benchmarks. To understand this phenomenon, we systematically characterize the implicit biases introduced by low-rank adaptation during alignment. Empirically, we find that low-rank alignment shifts model behavior from hallucinatory to conservative and preserves per-token linear separability of visual features that full-parameter alignment disrupts, a phenomenon we term LS-curse. Geometrically, low rank aligned models exhibit more homogeneous and structurally stable visual representations, maintaining modality-specific knowledge rather than prematurely fusing entity-level semantics. Theoretically, we establish two theorems showing that low-rank alignment induces preferences for parameter subspaces with flat gradients and feature subspaces robust to perturbations, providing a principled explanation for the observed structure-preserving behavior. Extensive experiments cover ablation over 100 alignment configurations, three families of low-rank operators, and various rank, encoder, and other settings.

This paper studies the problem of learning a joint distribution from marginal observations, which is inherently ill-posed due to the ambiguity of feasible couplings. We propose LUD-MSR, a latent-variable probabilistic framework that models the joint distribution via auxiliary representations and optimizes evidence lower bounds using only marginal data. Under mild assumptions, we establish an upper bound on the distribution approximation error. This analysis reveals a trade-off in representation learning between domain consistency and information preservation. To address this trade-off, we introduce a Multi-Scale image Representation (MSR) mapping that exploits structural similarity at coarse scales while suppressing domain-specific variations. We show that MSR achieves a more favorable balance of this trade-off compared to existing approaches. Experiments on real-world denoising benchmarks, including cryo-electron microscopy (cryo-EM), demonstrate the effectiveness of the proposed framework.

Large-vocabulary instance segmentation is constrained by long-tailed category distributions and fine-grained inter-class ambiguity. While data synthesis offers a promising alternative, current paradigms have complementary limitations: text-to-image (T2I) methods inherit noisy pseudo-labels and struggle on rare classes, whereas copy-paste methods compromise contextual realism. To address these issues, we propose a hybrid pipeline coupling T2I generation with context-aware image-to-image (I2I) editing. The T2I branch provides broad category and scene diversity, while a teacher-student scheme ensures label reliability by selectively retaining only prompt-specified categories. To strengthen supervision for rare classes, we introduce VRAIN (Verified Rare-class Augmentation via INstructed editing), a novel I2I editor. VRAIN inserts high-confidence instances at semantically appropriate locations within in-the-wild scenes, yielding semantically coherent and visually natural edits that reduce domain gaps and enable targeted augmentation. On the LVIS benchmark, our method surpasses existing baselines, improving overall AP by up to +4.0 points and rare-class AP by up to +9.5 points, while scaling effectively with backbone capacity. Our project page is available at https://seokhunchoi.github.io/TMI

Progress in colonoscopy polyp segmentation is routinely reported through leaderboard comparisons on a small set of public benchmarks. We argue that this apparent progress is difficult to verify: a systematic audit of \textbf{27 papers} published between 2015 and 2026 reveals three structural problems in how the community evaluates models. \textbf{First}, 25 of 27 papers \textit{omit the Hausdorff distance}. Hausdorff distance is a boundary-accuracy metric with direct clinical relevance for detecting flat or small polyps, and is a standard in radiotherapy segmentation. \textbf{Second}, at least five \textit{incompatible train/test split protocols} co-exist across papers reporting results on the same two datasets (Kvasir-SEG and CVC-ClinicDB), making published Dice scores non-comparable even when they appear in the same leaderboard column. \textbf{Third}, 26 of 27 papers make \textit{performance claims without any statistical significance test}. Strikingly, four papers published \emph{after} the Metrics Reloaded framework~\cite{metricsreloaded2024} (Maier-Hein et al., \textit{Nature Methods} 2024) perpetuate these same problems, suggesting that general-purpose metric guidance has not yet reached the colonoscopy sub-community. To show these problems are not merely cosmetic, we re-evaluate five representative models under three controlled protocols with a single uniform scorer, and find that the reported metric conceals large boundary and recall failures, that the ``best'' model changes with the metric, and that near-tied rankings reverse across random splits. We propose a five-point \textbf{Polyp Segmentation Reporting Checklist}~(PSRC) as a lightweight, domain-adapted corrective.

The privacy requirements of medical data and its substantial variations across organs and modalities hinder the clinical implementation of medical AI. Federated learning (FL) is a feasible approach to overcome these challenges. Due to the continuous emergence of FL algorithms and the highly heterogeneous nature of medical data, objectively evaluating their performance in real-world clinical settings remains difficult. Therefore, a comprehensive federated medical imaging benchmark, serving as a unified evaluation standard, is crucial for advancing the technology toward reliable clinical application. Existing federated medical imaging benchmarks have not yet adequately incorporated state-of-the-art algorithms, are limited to data from single organs or modalities, and overly emphasize model accuracy, making it difficult to comprehensively assess the overall efficacy of FL in real-world medical environments. To address these challenges, we developed the MobenFL benchmark. This benchmark integrates 20 cutting-edge FL algorithms and 22 medical imaging datasets, covering 12 critical organs across the human body, surpassing existing benchmark in breadth. In terms of evaluation dimensions, MobenFL not only assesses performance but also systematically incorporates key metrics such as algorithmic efficiency and privacy protection capabilities. Additionally, it conducts specialized evaluations for complex real-world clinical scenarios involving different diseases, devices, and imaging modalities, thereby providing a comprehensive and in-depth evaluation framework for the clinical application of FL in the medical field.

Large language model (LLM)-based lossless image compression methods typically represent pixel data through the native text interface of a pretrained model, converting pixel values into token sequences that the LLM processes through its vocabulary head. This design shows that pretrained language models can provide probability estimates for image coding, but it also couples compression to tokenizer behavior, vocabulary-specific numeric tokens, and model-family-specific adaptation. In this paper, we present LUMI (LLM-based Unified Model-agnostic lossless Image compression), a tokenizer-agnostic framework for lossless RGB image compression with frozen LLM backbones. LUMI replaces pixel-as-text tokenization with a pixel embedding module that maps raw intensity and channel information into the continuous embedding space of the LLM. It further introduces intra-patch position encoding to retain two-dimensional spatial structure after flattening, and uses a 256-way prediction head to produce probabilities over the native pixel alphabet. Only the pixel embedding, position encoding, soft-prefix parameters, and prediction head are trained, while the LLM backbone remains fixed. Experiments on natural, medical, and remote-sensing image benchmarks with LLaMA, Qwen, and Gemma backbones show that LUMI provides a unified interface across tokenizer families, achieves competitive compression rates, and improves cross-domain robustness over tokenizer-based LLM compression baselines. These results formulate LLM-based lossless image compression as pixel-space adaptation of frozen foundation models rather than tokenizer-specific language-symbol modeling.

Photorealistic Style Transfer (PST) aims to transfer the color and tonal style of a reference to a content image while strictly preserving its structural integrity. However, existing deep learning-based methods inherently suffer from semantic entanglement caused by pre-trained image encoders, leading to unnatural spatial distortions. Moreover, current pixel-level mapping paradigms often ignore color gamut topology, resulting in color banding, while also lacking the multimodal capability for intuitive text-driven control. To address these bottlenecks, we propose StatLUT, an innovative multimodal framework for 3D LUT generation. First, we bypass traditional encoders and introduce a Lab-Extractor to derive spatially-agnostic statistical features, fundamentally decoupling color distributions from structural semantics to ensure artifact-free rendering. Second, we formulate LUT generation as a Transformer-based Seq2Seq translation task, utilizing a Multi-dimensional Residual Mapper (MR-Mapper) to predict topologically smooth 3D LUTs. Finally, to break the single-modal barrier, we propose the H-Diffuser, a lightweight Diffusion Transformer that directly synthesizes statistical features from natural language prompts, enabling flexible text-driven color grading. Extensive experiments on standard benchmarks demonstrate that StatLUT significantly outperforms state-of-the-art methods in both visual quality and quantitative metrics, pioneering a highly robust and flexible paradigm for multimodal photorealistic style transfer.

Event-based lip reading has recently emerged as a promising direction for visual speech recognition, benefiting from the high temporal resolution and motion sensitivity of event cameras. However, existing methods typically perform spatial compression before sufficient temporal modeling, which may suppress sparse and localized motion trajectories that are crucial for distinguishing similar lip movements. Moreover, most current approaches optimize temporal representations mainly at the word-classification level, leaving the underlying articulatory structure weakly constrained. To address these limitations, we propose a temporally enhanced framework for event-based lip reading. First, we introduce Trajectory-Aware Differential Aggregation (TDA), which performs local temporal modeling at each spatial location before adaptive spatial aggregation. Second, we propose Viseme-Guided Aggregation (VGA), a unified temporal module composed of a CTC decoder and a viseme-guided gated aggregation branch, which injects viseme-aware sequence supervision and improves final temporal aggregation for word recognition. Third, we incorporate an EMA teacher--student training strategy to enhance robustness under strong event perturbations. Experiments on the DVS-Lip benchmark verify the effectiveness of the proposed design, and extensive ablation studies further validate the contributions of TDA, VGA, and teacher--student consistency. Qualitative decoding results also demonstrate that the proposed CTC-based temporal modeling learns meaningful viseme-aware structure from event streams.

Deploying classifier-free guidance (CFG) diffusion models under real-world compute budgets requires quantization, yet existing post-training quantization (PTQ) methods treat CFG models as single-branch networks, ignoring the paired conditional/unconditional structure that CFG inference fundamentally relies on. This structural blind spot has two consequences. At the system level, the two-pass CFG execution pattern imposes a latency overhead that parameter-count and bit-operation metrics conceal entirely, and commodity INT8 inference stacks fail to realize the theoretical efficiency gains that BOPs calculations promise. At the algorithmic level, calibrating against the guidance gap alone admits an exact null space: a quantized model can achieve perfect gap-fidelity diagnostics while the unconditional branch drifts arbitrarily, corrupting every guided prediction at inference time. This paper terms this the branch-drift trap, proves its existence analytically, and confirms it empirically through a false-positive result in which the best-calibrated model by standard diagnostics simultaneously produces the worst sample quality. To close the trap, Guidance-Aware Mixed Precision (GAMP) is proposed, which calibrates directly on the guided prediction, derives per-layer activation-bit sensitivity from guided-output degradation, and allocates bits via a greedy knapsack -- provably preventing unconditional branch drift by construction.

We study 4D generation to synthesize temporally coherent sequences of 3D geometry for animation and content creation. In contrast to existing SDS-based optimization methods and video-driven animation approaches, we adopt a skeleton-driven animation framework aligned with standard industrial pipelines, which enables explicit control and editing. To this end, we propose SkelGen4D, a weakly supervised feed-forward framework for text-driven mesh animation that generates explicit skeleton motions without requiring per-frame skeleton annotations. SkelGen4D first recovers temporally consistent pseudo-skeletons from animated meshes via differentiable fitting, and then generates text-conditioned skeleton motion sequences in a feed-forward manner, further refined with Motion-GRPO to ensure temporally coherent, physically plausible, and articulated animation. We evaluate our method on two large-scale benchmarks, Truebones Zoo and Diffusion4D. Our results show that our weakly supervised skeleton modeling matches or surpasses fully supervised baselines while scaling to diverse object categories for high-quality text-driven mesh animation. Further, our method supports flexible motion editing and is aligned with standard animation production pipelines.

Slot attention is a powerful framework for object-centric learning, decomposing visual scenes into latent slots through iterative competitive attention. However, existing methods share two critical limitations: they decompose scenes into a flat set of slots at a single granularity, and this decomposition is based on appearance rather than semantics. Yet humans understand scenes through semantic hierarchies: separating foreground from background, recognizing object categories, and identifying individual instances. Crucially, such semantic hierarchies cannot emerge without supervision, because category names are human constructs, not visual patterns. We propose Hierarchical Slot Attention (HSA), which learns multi-granularity semantic scene decomposition from a single model. HSA decomposes scenes at three levels: holistic (foreground/background), semantic (object categories), and panoptic (individual instances). Using only 10\% labeled data, combined with hierarchical alignment loss, HSA learns all three levels jointly. We further introduce grouping purity and containment to measure whether the hierarchy is encoded in representation space, not just output masks. Experiments on COCO and PASCAL VOC demonstrate that HSA outperforms the strongest flat baseline by up to \textbf{$+$41.5} ARI at holistic, \textbf{$+$14.6} at semantic, and \textbf{$+$10.4} at panoptic level on COCO, with even larger gains on Pascal VOC, while requiring a single model instead of three. Code will be made available upon acceptance.

Dynamic scene reconstruction remains challenging due to the heterogeneous and spatially varying nature of real-world motion. Although recent 3D Gaussian Splatting methods have introduced diverse deformation formulations for dynamic novel view synthesis, each method typically relies on a single deformation model within its representation, which limits robustness across diverse dynamic scenarios. In this work, we study a fundamental problem-multi-deformation modeling for dynamic 3D Gaussian representations-under two distinct integration constraints that differ in when and how multiple deformation experts interact during training. From a Mixture-of-Experts (MoE) perspective, we view multi-deformation modeling as the problem of combining multiple specialized deformation models within a unified 3D representation. We first introduce Mixture of Deformation Experts (MoDE), which integrates multiple deformation experts directly into the deformable Gaussian Splatting pipeline through joint optimization. In MoDE, experts operate on a shared canonical Gaussian representation, enabling multi-deformation modeling without introducing additional training stages or modifying the original optimization schedule. In contrast, we further present Mixture of Experts for Dynamic Gaussian Splatting (MoE-GS) under a different integration constraint, where deformation experts are optimized independently and combined through a separate routing stage. As a result, expert interaction occurs over non-canonical Gaussian representations after individual optimization. Together, these two approaches provide alternative strategies for multi-deformation modeling, clarifying how integration constraints shape the design and behavior of deformation experts in dynamic 3D Gaussian representations. Our code is available at: https://github.com/cvsp-lab/MoE-GS-studio.

Unmanned aerial vehicles (UAVs) increasingly rely on visual grounding capabilities to localize task-relevant targets from diverse instructions in complex aerial scenes. Existing referring expression comprehension (REC) benchmarks and methods, however, are largely built around text-only queries and single-object outputs, which limits their applicability to practical UAV scenarios involving reference images, multimodal instructions, absent targets, and multiple valid target instances. To address this gap, we introduce \emph{Universal Referring}, a generalized UAV referring task that jointly expands the query modality and the output cardinality. We construct \emph{UniRef-UAV}, a multimodal benchmark that supports text-only, image-only, and text+image queries with modality-dependent target cardinality, where text-only and text+image queries admit no-target, single-target, and multi-target grounding while image-only queries focus on existence-aware single-instance grounding. It also provides in-domain and cross-domain evaluation protocols for visual-query generalization. We further present \emph{UAV-URNet}, a detection-style baseline that maps heterogeneous queries into a shared query space and predicts variable-size target sets through set prediction. Extensive experiments show that UAV-URNet provides a stable and reproducible baseline with more consistent no-target discrimination and a more lightweight, reproducible implementation than large general-purpose MLLMs. Additional domain analysis, query-representation analysis, and ablation studies demonstrate that multimodal queries help reduce visual-query ambiguity and promote a more unified query--target alignment space. The annotations, visual query crops/images, train/validation/test splits, evaluation scripts, and baseline code will be made publicly available to facilitate reproducible research.

Forecasting the future anatomy of slow-evolving neurodegenerative diseases could enable earlier, more targeted intervention and improve clinical trial design, but it remains challenging because true progression signals are subtle in longitudinal MRI. In this low-signal regime, transferring modern generative sequence models directly is unreliable: training is dominated by stable baseline anatomy and confounded by dense, sample-specific nuisance variation. We first provide a theoretical analysis that explains these failures through two modes. Identity collapse occurs when optimization is driven toward reproducing the current anatomy, which prevents the model from learning faint temporal change. The continuous interpolation trap arises when standard smooth networks cannot separate localized biological drift from pervasive noise, which leads to spurious changes that diffuse across the volume. To address both issues, we propose Latent Drift, a progressive generative framework that learns change in a compressed semantic representation rather than synthesizing full-resolution anatomy. This design removes pixel-level identity from the prediction target and concentrates model capacity on progression-relevant dynamics. We further apply Finite Scalar Quantization to the learned change representation, which suppresses small, high-frequency nuisance fluctuations while preserving consistent structural drift. Experiments on longitudinal 3D brain MRI show that Latent Drift improves patient-specific neuro-forecasting over diffusion and autoregressive transformer baselines across generative fidelity and clinically relevant evaluation metrics. Project page: \href{https://cutepkq.github.io/latent-drift}{https://cutepkq.github.io/latent-drift}.

Accurate poverty mapping using satellite imagery is often hindered by (i) noisy and sparse survey-derived supervision, (ii) image quality issues such as cloud cover and image corruption, and (iii) lack of explicit spatial structure in image-only models. Building on the KidSat framework, we develop an enhanced pipeline that improves predictive accuracy via refined data preprocessing, systematic image quality assessment, and mathematically defined geographic encoding. First, we refine the fine-tuning target matrix by resolving high-cardinality sparsity and reducing one-hot dimensionality from 103 to 51 via DHS re-aggregation. Second, we introduce a simple two-stage quality-screening procedure to filter heavily clouded or corrupted observations. Third, we fuse DINOv2 visual embeddings with Spherical Harmonics (SH) location features. Across extensive experiments, these changes reduce MAE from 0.2167 to 0.1759, corresponding to an 18.83% relative reduction on the cluster-level severe-deprivation proportion scale. When extended from 16 to 33 African countries, the best-performing configuration achieves an overall MAE of 0.1658. We find that SH features consistently improve performance over the image-only backbone, whereas higher-capacity coordinate Multi Layer Perception augmentation (SH+SIREN) can underperform without carefully designed objectives. Finally, gradient-boosted tree heads (XGBoost/LightGBM) most effectively exploit nonlinear interactions in the fused visual-geographic representation. These findings provide a scalable and principled recipe for improving satellite-based socioeconomic predictions using only publicly accessible data.

Background and Objective: Quantitative analysis of cell dynamics is central to modern biological research, providing critical insights into immune cell interactions, disease progression, and drug mechanisms. Automated cell tracking in time-lapse microscopy remains challenging due to noise, morphological variations, overlapping cells, and dynamic events such as divisions and fusions. Methods: We present ARGUS, a framework for Accelerated, Robust, General, and Unsupervised Cell Tracking Solutions. ARGUS combines adaptive cell detection, dense Farneback optical-flow prediction, frame-to-frame linear assignment, and a sequence-level tracklet-refinement step that reconnects trajectory fragments across short temporal gaps. Results: On publicly available Cell Tracking Challenge datasets, ARGUS achieved detection accuracy of 0.905-0.971 and tracking accuracy of 0.897-0.964, with runtimes within 1 minute (5-6 seconds for 3 frames). Conclusions: ARGUS is a modular, interpretable framework that can be adapted to different imaging modalities and biological applications without training data or GPU infrastructure. The implementation is publicly available at https://github.com/Gitinc/argus

In computational vision science, Convolutional Neural Networks (CNNs) have emerged as a popular model of biological vision because of the alignment they can exhibit with neural and behavioral data in humans and animals. However, it remains unclear to what extent this alignment persists for visual tasks that extend beyond the canonical object recognition paradigm based on well defined semantic content. In this study, we diverge from the common object-centric view by focusing on another aspect of vision: texture perception. We consider textures of different complexity generated with three different algorithms from the same source images. Using a rank-based statistic, we quantify the information encoded in the internal representations of a CNN and three Vision Transformers (ViTs), and we compare the similarity of these representations to those inferred from human psychophysics data. We find that the representation of textures is aligned in different ViTs, but not between the ViTs and the CNN; that ViTs form similar representations for textures of different complexity; that human performance in recognizing textures can be better predicted from ViTs representations rather than CNN representations. Taken together, these results suggest that ViTs may capture more faithfully than CNNs how texture patterns are visually processed by humans, and that the representations of texture stimuli in computational models may be driven by the network architecture.

Vision-Language-Action (VLA) models have advanced end-to-end autonomous driving. However, existing methods either lack comprehensive world cognition or suffer from fragmented world foresight, inherently confining these models to reactive driving. To address this limitation, we propose WCog-VLA, a novel dual-level World-Cognitive VLA framework that successfully bridges semantic world forecasting with generative world evolution to achieve proactive autonomous driving. At the semantic level, WCog-VLA unifies world cognition and reasoning by incorporating 3D spatial perception and injecting agent tokens to capture the world dynamics, while concurrently enabling Game-theoretic Chain-of-Thought (Game-CoT) reasoning. At the generative level, we introduce the Aligned Decoupled Diffusion Transformer (ADDT) as a powerful generative world model that synthesizes physically-plausible joint multi-agent trajectories. Through scene representation alignment, ADDT reduces the number of denoising steps required and thus significantly accelerates inference. To facilitate strategic reasoning, we further construct a large-scale dataset featuring 85k Game-CoT annotations. Extensive experiments on the NAVSIM benchmark demonstrate that WCog-VLA achieves a State-Of-The-Art (SOTA) PDMS score of 92.9.

Quantifying how mirror-symmetric an image is about a given axis (symmetry scoring) underpins applications from visual aesthetics to medical imaging, yet proposed scoring methods have never been compared on a common, statistically grounded protocol. We benchmark 13 scoring methods (nine collected from literature, four introduced here) spanning from classical features to frozen deep features, across four single-axis and five multi-axis datasets under a reflection-exact protocol with a chance-anchored, significance-tested discrimination skill. Deep backbones perform best on single-axis and harder multi-axis protocols. However, a classical histogram-of-oriented-gradients (HOG) descriptor trails the best frozen-network readout by a small (but significant) margin, is not statistically separable from the runner-up (a CNN-filter measure), and runs ~300x faster on CPU. Our results show that discrimination concentrates in mid-scale oriented features, where deep backbones peak at a low or mid stage, and HOG peaks at a mid cell size. Among existing methods, frozen deep features thus offer little over a tuned classical descriptor for measuring symmetry; whether task-trained deep scorers can do better remains open. We release the scorers and harness in imgsym, an open toolkit for image symmetry detection and measurement.

Referring Image Segmentation (RIS) aims to segment image regions specified by natural language, enabling fine-grained and controllable visual understanding. Extending RIS to endoscopic imagery, however, presents unique challenges, including scarce high-quality annotations and complex, domain-specific image-text relationships. Although recent vision-language models demonstrate strong cross-domain alignment, they often fail to capture fine-grained textual cues in endoscopic settings, resulting in suboptimal performance and limited generalization. To address these challenges, we introduce ReferEndoscopy, a large-scale benchmark for RIS in the endoscopy field. Building on this dataset, we propose the Attribute Retrieval-based Endoscopic-RIS (AR-ERIS) framework for open-vocabulary endoscopic compositional referring segmentation. AR-ERIS leverages attribute retrieval for open-vocabulary endoscopic compositional referring segmentation and is pretrained on the curated ReferEndoscopy dataset, achieving state-of-the-art performance with strong generalization across both simulated and real-world endoscopic data. The dataset and code will be publicly released upon completion of the review process.

Large-scale and diverse datasets are needed to train AI models to take real-time decisions for autonomous vehicles (AVs), an intelligent transportation system (ITS) application. Pedestrian intention and trajectory prediction are critical models used in AVs, requiring datasets involving diverse pedestrian images. Unrestricted access to these datasets imposes serious security risks, like identity theft and pedestrian tracking. The challenge is to apply privacy preservation procedures while maintaining the image attributes needed to train the models. Existing privacy methods may preserve the pedestrian's privacy, but degrade the image usability, which hinders the models' effectiveness. This work's focus is to implement a five-stage pipeline to protect pedestrians' privacy through face swapping while keeping the essential facial attributes intact. It should be tailored to satisfy the privacy needs of the Egy-DRiVeS dataset. Moreover, Roop and Ghost-v2 face-swapping models are evaluated. Provenly, Roop outperforms Ghost-v2 in various aspects, as will be discussed. Consequently, Roop is the face-swapping model to be used in the pipeline to strike the balance between pedestrian privacy via identity concealment and data usability via facial attribute preservation.

Gaussian splatting is the current state-of-the-art for dense, deformable 3D anatomy reconstruction in robot-assisted minimally invasive surgery (RAMIS); however, most pipelines are offline and depend on accurate camera trajectory priors (often from robotic kinematics), limiting applicability when priors are missing or noisy. To address these limitations, we propose Track2Map, an online 3D Gaussian Splatting pipeline that jointly optimizes camera trajectory and 3D deformable scene representation directly from surgical video. Track2Map is therefore capable of robust 3D reconstructions when camera trajectory priors are either absent or noisy, and due to its online nature it effectively works as a Simultaneous Localisation and Mapping (SLAM) method. To stabilize optimization in the presence of tissue motion and ambiguous visual cues, we introduce a track-anchored deformation initialization using dense 2D point tracks. Track statistics are further utilized to disentangle camera motion from scene deformation by detecting static camera periods and reducing drift during incremental mapping. Experiments on StereoMIS show improved reconstruction quality and camera trajectory against competing SLAM methods, as well as compared to non-SLAM methods that utilize camera trajectory priors. The code is available at https://track2map.github.io/.

Current Unified Large Multimodal Models (ULMMs) support interleaved multimodal reasoning through textual reasoning and intermediate visual states, but typically generate each visual state as a full image. This full-image generation paradigm introduces substantial visual-token redundancy and dilutes supervision on sparse yet reasoning-critical state transitions. We propose DeltaV, a ULMM that replaces full-image generation with visual updates. Conditioned on historical visual states, DeltaV incrementally predicts compact update tokens that capture the visual changes across reasoning steps, avoiding repeated modeling of unchanged content. To align the token budget of each update with the magnitude of visual change, DeltaV introduces a temporal similarity (TSIM) Router, which stops allocating tokens once the marginal reconstruction gain falls below a threshold. To support more diverse and generalizable reasoning, we further construct StructCoT, a large-scale interleaved multimodal reasoning dataset with 1.05M samples spanning 44 task domains. Experiments show that the visual-update paradigm reduces newly generated visual tokens by 55.6\% on average without compromising reconstruction fidelity, and improves multimodal reasoning by 3.3\% over full-image generation. Trained with StructCoT and large-scale multimodal data, DeltaV-2B further outperforms substantially larger open-source models by 8.4\% on in-domain multimodal reasoning evaluations and surpasses the comparable-scale Qwen3-VL-2B by 5.9\% on external multimodal reasoning and understanding benchmarks. Code, models, and StructCoT will be released at https://github.com/Pengjie-W/DeltaV.

Determining agricultural potential is fundamental to sustainable land management and agricultural planning. Remote sensing data is increasingly valuable as an avenue for agricultural potential due to the cost of traditional methods (surveys, in-situ measurements, soil testing, etc). ImageCLEF AI4Agri 2026: Subtask 1 is concerned with the prediction of viticulture potential in Southern France. The DS@GT ARC's submission for Subtask 1 introduces an ensemble of U-Net and a Geospatial Foundation Model (Prithvi-2.0). Our best model achieved a $\pm$1 accuracy of 68.32 on the leaderboard, ranking 2nd among 7 teams. The implementation for this work is publicly available at https://github.com/dsgt-arc/imageclef-ai4agri-2026 .

Vision-language models excel at video captioning, yet typically generate descriptions that fail to capture individual viewers' attention. We propose VEGAS (Video caption Evaluation via GAze Score), a training-free metric that leverages test-time gaze to sample personalized, attention-aligned text. It is a cross-modal, information-theoretic metric that quantifies how well a candidate caption matches a viewer's focus. To evaluate VEGAS, we curate a dataset of egocentric activities and instructional slides paired with synchronized gaze and reference annotations. We then select captions based on VEGAS via rejection sampling without model retraining. Experiments show that VEGAS-selected captions align significantly better with human focus and improve downstream caption-to-video retrieval, demonstrating the practical utility of incorporating viewer attention during inference.

Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing. However, they repeatedly feed all historical visual and textual inputs into a shared context window, limiting long-horizon multimodal dialogue due to visual token explosion and unreliable cross-turn referencing. We propose a Cognitive-structured Multimodal Agent that externalizes visual information into an Episodic Visual Memory and selectively reactivates relevant episodes during reasoning. The agent consists of a Perceptual Abstraction Engine for structured visual abstraction, a Cognitive Retrieval Engine for cross-turn memory retrieval, and a Multimodal Executive Controller for autonomous task inference and action planning. To address the lack of turn-level retrieval supervision in existing datasets, we develop a Unified Scenario Engine that programmatically generates structured multi-turn conversations with fine-grained retrieval annotations, enabling reinforcement learning to optimize abstraction and retrieval policies. We also construct a long-horizon visual-dialogue benchmark stratified by difficulty to evaluate episodic visual recall. Our 8B agent achieves 91.4% retrieval accuracy over 20-turn sessions, surpassing 32B baselines by +8.2% while nearly halving per-turn inference time (23.1s -> 12.7s). We further present the Cognitive-structured Multimodal Agent Harness (CMA-Harness), a tool-augmented deployment of the same cognitive structure integrating persistent multimodal memory, web access, image generation/editing/composition tools, and OpenAI-compatible serving. Structured memory and modular decision-making offer a more scalable, efficient paradigm for long-horizon multimodal agents than monolithic parameter scaling. Code: https://github.com/caseclose/cma-harness ; Project page: https://caseclose.github.io/cma-harness/

Accurate prognosis prediction is important for treatment planning in lung cancer, but deep learning-driven survival modelling is often limited by the scarcity of curated imaging cohorts with reliable outcome data. This study evaluates whether representations from a domain-specific foundation model can be used for multimodal survival prediction in data-constrained clinical settings. We assess the foundation model CT-CLIP as a feature extractor for pretreatment computed tomography images and clinical variables from 242 diagnosed lung cancer patients. The evaluation includes adaptation strategies based on frozen encoders, full fine-tuning, and low-rank adaptation, together with modality ablations and comparisons with clinical and multimodal baselines. The results show that a frozen CT-CLIP model combined with a trainable lightweight survival head outperforms the clinical baseline and achieves comparable or improved performance relative to other multimodal approaches, and separates patients into clinically meaningful high- and low-risk groups.

Hand-object interaction (HOI) recognition requires capturing both hand manipulations and object transformations. However, existing video-language models often fall into shortcuts by relying on spurious correlations among hands, objects, or environmental context, rather than reasoning from the appearance and dynamics of hands and objects themselves. To address this limitation, we propose a new learning paradigm that combines (i) hand-object masked training, which enables robust reasoning from partial hand or object observations, and (ii) an HOI-dynamics-aware decoder that explicitly learns hand- and object-centric embeddings through auxiliary predictions of their locations and semantics, enhancing sensitivity to both cues. To systematically evaluate such cue-specific reasoning, we introduce Cue-Isolated HOI (CI-HOI), a new evaluation that assesses models' ability to predict actions from hand- and object-related cues independently. To enable CI-HOI, we curate the DEHOI testbed, which separates hand- and object-related observations for disentangled HOI evaluation through inpainting. Using DEHOI, we demonstrate both quantitatively and qualitatively that our training strategy exploits hand- and object-centric information more effectively than existing models. Our approach improves over existing models on DEHOI, standard action recognition, object state recognition, and even robot manipulation action recognition, leading to more robust HOI understanding.

Text-to-image (T2I) models have been shown to exhibit social biases. Prior work has mainly focused on gender, skin tone, and cultural representation within restricted occupational associations, and emerging benchmarks increasingly incorporate these dimensions. However, disability remains systematically underexplored. Current evaluation practices often fail to align with sociologically grounded definitions of stereotyping, limiting principled assessment of representational harms toward people with disabilities (PWD). To address this, we introduce INCLUDE-BENCH, the first large-scale benchmark for evaluating disability-related bias in T2I models. INCLUDE-BENCH comprises 119K generated images based on prompt design across multiple bias dimensions and both static and dynamic contexts. We evaluate 15 open-source and 2 closed-source models. Our key findings reveal that: (1) mobility-impaired and default disability prompts predominantly yield wheelchair depictions across all models; (2) disability-conditioned generations consistently exhibit less diversity; (3) stereotypical portrayals demonstrate stronger disability-text alignment; and (4) we introduce the Stereotype Content Model (SCM) Score, demonstrating that T2I models reflect real-world stereotypical associations.

The recently established 'Out of Sight, Not out of Mind' (OSNOM) task for egocentric videos focuses on tracking objects that are moved by the camera wearer, online, maintaining knowledge of instance locations throughout the video even when they leave the field of view or become heavily occluded. In this paper, we propose the first learning-based solution to the OSNOM task: Whareformer, a transformer-based model with two components: an updatable memory of established tracks and a track assignment module that associates observations with existing tracks in a feed-forward manner. Whareformer jointly reasons over evolving object appearance (what) and updated 3D location (where), and employs a dedicated New Track token to reason about novel objects. Thanks to its design choices of using relative distances and evolving track representations, Whareformer is trained on a small set of 56 videos but achieves SOTA performance on 260 long test videos from three datasets: EPIC-KITCHENS-100 (unseen videos), IT3DEgo, and HD-EPIC, with significant absolute improvements over prior work.

Open-vocabulary object detection and segmentation aim to recognize arbitrary objects beyond predefined categories. Although recent vision-language and reference-based approaches have significantly advanced this field, they often rely on text prompts, limited visual examples, or expensive feature matching procedures, making them difficult to scale to large and continuously expanding object repositories. In this work, we propose VocaDet, a sample-driven open-vocabulary object detection and segmentation framework that learns object concepts directly from user-provided positive and negative sample collections without model retraining. The key idea is to transform continuous visual representations into discrete visual vocabularies and perform efficient retrieval-based recognition through a scalable vector database. Specifically, we employ DINOv3 as the visual feature extractor and apply agglomerative clustering with adaptive clustering sensitivity to generate multi-granularity visual tokens. These visual tokens, together with position-debiased representations and spatial topology information, are stored as expandable object memories in a vector database. During inference, query images are converted into visual tokens and efficiently matched against the stored object memories for object localization and segmentation. Furthermore, a background filtering mechanism is introduced to remove frequently occurring background patterns and reduce redundant retrieval operations in practical fixed-camera scenarios. Experiments on the UA-DETRAC dataset demonstrate that VocaDet achieves effective open-vocabulary detection performance without conventional detector training, while supporting continuously expandable recognition capability as additional positive and negative samples are accumulated.

Multimodal Large Language Models (MLLMs) often follow a fixed Think-then-Answer paradigm, which is inefficient in heterogeneous multitask settings because simple inputs may not require explicit reasoning while difficult ones can benefit substantially from it. Learning when to think is also unstable during post-training, where imbalanced rollouts can drive the model toward always-thinking or always-direct behavior. We propose Switch-Reasoner, a GRPO-based framework that learns to adaptively select reasoning modes for MLLMs. It treats thinking as a virtual tool invocation and allows the model to either answer directly or invoke explicit reasoning before answering. To stabilize this decision, we introduce a dual-level regulation mechanism that balances the overall use of Thinking Mode and Direct Mode while providing sample-level supervision based on the relative benefit of the two choices. Experiments on 11 multimodal tasks show that Switch-Reasoner reduces unnecessary reasoning while maintaining strong performance, achieving a better accuracy-efficiency trade-off.

Sparse autoencoders (SAEs) have emerged as a promising technique for mechanistic interpretability by learning a set of sparse latent features in large models, each of which encodes a distinct concept. However, in vision-language models (VLMs), vanilla SAEs struggle to learn modality-consistent concepts, with concepts often exhibiting fragmented coverage (i.e., disjoint regions) in the visual modality. To address this challenge, we propose a Structured Sparse AutoEncoder ($S^2AE$) that enforces concept consistency from both semantic and spatial perspectives in the visual modality. Specifically, we group image patches based on Transformer attention similarity and spatial proximity, and introduce a structured sparsity regularization when training the vanilla SAE. The regularization consists of exclusive sparsity for inter-group concept disentanglement and group sparsity for intra-group concept consistency, which drives the latent neurons by SAEs to specialize in distinct, semantically grounded concepts. Evaluated on the \texttt{Qwen2.5-VL-7B-Instruct} model, the method achieves 6.06% average improvement in semantic alignment (mIoU) and 60.81 in representational efficiency (lower l0 norm) while maintaining near-perfect reconstruction fidelity with an Explained Variance above 99%. Cross-modal analysis further demonstrates that $S^2AE$ enhances neuronal monosemanticity by this visual structural prior, achieving a 3.08% average gain in semantic consistency and a 2.37% average gain in monosemanticity scores for both modalities of multimodal features, thereby fostering more coherent and disentangled representations.

The rapid advancement of generative AI has enabled the creation of highly realistic deepfake media, posing significant threats, including misinformation, digital identity theft, fraud, and manipulation of public opinion. AI-generated image (AIGI) detection is reliably challenging due to the diversity of generative methods and the subtle artifacts they leave behind. In this work, we propose GenRes, a novel framework for generative residual learning via a neural tensor network, which models fine-grained relational features between original and transformed samples to enhance generalization. To address scenarios involving multiple generative transformations, we introduce GenRes++, which employs a learnable attention mechanism to aggregate relational features across multiple transformed samples and enables the model to focus on the most informative cues. Both models leverage PE-Core as a feature extractor, providing generalized and semantically rich embeddings that improve cross-domain performance and enable the detection of AIGI generated by unseen methods. Comprehensive experiments on multiple benchmark datasets demonstrate that the proposed GenRes++ approach outperforms existing methods.

Diabetic Retinopathy (DR) is a leading cause of preventable blindness worldwide, requiring automated lesion segmentation using deep learning models for early detection and monitoring. However, DR lesions vary dramatically in size from tiny microaneurysms to large hemorrhages and exudates. This variability creates conflicting demands on the model architecture and input resolution, posing a challenge for effective design. This work investigates the impact of input resolution on different lesion types. Through systematic experimentation with multiple architectures (U-Net, UNet++, Vision Transformers, DeepLabV3+) at $512 \times 512$ and $1024 \times 1024$ resolutions, we identify a critical, counter-intuitive phenomenon where increasing input resolution has opposing effects on different lesion types. We demonstrate that while higher resolution is essential for resolving fine-grained microaneurysms, it can unexpectedly degrade performance on larger hemorrhages. This finding challenges the common assumption that higher resolution is uniformly beneficial. To address this, we propose a novel Multi-Resolution Feature Stem, an input-level pyramid integrated with a UNet++ backbone. This architecture processes multiple scales in parallel, capturing fine-grained details without sacrificing contextual information. This work contributes crucial empirical evidence of this complex, resolution-dependent behavior and a practical, parameter-efficient architecture that successfully resolves this trade-off.

Modern Video Object Segmentation (VOS) involves tracking and segmenting user-specified targets. While recent approaches have achieved remarkable performance in single-target scenarios, extending them to multi-target settings typically involves replicating the single-target processing for each individual object, resulting in reduced frame rates (FPS) with unbounded latency as target count increases. Built upon Segment Anything 2 (SAM2), we propose SAM-MT, which addresses this by transforming the model into an interactive framework for real-time Multi-Target video segmentation. SAM-MT uses explicit queries to represent different individual targets, in parallel with a shared representation for global context. It employs decoupled masked attention to keep individual identities distinct from cross-target interference, and sparse memory for stable temporal evolution, along with specialized strategies for occlusion handling and overlap prevention. SAM-MT successfully decouples latency from the number of targets, achieving real-time speed on par with single-target baselines (>36 FPS for 10 targets) while maintaining SAM2's robust video segmentation performance.

Rapid advancements in video diffusion models and temporal editing tools have enabled the generation of highly realistic human-centric videos, posing unprecedented challenges to digital content forensics. Existing benchmarks primarily focus on either face-swapping or global text-to-video synthesis, overlooking the crucial dimensions of human-object or human-human interactions and multi-modal alignment. To address these limitations, we introduce HumanForge, a unified, large-scale, and multi-paradigm human-centric video forgery dataset. To construct and annotate this dataset without labor-intensive manual labeling or hallucinated monolithic prompts, we propose Gen2Anno, a modular active multi-agent pipeline built on LangGraph. Gen2Anno coordinates six specialized agents-ranging from source profiling to MoE-based reference analysis and closed-loop forensic verification-to generate over 18K high-fidelity video segments and produce structured, contrastive omni-annotations containing binary decisions, fine-grained artifact categories, and spatio-temporal localization. Extensive benchmarks using state-of-the-art traditional detectors and Large Multimodal Models (LMMs) demonstrate the significant challenges of zero-shot generalization and fine-grained reasoning on HumanForge. Code and dataset will be publicly released.

Accurate 3D terrain maps are essential for emergency response when assessing wildfire hazards. However, wildfire-prone regions often span vast areas where conventional reconstruction methods underperform. Airborne LiDAR systems provide high-resolution terrain data, but they are expensive and infrequently updated. Image-based methods offer a lower-cost alternative, but struggle due to sparse visual features and limited image overlap. We propose a multi-modal reconstruction framework leveraging outdated Digital Elevation Models (DEMs) as geometric priors for image-based 3D reconstruction. Our key innovation is physics-based pixel-pixel alignment between images and DEM data, dramatically reducing computational complexity by eliminating expensive feature matching procedures. To validate our approach, we developed a large-terrain simulator based on a real wildfire-prone area, generating realistic images enabling a comprehensive evaluation. Given posed images and legacy DEMs, our method produces high-fidelity depth maps while maintaining real-time performance. We find significant improvements in reconstruction accuracy and computational efficiency over existing techniques, offering a scalable solution for wildfire response.

Recent progress in 3D human pose estimation has made markerless recovery of skeletal motion increasingly accurate and scalable. However, most pose estimators remain optimized for geometric keypoint accuracy, while many real-world applications in rehabilitation, sports science, ergonomics, and clinical movement analysis require biomechanical quantities that describe how the body moves, loads, and activates. In this work, we propose BioModule, a lightweight plug-in temporal transformer that attaches downstream of any 3D pose estimator and predicts biomechanical attributes from standard 17-joint 3D skeletons. BioModule is estimator-agnostic and requires no modification of the upstream pose model, enabling existing pose estimators to be extended toward physically interpretable motion analysis. To train and evaluate BioModule, we construct a large-scale aligned dataset pairing Human3.6M video and 3D keypoints with the biomechanical label space of Human3.6Mplus. We establish and verify anatomical correspondence between coordinate systems of the two datasets, enabling frame-accurate cross-modal supervision. Using this aligned supervision, BioModule predicts biomechanical quantities. We further benchmark BioModule across seven state-of-the-art 3D pose estimators, providing the first systematic analysis of how upstream pose estimation quality propagates to downstream biomechanical prediction fidelity. The results position BioModule as a compact, modular bridge between vision-based pose estimation and biomechanically meaningful human motion analysis.

Multi-object tracking (MOT) has achieved strong performance on benchmarks dominated by short video sequences. However, such datasets do not adequately evaluate long-term identity preservation, where objects must be tracked consistently over extended durations. We introduce WaspMOT, a benchmark designed to address this gap through long-duration tracking of Trichogramma wasps in controlled ecological experiments. The dataset contains 10 sequences of approximately 12,000 frames each (over 8 minutes at 25 FPS), with dense MOTChallenge annotations and oracle detections to isolate association performance. Unlike existing benchmarks, WaspMOT forms a closed-set tracking scenario where all individuals remain present throughout the sequence, requiring consistent identity assignment across thousands of frames despite abrupt jumps, occlusions, and highly similar appearance. We establish a benchmark by evaluating five tracking-by-detection methods, including ByteTrack, BoT-SORT, C-BIoU, OC-SORT, and McByte, under a unified protocol. Results show that all methods suffer from significant trajectory fragmentation, highlighting the difficulty of long-term identity preservation even with perfect detections. A simple spatial tracklet stitching baseline consistently improves performance, indicating that substantial gains remain possible. WaspMOT provides a new benchmark for studying long-term association and reveals limitations of current tracking approaches that are not observable on conventional datasets. The benchmark will be made publicly available at the project repository: https://github.com/tstanczyk95/WaspMOT/ .

Reasoning has become a core capability for large models, especially when reliable decisions require understanding logical consequences. Recent video generation models offer a reasoning path distinct from previous Chain-of-Thought (CoT): reasoning can unfold through temporally connected frames, known as Chain-of-Frame (CoF) reasoning. However, existing video generators are primarily trained on general video corpora, still lacking diverse supervision and dedicated designs for CoF reasoning. To address this gap, we introduce OpenCoF, a framework comprising the OpenCoF-17K dataset, a reasoning video dataset spanning 11 task families, and Wan-CoF, a fine-tuned video model for studying whether diverse temporal supervision improves CoF behavior. Across four video reasoning benchmarks, Wan-CoF achieves considerable gains over the Wan2.2-I2V-A14B baseline. Building on this, we empirically explore more advanced designs for CoF capabilities, i.e., equipping the model with visual and textual reasoning tokens. This mechanism respectively captures low-level visual cues and high-level semantic priors for spatial and temporal reasoning. Through performance comparisons and attention analysis, we examine how these tokens contribute across model depth, denoising steps, space, and time. Our results suggest that stronger video reasoning requires both broad temporal supervision and explicit mechanisms for organizing intermediate reasoning state. We open-source the dataset, model, and code to facilitate future research on reasoning-oriented video generation.

In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with downstream task-specific fine-tuning. To address the lack of large-scale, high-quality training data tailored to in-context panoramic tasks, we propose Canvas360Dataset, a collection of 1M high-quality paired panoramic samples for style transfer, inpainting, outpainting, and editing, enabling effective supervision across diverse in-context generation scenarios. On the modeling side, Canvas360 enhances text-to-panorama generation through parallel depth generation, velocity circular padding, and similarity loss regularization, enabling the model to learn geometry-aware representations, capture object distortion details, and improve geometric consistency and global coherence. Furthermore, empowered by strong panoramic priors, Canvas360 enables a unified in-context panoramic generation framework that supports diverse downstream tasks via token-level concatenation, surpassing prior methods in both task coverage and modeling flexibility. Extensive experiments show that Canvas360 improves panoramic image fidelity, achieving particularly strong performance on the panorama-specific FAED metric and competitive or leading results across the reported quantitative evaluations. More information can be found on our project page: https://zry000.github.io/Canvas360/

We propose OPSD-V, an on-policy self-distillation paradigm for post-training few-step autoregressive (AR) video diffusion models. Existing few-step AR video generators can produce long videos with low latency, but still suffer from error accumulation and weakened motion dynamics during long autoregressive rollout. OPSD-V reduces long-horizon degradation while preserving the original few-step inference path. The key idea is to introduce real long-video data as temporal context during training and use it to provide dense trajectory-level supervision. Specifically, the student follows the exact inference-time rollout, generating each chunk conditioned on its own previously generated KV cache. In parallel, the teacher is evaluated at the same student-visited denoising states, but uses a cleaner AR-consistent temporal cache in which older history can be replaced by real-video context. This provides dense denoising-level corrective targets under on-policy AR cache dynamics, without changing the sampler, number of denoising steps, or inference-time cache mechanism. We apply OPSD-V to representative few-step AR video models, including Self-Forcing and LongLive. Experiments show consistent improvements in visual quality, motion dynamics, and VBenchLong scores. A user study with 10 participants comparing 20 video pairs shows that OPSD-V is preferred over the base models in 66.0% of overall-preference judgments (82.5% excluding ties).

Scaling 3D Gaussian Splatting (3DGS) to large outdoor scenes is costly in both data acquisition and computation. Adopting panoramic images with equirectangular projection (ERP) can reduce capture effort via their full $360^{\circ}$ field of view, yet the resulting omnipresent visibility invalidates existing partitioning strategies that rely on local camera frustums, causing block-wise optimization to degenerate into global training. Thus, we propose PanoLOG, a two-stage coarse-to-fine framework equipped with a Geometry and Gradient-based Partitioning Strategy tailored for large-scale panoramic 3DGS reconstruction. In the global coarse stage, PanoLOG leverages sky-sphere modeling and panoramic monocular depth supervision for reliable geometry, while in the refinement stage, G$^2$PS builds adaptive bounding volumes via parallax-driven uncertainty and assigns cameras via gradient-based importance scoring. Furthermore, we construct Pano360, the first benchmark on large-scale panoramic dataset for outdoor scene reconstruction. Extensive experiments demonstrate that G$^2$PS achieves state-of-the-art rendering quality while maintaining scalable, block-parallel training. Our models, training code, and dataset are publicly available.

Recovering high-quality video from sparse event streams is a challenging task. Regression methods often blur textures, while existing generative models struggle with long-term stability. We propose LongE2V, a novel approach that leverages pre-trained video diffusion priors to jointly handle event-based video reconstruction, prediction, and frame interpolation. By fine-tuning a foundational video model, our approach achieves high data efficiency and superior perceptual quality. We introduce Autoregressive Unrolling and Adaptive Context Switching to mitigate temporal drift in extremely long sequences. We also propose Reencoding Alignment with Cross Residual Correction to ensure precise bidirectional consistency during frame interpolation. Furthermore, Event Voxel Density Augmentation ensures robustness across varying sensor resolutions. Extensive experiments on real-world benchmarks demonstrate that LongE2V outperforms state-of-the-art methods across all three tasks, exhibiting exceptional temporal coherence and zero-shot generalization. Project page: https://cdfan0627.github.io/LongE2V-page/

Monocular depth estimation has seen remarkable progress through foundation models achieving robust zero-shot generalization, yet their computational demands place them far beyond the reach of embedded and mobile platforms. Lightweight alternatives exist, but have been developed almost exclusively within single-domain, self-supervised paradigms, failing silently under domain shift. We present ZipDepth, a compact monocular depth network that bridges this gap by combining an efficient reparameterizable encoder-decoder with large-scale knowledge distillation from a foundation model over a large multi-domain training set. Comprising just 6.1M parameters, ZipDepth runs at real-time rates from server GPUs to power-constrained devices, achieving the best trade-off between zero-shot accuracy and deployment efficiency among lightweight models across five benchmarks, taking a significant step towards the accuracy of foundation models with 50x more parameters.

Estimating 3D geometry in underwater environments presents unique challenges due to light attenuation, scattering, and the absence of large-scale, high-quality 3D annotations. Pioneering methods rely on massive dense annotations that are impractical in underwater settings. In this paper, we propose Wat3R, a cross-domain semi-supervised learning framework designed to adapt feed-forward 3D reconstruction models from air to underwater scenes. Uniquely, our method eliminates the need for any annotated underwater data following a teacher-student architecture, that learns robust geometry representations merely on abundant unlabeled real underwater video footage. We also design a cross-view consistency loss that leverages geometric cues from other views to compensate for the information degradation in the current view caused by water attenuation and scattering. Furthermore, considering the lack of comprehensive evaluation benchmarks, we construct Water3D, a diverse dataset covering various water bodies and underwater scenarios, designed for geometric task evaluation. Experimental results demonstrate that Wat3R outperforms current state-of-the-art methods in underwater multi-view depth estimation and point cloud reconstruction. The dataset and code are available at https://github.com/LSXI7/Wat3R .

Retrieval-Augmented Generation (RAG) and agentic frameworks have advanced enterprise AI considerably, yet agents remain fundamentally reactive: they wait for a human query before acting. This paper argues that genuine enterprise productivity gains require proactive agents: systems that surface relevant, actionable information to workers before they ask. We propose the Context Graph, a live relational data structure that models enterprise entities, their relationships, and state transitions over time. Built on this graph, we define a Delta Detection Engine that continuously monitors state changes, a Proactivity Scorer that ranks candidate insights by urgency, relevance, and persona-fit, and a Surfacing Layer powered by an LLM that delivers ranked notifications with grounded explanations. We formalize each component, derive a unified Proactivity Score function, and provide a complete end-to-end Python implementation using NetworkX and the Anthropic Claude API. Evaluation across three generic enterprise case studies (contract lifecycle management, engineering incident response, and sales pipeline hygiene) demonstrates that context-graph-driven proactivity achieves Precision@5 of 0.83, a false positive rate of 0.11, and reduces mean time to surface from 47 minutes (reactive baseline) to under 30 second.

Agricultural supply chains are vulnerable to disruptions through linked biophysical and economic systems. We develop an AI-powered tool that integrates economic models (GTAP) with biophysical models (APSIM) to analyze supply chain shocks, enabling policymakers and market participants to assess cross-disciplinary impacts through queries and responses written in natural language.

We outline an adversarial social epistemology (ASE) for densely interactive communicative landscapes in which public assertions are scaffolded by chains of testimony, inference, institutional certification, and tacit trust. In such landscapes, agents have incentives and affordances to distort, color, omit, fabricate, or strategically under-specify information for private, reputational, rhetorical, or material gains. We argue that these phenomena are not adequately captured by familiar descriptions of epistemic bubbles, echo chambers, or misinformation diffusion. What requires explanation is how communicative agents exploit the commitments and entitlements that normally make scaffolded assertions trustworthy. We provide language that delivers the requisite analysis, outline mechanisms that subvert trust in scaffolded public communications, and outline machinery for auditing and redressing trust breaches arising from subverting the auditability of inferential chains, drawing on epistemic networks, enriched with an inferentialist semantics for interpreting assertions.

Large language models (LLMs) have emerged as important tools in healthcare, showing growing potential for clinical reasoning and patient care. This survey examines recent progress in medical LLMs, focusing on reasoning applications and requirements. We present a dual-view approach that connects clinical practice with computational methods. On the clinical side, we establish a five-level competency scheme following Miller's Pyramid, progressing from knowledge recall to dynamic case management. On the computational side, we link deductive, inductive, and abductive reasoning patterns to common medical goals and tasks. We also introduce a benchmark dataset spanning five levels of medical reasoning capability and report results on 18 state-of-the-art models, revealing that medical specialist models excel in diagnosis-centric tasks while general models lead in decision support and dialogue. We conclude by discussing current progress and open challenges, including data limitations, hallucination, and grounding issues, and outline directions toward safer, more reliable, and workflow-ready systems.

Large language models (LLMs) have become significant providers of mental health support, yet they remain products of an attention economy whose operational and commercial targets favour sustained engagement over the friction that effective psychological support often requires. Developers' safety responses have been largely reactive, addressing the most visible and acute harms while subtler, longer-term patterns of risk (e.g., dependency, boundary erosion, the amplification of distorted beliefs) receive less attention. We contend that making LLMs structurally safe requires alignment organised at three levels that mirror how society assures the safety of human clinical practice: 1) explicit value specification grounded in the codified normative commitments of clinical practice; 2) training that embeds those values in the model; and 3) oversight that detects drift and longer-term harm during deployment, much as clinical supervision does for human practice. Organising alignment in this way yields a construct we call alignment plausibility - a structured demonstration that a system's values, training regime, and oversight mechanisms are together consistent with safe and positive outcomes. We propose alignment plausibility as a regulatory construct (by drawing analogy to the established construct of biological plausibility) for AI in health: a principled way to argue for, or against, trust that systems are aligned to positive health outcomes, will cause no harm even where capable of doing so, and will ultimately lead to patient benefit.

The human body is at the center of a growing family of technologies designed to tightly and persistently couple biological and digital systems. Robotic prostheses are a representative example of this tight coupling. Also referred to as bionic limbs, robotic prostheses are devices that support people who have lost limbs in pursuing daily life activities such as walking and grasping objects. Bionic limbs are now perceptive and responsive owing to their integration with advanced sensors and artificial intelligence-based control approaches. Consequently, such robotic prostheses can now be viewed as semiautonomous wearable robotic systems that can co-adapt with their users. However, the same sensing and control advancements that increase the capability of robotic prostheses also introduce threat vectors that could be exploited by malicious entities to violate the privacy of users. To fully realize the benefits of next-generation bionic limbs, we maintain it is important to directly understand and address these privacy risks and the barriers they might present to user adoption. This paper therefore introduces a new line of inquiry we term idiobionics to holistically investigate issues at the intersection of privacy and intelligent bionic limbs. As the main contribution of this paper, we define idiobionics, ground it in related literature, and provide preliminary evidence showing and discussing potential adversarial attacks that could exploit intelligent bionic limb designs. We then contribute a curated list of open research questions within idiobionics that are relevant to researchers in wearable robotics and other human-facing autonomous systems. We expect that idiobionics research will help unlock the full potential of robotic prostheses and related bionic devices.

We present Infinity-Parser2, a large multimodal model that couples a controllable data-synthesis pipeline with multi-task reinforcement learning for end-to-end document parsing, addressing the persistent scarcity of faithfully annotated parsing corpora. Our contributions are threefold. First, we build a scalable synthesis engine, pairing a controllable rendering framework with an iterative refinement loop, and use it to construct and open-source Infinity-Doc2-5M: a 5-million-sample bilingual (Chinese/English) corpus spanning diverse document types, annotated with element bounding boxes, canonical content forms (Markdown, HTML, LaTeX, SMILES, structured charts), and full-page reading order. Second, we introduce a verifiable, multi-task reward system that enables Joint Reinforcement Learning across eight co-trained objectives (document parsing, layout analysis, table parsing, math formula parsing, chart parsing, chemical formula parsing, document VQA, and general multimodal understanding), unifying perception, structure, and reasoning in a single optimization signal. Third, we release two variants under a shared architecture: Infinity-Parser2-Flash, optimized for low-latency inference with a $3.68\times$ throughput gain over Infinity-Parser-7B, and Infinity-Parser2-Pro, engineered for precision-critical settings. Infinity-Parser2-Pro reaches state-of-the-art 87.6% on olmOCR-Bench and 74.3% on ParseBench, surpassing DeepSeek-OCR-2, PaddleOCR-VL-1.5, and MinerU2.5, with strong generalization to charts, chemical formulas, and document VQA.

VectorizationLLM is a specialized Large Language Model based on Google open-weight LLMs. The model is designed to assist students to learn smart vectorization, time/wave vector analysis, piecewise functions, Fourier analysis, and differential equations in MATLAB. The course application is CTEC 247: Applied Computational Analysis II by the Department of Electrical & Computer Engineering Technology at New York Institute of Technology Old Westbury. The LLM model is designed to be an instructive assistant, providing detailed explanations of concepts with examples from in-class notes without providing direct answers to questions. The model is designed with a RAG (Retrieval Augmented Generation) knowledge base and system prompt architecture. Examples in both code, text, and images are provided in the LLM responses.

For seemless control of advanced hand prostheses and augmented reality, accurate and immediate hand gestures recognition is essential. Surface electromyography (sEMG) signals obtained from the forearm are commonly employed for this purpose. In this paper, we present a novel approach for sEMG representation that utilizes graph networks which contain information about muscle activation patterns in the forearm. Based on these graph networks, we have developed a machine learning algorithm capable of real-time hand gesture recognition using a graph neural network. The algorithm's performance was evaluated using sEMG signals acquired from myoband, which has 8 electrodes placed around the forearm, involving 8 healthy subjects. The proposed method demonstrated an average classification accuracy of 99\%, surpassing the performance of state-of-the-art techniques. The average time for both graph construction and prediction stood at 48ms utilizing a M1 pro CPU, rendering the approach well-suited for real-time applications.

Artificial intelligence (AI) is beginning to reshape actuarial practice, particularly in domains that require reasoning over unstructured documents, heterogeneous data sources, and regulated decision workflows. Actuaries now face a design space that ranges from traditional rule-based automation to large language models (LLMs), retrieval-augmented generation (RAG), and multi-agent ``agentic'' systems that plan, retrieve, call tools, and reflect. This paper examines how these emerging architectures can support actuarial priorities such as transparency, auditability, and human-in-the-loop governance, with a focus on straight-through decision processes. To make these ideas concrete, we develop and analyze an agentic AI framework for straight-through underwriting of small commercial Business Owner Policies (BOPs). We construct a synthetic but realistic experimental environment and compare three underwriting pipelines: (i) a single-LLM baseline, (ii) a naive RAG system, and (iii) a multi-agent ``Agentic RAG'' pipeline that combines targeted retrieval, third-party data checks, and explicit multi-step rule evaluation. The agentic system performs best overall, with the largest gains in multi-step and missing-information scenarios, where structured retrieval and reflection help the model avoid unsupported straight-through decisions.

Reinforcement learning (RL) research has increasingly shifted focus towards alignment, ensuring agents learn behaviors adhering to human values. While human demonstrations and feedback have proven crucial for alignment, existing approaches predominantly combine these signals using multi-stage pipelines designed for the contextual bandit framing of language generation. Yet little work explores how these complementary inputs can serve as a richer, interconnected signal for single-stage offline training in fully sequential decision-making environments. We propose Feedback Manipulation Regularization (FMR), an algorithm-agnostic method that harnesses evaluative feedback as a corrective signal to improve the alignment of imitation learning policies. We adapt Safety Gymnasium environments to be a principled testbed for alignment evaluation, demonstrating improved aptitude and up to a 98\% reduction in misalignment across a range of imitation learning algorithms. FMR remains robust in limited data regimes, even when learning from scarce aligned and uninformative noisy demonstrations.

There is relatively little, public, and model-ready data on industrial machinery for African economies. This makes it hard to do quantitative analysis or to train language models on numeric tasks grounded in that setting. We release two things to help with part of this problem. The first is the Nigeria Machinery Usage and Failures Dataset: 89 machine-level records across 28 indicators, covering Nigeria's manufacturing and oil and gas sectors from 2006 to 2025. Every record names a public source and is decoded by a codebook. The second is a method for building chain-of-thought (CoT) reasoning examples from these sparse numeric values. The result is 94 prompt, completion, and reasoning-trace rows. In every row, the prompt names the real indicator, subsector, year, and source of the record it comes from. The data adaptation work was carried out by Adaption Labs. Along the way we describe a problem that is common when language models are used to build datasets. The prompts can match the real numbers while saying nothing about the real domain. We show that fixing this raises the share of domain-grounded prompts from 1 out of 78 in an earlier release to 94 out of 94, and that every retrieval answer now matches its source value (84 out of 84). We release the data, the reasoning layer, and a per-row provenance file under CC-BY-4.0. We are clear about the limits. With 89 records and 17 indicators that have only one observation, this is a reference and seed dataset, not a large training set. Most reasoning rows are retrieval rather than multi-step computation.

Large language models exhibit recurring behavioural patterns -- personas -- that shape generalisation and safety, but we lack reliable tools for decomposing, measuring, and controlling them. Our central insight is to treat personas as positions in a space of behavioural traits, using the OCEAN framework to describe model personas in terms of Openness, Conscientiousness, Extraversion, Agreeableness, and Neuroticism. We train low-rank adapters to amplify or suppress individual traits, and evaluate their effects using an LLM-judge calibrated against a human-validated panel, trait-specific multiple-choice benchmarks, and standard capability evaluations. Across six models from three families (4B-32B), we find that each adapter moves its target trait largely monotonically with scale, combines approximately additively with other adapters to construct mixed personas, and preserves performance on capability benchmarks at moderate scales. We further show that the induced trait axes affect safety-relevant behaviour in downstream evaluations: for example, moving along neuroticism and agreeableness axes affects frustration and sycophancy respectively. We also introduce an unsupervised psychometric pipeline that recovers four interpretable behavioural factors (tone, initiative, didacticism, epistemic caution) from model rollouts. Persona control can then be considered in terms of learning, scaling, and composing traits in weight space, providing a bridge between personality measurement, model editing, and safety.

Autism spectrum disorder (ASD) affects over 75 million individuals worldwide, yet scalable computational methods for remote behavioral screening remain limited. This study addresses two complementary challenges in automated detection of autism-related self-stimulatory behaviors from video: (1) identifying the optimal sequence-based neural network architecture and temporal sampling rate, and (2) characterizing data augmentation strategies for training on small behavioral datasets. For the first objective, long short-term memory (LSTM) and gated recurrent unit (GRU) models were trained on pose-derived features from the Self-Stimulatory Behavior Diagnosis (SSBD) dataset at frame sampling intervals of 1, 5, 15, 30, 45, and 90 frames. Both architectures exceeded prior convolutional neural network (CNN) baselines (62-76% accuracy), with peak accuracies of 97.5% (LSTM) and 98.75% (GRU) at a sampling interval of every 15 frames. For the second objective, ten data augmentation strategies were applied to an I3D transfer learning pipeline, with an ablation study quantifying the marginal contribution of each technique. Horizontal flip achieved the highest standalone accuracy (48.78%), while exclusion of upsampling from the augmentation pipeline produced the largest performance degradation, indicating its necessity for complex behavioral video augmentation. A personalized machine learning approach, in which per-subject models were trained and tested on temporally split segments of each video, produced consistent predictions (mean loss 1.84, SD 0.79). These results provide practitioners with concrete guidance on architecture selection, sampling rate, and augmentation strategy for video-based behavioral classification in data-scarce clinical domains.

Neural architecture search (NAS) methods have grown increasingly efficient, yet they remain bounded by manually engineered search spaces that require substantial domain expertise and must be rebuilt for every new task. Large language models (LLMs) can generate architectures in an open-ended space, but how to optimally divide the labor between LLM-driven design and NAS-driven search remains unexplored. We propose a mechanism that bridges these two paradigms: an LLM produces a high-quality seed architecture, then decomposes it into a "slotted architecture", a scaffold with named, interchangeable module slots that automatically defines a bounded, task-specific search space for conventional NAS to explore, without manual engineering. We instantiate this mechanism in AgentNAS, a modular three-phase pipeline in which each component's contribution can be measured independently. On 17 tasks spanning classification, dense regression, segmentation, and multi-label tagging across diverse modalities (NAS-Bench-360 and Unseen NAS), AgentNAS establishes a new state of the art on 11 tasks, outperforming published baselines including task-specific expert designs. Ablation studies show that the two search mechanisms are broadly complementary: the LLM-generated seed already surpasses published baselines on the majority of tasks, and NAS delivers additional gains in most cases through combinatorial recombination across slots, a mode of search that independent LLM samples cannot replicate. These patterns hold across three LLMs of different capability levels, confirming that the division of labor is robust. Our code is available at https://github.com/alroimfebruary/AgentNAS.

LLMs often struggle to balance compositionality with knowledgeability, a challenge we define as Composition-Knowledge Dichotomy. To address this, we propose Concretized Proposition Prompting (CPP), a framework that explicitly concretizes propositions relevant to questions. The results demonstrate that CPP significantly enhances reasoning performance, particularly in medical benchmarks where precise knowledge is paramount, while being competitive on math benchmarks where deductive reasoning is prioritized. Additional experiments reveal that CPP is scalable to various foundation models and parameter sizes, being a fundamental paradigm that bridges the gap between composition- and knowledge-based approaches. Consequently, CPP resolves the composition-knowledge dichotomy by providing a solid foundation for logically organized and factually grounded reasoning.

Enterprise large language model (LLM) applications often begin as prototypes whose behavior is carried by prompts and retrieval context. Productization adds requirements for source boundaries, entity routing, answer contracts, and reproducible traces. We present a harness-engineering approach that reconstructs this pattern into a traceable, auditable LLM-agent architecture: deterministic behavior moves into code, manifests, schemas, and validation artifacts around a replaceable composition boundary, while source-backed claims remain the authority for runtime answers. We instantiate it on a public-data slice of five Korean corporate groups (25 listed companies) and evaluate three research questions. (1) The harness preserves its source-grounding, entity-routing, trace, output-hygiene, and recommendation-language contracts across the fixed validation scenarios; a fault-injection control confirms the validators flag deliberately broken contracts. (2) The checks the harness enforces held under model substitution: across three hosted models, they passed on all 270 composition-boundary runs; failures were confined to the model-composed side and were caught and recorded. (3) The code-owned guarantees are load-bearing, not reproducible by prompting alone: holding the model fixed and varying only the enforcement layer, prompt instructions alone let recommendation-language and internal-trace-leakage violations reach the reader, which the harness blocks entirely. A bolt-on external guardrail prevents such violations too but over-refuses, dropping utility to 88/120 where the harness preserves full utility (120/120); in this ablation, only code-owned enforcement preserves both safety and utility. The result is a reusable engineering pattern for turning exploratory prototypes into auditable applications with versioned source, control, and validation artifacts.

Diagnostic error is a major threat to patient safety, yet current large language model (LLM) systems often treat diagnosis as a one-shot prediction task, lacking safeguards against missed high-risk alternatives or rigorous verification of their reasoning. Here, we present AegisDx, a safety-oriented framework for hypothetico-deductive clinical reasoning. AegisDx coordinates specialized LLM components through role-specific contracts, structured intermediate outputs, evidence-retrieval interfaces, and verification gates to generate broad differential diagnoses, enforce explicit screening for dangerous "must-not-miss" conditions, verify reasoning against grounded medical evidence, and structure actionable next steps. We evaluated AegisDx across three layers. On literature-derived case reports from NEJM and JAMA, with GPT-oss-120B as the shared backbone, Top-3 diagnostic accuracy was 59.9% versus 52.1% for the standalone LLM on JAMA cases and 62.7% versus 51.4% on NEJM cases. On cases from Annals of Emergency Medicine, Top-3 accuracy was 85.7% versus 68.6%; against physician-consensus must-not-miss diagnosis sets, AegisDx captured at least one such condition among its top three diagnoses in 78.0% of cases versus 52.0%. In a blinded physician evaluation of 43 real-world emergency department notes from the Yale New Haven Health System compared against GPT-5, AegisDx improved the physician-rated composite safety score from 4.31 to 4.55 on a 5-point scale (adjusted p = 2.1x10^-4), with qualitative gains in must-not-miss identification and reasoning safety. Our findings suggest that engineering diagnostic AI as a safety-oriented reasoning framework, rather than optimizing raw predictive accuracy alone, can provide a safer, more transparent, and clinically meaningful layer of bedside decision support for acute care workflows.

LLM-as-judge (Zheng et al., 2023) is increasingly the default for evaluating AI systems in enterprise pipelines, often scaled to ensembles (Verga et al., 2024) or "mixture-of-experts" (Shazeer et al., 2017) panels of judges. These systems share a key assumption: that consistency -- agreement among judges, or among a model's own samples -- indicates correctness. We show this assumption is unreliable. Agreement is not accuracy: a model can agree with itself, and different models can agree with each other, out of shared bias, a memorized heuristic, or an option-position prior rather than truth. We ask when agreement is nonetheless a usable proxy, in a large-scale cross-runner study: 53 runners drew K=50 samples for assigned overlapping cases across comparisons of model tier, prompting, and scale on GPQA Diamond and AIME -- 265,000 samples. Using majority-correctness as the deployment label and a hierarchical runner-clustered bootstrap, agreement is a positive but weak predictor (rho 0.20-0.59, all positive under item-clustered resampling) whose usefulness is regime-dependent: best for unsaturated mid-tier models and for allocating compute, and worst -- over-confident yet no more accurate -- for the most consistent frontier model (agreement >=0.8 on 77% of GPQA case-result entries, 48% of those wrong). An exploratory cross-family check on three Claude tiers shows the same frontier over-confidence, with confident errors recurring across providers above a marginal-preserving null. Self-consistency is thus a conditional proxy for correctness, not a standalone confidence score. We publicly release the de-identified per-run rows and answer distributions.

Chain-of-thought (CoT) monitoring is a promising safety mechanism for AI agents, based on the premise that visible reasoning traces can surface misaligned or deceptive behavior. While effective in standard scenarios, recent work highlights that LLMs remain vulnerable to persuasion-based jailbreaks, where natural-language arguments override model constraints. We stress-test whether this vulnerability extends to monitoring LLMs: can an adversarial agent persuade its CoT monitor to approve proposed actions that violate the monitor's policy? We design an evaluation framework with 40 tasks and analyze thousands of agent-monitor interactions, where agents are instructed to argue for policy-violating proposals. We find that in such adversarial settings, monitor access to the agent's CoT reasoning increases rather than decreases approval of harmful actions on average by 9.5%, as the scratchpad provides an additional persuasion channel. To address this, we introduce a fact-checking monitoring framework. We find that a fact-checker and monitor pairing from different model families, for example a Claude 3.7 Sonnet monitor paired with a GPT-4.1 fact-checker, reduces approval of policy-violating actions by up to 45%, compared to only 6%, when using the same model for both fact-checking and monitoring roles. Our results demonstrate that CoT monitoring alone may be insufficient against adversarial persuasion, and that model-diverse fact-checking provides a robust mitigation.

Accurate photovoltaic (PV) power forecasting is essential for reliable grid dispatch and renewable energy integration, yet it remains challenging because PV generation is jointly shaped by weather variability, day-night transitions, regime-dependent dynamics, and strict physical constraints. We propose PARA-PV, a Physics-Aware Retrieval-Augmented framework that embeds physical knowledge throughout the forecasting process. The framework first encodes multivariate PV observations into patch-level representations and, through a physics-aware retrieval-augmented learner, retrieves historical patches and analog trajectories that are consistent with the current window in temporal shape, power level, PV operating state, and intra-day period; this yields a physically grounded base forecast. To supplement local memory with broader temporal knowledge, the base forecast is then calibrated against a frozen Chronos time-series foundation-model prior through a lightweight residual adapter, so that general temporal regularities are adapted to PV-specific dynamics without overriding the physically grounded prediction. Because residual conditional distribution shifts persist when weather and diurnal regimes change, a physics-aware distribution shift correction module subsequently adjusts the preliminary forecast using power, weather, timestamp, and day/night conditions, applying gated mean-shift and scale corrections selectively. Finally, a physics-constrained loss function partitions the samples into peak, ramping, night-time, and regular regimes and adaptively reweights their error contributions, preventing the dominant regular regime from suppressing learning of operationally critical states. Our code is available at https://github.com/weican1103/PARA-PV.

Large language models (LLMs) increasingly act as integrated data-science agents, combining abstract reasoning with advanced tool use. Yet the relevant benchmark landscape largely divides into symbolic causal reasoning benchmarks without realistic data analysis or data analysis benchmarks without a principled causal data-generating structure. Furthermore, existing causal evaluation datasets are often restricted to curated examples from existing sources, with diversity coming from limited templatized variations rather than from systematic generation of novel synthetic causal structures. We introduce CausalDS, a benchmark for evaluating causal reasoning in agentic data-science workflows. Each benchmark instance is a scene consisting of a sampled structural causal model (SCM) with generated observational data and an accompanying synthetic natural-language story grounded in a realistic domain. We optionally ground the composition of the benchmark components in empirical distributions obtained from real-world datasets, thus retaining empirical structure while reducing the "causal parrot" risk through completely synthetic generation. From each scene, we then derive tasks spanning all three of Pearl's rungs, with typical data-science prediction tasks appearing as Rung 1. Most tasks include a data science coding component, where the model typically needs to use several tools to arrive at the final answer due to the frequent presence of imperfect observations, which are generated by an observation model. Additionally, recognizing when a question admits no warranted answer and abstaining is treated as a first-class scored outcome. The benchmark thus jointly evaluates symbolic causal reasoning, data science, uncertainty quantification, abstention, and tool use/coding.

We present a general neurosymbolic reasoning and learning methodology based on a modular integration of answer set programming with an energy based model substrate. Key contributions are: (1) supporting joint optimisation in the continuous latent space through explicit ASP-based declarative semantics fully incorporating background knowledge, constraints, non-monotonic inference; and (2) advancing recent works at the interface of answer sets, probabilistic logic, and answer set modulo theories by providing a generalised model and practical platform for ASP-centric robust, end-to-end training for applications in dynamic domains (e.g., involving perception and interaction). We provide a practical implementation, and demonstrate basic use and application (with MNIST), and evaluate with the visual question-answering benchmark Clevr and the multi-object tracking benchmark MOT.

Black box auditing of language models is an essential pre-deployment tool, but it may miss subtle forms of misalignment and hidden information. To better elicit hidden information during an auditing process, we introduce \emph{overthinking}: the process of using reasoning task vectors to amplify the propensity to think out loud of reasoning models. Given the parameters of a non-reasoning instruct model $M$ and reasoning-distilled model $R$, we define the \emph{overthinking model} as $\boldsymbol{\theta}_{\mathcal{O}_\alpha} = \boldsymbol{\theta}_{\mathcal{M}} + \alpha(\boldsymbol{\theta}_{\mathcal{R}} - \boldsymbol{\theta}_{\mathcal{M}})$, where $\alpha > 1$ amplifies reasoning beyond the pure reasoning model $R$. Additionally, we introduce new layer-wise attenuation strategies that selectively amplify reasoning without losing quality and coherence of model outputs. We demonstrate that overthinking models are more likely to reveal hidden information across four experimental settings, across 2B-32B models. Our findings suggest that reasoning amplification may surface secrets or unintended behaviors acquired during training up to $10\times$ more frequently than the original reasoning model. How secrets surface depends on the secret type: some require perturbation along the reasoning direction, while others yield to any sufficiently large weight perturbation.

In this paper, we study the automatic schema generation problem: given a collection of historical ship maintenance and operational reports across multiple form categories, automatically discover compact and informative schemas that capture the essential information requirements of each report type. To address this challenge, we propose ASMR, a modular agentic framework consisting of two specialized agents. A Field Generation Agent extracts semantic concepts from historical narratives and generates candidate schema fields through adaptive multi-granularity clustering, while a Structural Optimizer Agent employs reinforcement learning to identify compact, informative, and non-redundant schema representations. The resulting schemas can guide report authors toward producing more complete, consistent, and actionable reports. Preliminary results demonstrate the promise of the proposed approach and highlight several open research challenges at the intersection of data management, agentic AI, and human-centered AI.

As part of a series on first-principles modeling of cognitive functions, this paper attempts to provide a mathematical formulation of thinking and perception. It formally derives slow thinking or more generally, active perception, and encompasses the design, training and inference of slow thinking large language models. Our starting point is the lifting and projection of probability distributions on the observable and latent spaces, with the objective of representing complex data distributions by simple function families such as neural networks. A theory called "active lifting" is proposed, based on the sampling of latent sequences and an intrinsic drive to reduce uncertainty with maximum rate. It derives a large design space, containing the slow thinking models in a subspace that we call the static theory. These models are positioned on the representation hierarchy and sampler hierarchy induced by the static theory, and can be upgraded by climbing the two hierarchies. Active lifting further derives an inference process with an internal time axis, and a training objective that resembles minimum-length coding as well as the invention of languages. Thus, it characterizes the agency of perception, including the emergence of the slow thinking formats. Technical by-products of this theory include a three-stage pathway for improving slow thinking models, a unified approach to constructing encoders and generative models for all data modalities, a priori formation of human-like visual representations, and a possible solution to policy collapse.

A central challenge in building intelligent systems is enabling agents to jointly perceive complex inputs, form hypotheses about hidden patterns, and design informative experiments to test them. To study this problem, we propose ZendoWorld, a controlled interactive environment in which agents must infer a logical rule about visual game observations, acquire information by proposing new scenes, and refine their hypotheses based on feedback from the game environment. We evaluate several agents spanning pure VLM reasoning, Bayesian particle filtering, dynamic concept discovery, and neuro-symbolic methods. Our main findings are: (1) high accuracy in predicting labels for observed examples does not imply recovery of the underlying rule; (2) perception and induction are distinct bottlenecks for different agent classes; and (3) VLM-based agents propose near-uninformative experiments, failing to actively reduce hypothesis uncertainty. To compare these results, we collect human data on the task, which reveals a gap in inductive reasoning, particularly for more complex rules. Overall, ZENDOWORLD takes an important step toward evaluating intelligent agents and identifies concrete avenues for improvement, particularly in domains like scientific discovery.

Long-term persona agents must remain identifiable while adapting to new events, relationships, evidence, and social conditions. We identify self-locking as a runtime failure mode in continuing persona-life loops: locally plausible events keep appearing while the generated life collapses toward familiar environments, weak relationships, suspended decisions, and stale life stages. We trace this failure to model-level convergence toward high-probability behavioral channels and system-level context gravity from State, memory, history, and environment summaries. We introduce AutoPersonas, a multi-timescale life-environment engine for bounded persona-level recursive self-evolution. It separates environment-side Occurrences, accumulated Observations, and persona State. Its OSO loop admits divergent future-facing material while requiring evidence-governed absorption before State or reachability changes. A three-year compressed simulation exposed environment watermark shells, occurrence-hardening gaps, slow-change accumulation failures, recursive indecision, and weak relationship persistence. An eight-model 40-day stress test generated 1,600 events and found mean rolling 5-day action-category repetition of 95.2%-97.6%, with all models crossing 90% by day 11. Semantic re-keeping found 79.0%-88.0% macro-theme repetition across all direct-loop runs. In a same-runtime 40-day A/B, context-slice masking plus per-sample divergence targeting reduced macro-theme repetition from 61.8% to 36.3% and roughly doubled cumulative theme count. A juvenile-goblin fictional-world run reproduced the anti-fixation regime without hard real-world intrusions. These results support a bounded claim: separating controlled divergence from evidence-governed absorption can reduce persona-environment self-locking while preserving identity continuity.

Large language models increasingly serve as teachers generating training data for smaller students. Prior multi-teacher knowledge distillation methods merge outputs without determining which frontier model teaches best, often relying on an LLM judge biased toward its own outputs. We introduce a compete-then-collaborate framework where four frontier AI teachers (Claude, Codex-GPT, Grok, Gemini) are ranked head-to-head by an execution-based judge (unit tests and stdin-stdout checks) with fairness controls, and then collaborate to build a verifiable curriculum for a student (Qwen2.5-Coder). We report three findings. (1) Under execution verification, all teachers solve standard problems near-perfectly after self-correction (99-100%) due to a saturation effect, but harder competition problems separate them (Gemini 77% > Claude 69% = Codex 69% > Grok 50%); however, the robust student-side results do not depend on teacher ranking. (2) Imitation (SFT) on verified solutions does not improve, and can degrade, an already-competent student at 7B and 32B (e.g., from 76.7% to 72.7% on MBPP-test, and 5.9% to 2.9% on competition problems). (3) Using the same collaborative curriculum as a reinforcement learning with verifiable rewards (RLVR) environment improves the student (from 5.9% to 8.8% peak on competition problems, a +49% relative gain), reversing SFT's direction. The value of AI-teacher collaboration lies not in pooling answers to imitate, but in jointly constructing a verifiable environment where the student learns by doing. We release a reproducible on-prem pipeline (NVIDIA GB10) with framework patches for running GRPO on a bleeding-edge stack.

Large language models (LLMs) have shown strong performance on isolated psychiatric tasks, including dialogue, diagnosis, and treatment planning, yet existing benchmarks rarely simulate complete psychiatric clinical encounters. We introduce $\textbf{MentalHospital}$, a virtual evaluation environment for LLM-based psychiatric clinical encounters. MentalHospital instantiates the Subjective Interviewing, Objective Examination, Diagnostic Assessment, and Treatment Planning (S.O.A.P.) workflow, using skill-augmented standardized patients constructed from 1,193 de-identified psychiatric electronic health record (EHR) cases spanning all major ICD-11 categories and 76 disorders. Each encounter is assessed through a dual-track protocol that combines objective comparison against EHR-derived references with subjective assessment of clinical process quality. To scale specialist judgment, we develop $\textbf{MentalEval}$, five domain-specific evaluators covering communication empathy, interviewing professionalism, clinical-note quality, diagnostic rigor, and treatment appropriateness, trained with rubric-grounded SFT and expert-guided DPO. Survey responses from 22 clinicians support MentalHospital's clinical fidelity (3.88/5), while MentalEval achieves strong expert alignment with an average QWK of 0.944. Benchmarking shows that even the strongest LLM trails clinicians by 37.28 percentage points in objective psychiatric competence, with mental status assessment as a key bottleneck.

High-volume structured extraction pays a large model's latency on every item, so distilling the task into a small on-device model is attractive: comparable output at a fraction of the time and cost. We measure what that distillation actually delivers, per sub-task. Each news article is mapped to one JSON object with a short summary and five categorical labels. We distill an 8B reasoning teacher (deepseek-r1:8b) into a 0.6B student (Qwen3-0.6B; QLoRA, three seeds), and add two teacher controls: a same-size non-reasoning teacher and a larger managed pipeline. A blinded, reference-free, three-judge panel scores every arm against the full article, alongside two non-distillation baselines, few-shot prompting and constrained decoding. The student runs at about 0.8 s per article against the teacher's 39 s, and recovers 58% of the base-to-teacher gap on summary quality, beating its primary baseline (constrained decoding) by +16.8 points and few-shot prompting by a secondary +4.9. A same-size non-reasoning teacher trains a student no better than the untuned base, so the summary gain follows from the teacher's reasoning nature rather than its scale. Capabilities then split by teacher: the reasoning teacher transfers writing quality and the managed pipeline transfers label diversity, while a same-size instruction teacher's students stay more grounded on the 22 short, thin-source articles in the 93-item test set (74 versus 55 faithful), where the reasoning-lineage student fabricates. That grounding difference is a consistent ordering rather than a significant aggregate effect, and the subgroup is small, so we report it as a direction. Because no single engine wins every field, the deliverable is a per-field routing map for on-device enrichment.

Existing retrieval-augmented generation (RAG) systems treat web pages as flat text, losing the structural and semantic signals encoded in HTML. We present PolyUQuest, a verifiable, structure-aware web RAG framework built on a heterogeneous graph that unifies hyperlink topology between pages, DOM hierarchy within pages, and entity-relation knowledge across pages. A two-tier router dispatches each query to one of three retrieval modes matched to its structural need, including direct block retrieval, cross-page graph traversal, and multi-hop entity reasoning. Every answer is fully verifiable, as each cited block carries its source page, heading path, and entity links so that users can trace any claim back to its structural evidence. We evaluate on the official websites of the Hong Kong Polytechnic University (PolyU), comprising 4,240 pages, 31,086 DOM blocks, 29,119 entities, and 37,680 relations, together with a multi-type evaluation benchmark. PolyUQuest outperforms existing RAG systems in answer correctness, coverage, and faithfulness, while consuming significantly fewer LLM tokens per query. The demonstration provides an interactive interface for inspecting cited answers, comparing retrieval traces across routing modes, and exploring evidence graph paths. PolyUQuest is being prepared for deployment as a student-facing QA service at PolyU.

Large language models (LLMs) have demonstrated rapidly improving long-context capabilities, prompting a wave of benchmarks designed to evaluate them. However, existing long-context evaluations - from Needle-in-a-Haystack (NIAH) tests to more recent multi-hop reasoning and summarization tasks - predominantly measure average-case performance, and many are either saturated or lack robustness. Notably absent is a systematic way to probe how models perform as we scale up the difficulty of tasks along various axes. We address this gap by proposing PredicateLongBench, a benchmark that stress-tests long-context reasoning by asking models to identify the longest contiguous subsequence of words in a long input that satisfies given predicates/constraints (e.g., lexicographic ordering), drawn from a broader predicate class. The central innovation of our benchmark is the identification and systematic exploration of multiple different axes of difficulty which test multiple aspects of long context understanding. We provide two complementary generation pipelines - a fully synthetic setup using random word-like strings, and a real-world setup that samples words from natural documents while preserving their distributional properties. We find that frontier models struggle to perform well as we scale up the difficulty of tasks along our axes, demonstrating the utility of our benchmark in understanding the limitations of current long-context capabilities. Furthermore, the tasks in PredicateLongBench, though challenging, are conceptually simple and do not require LLM-based generations or judges.

Current AI evaluation frameworks focus primarily on technical performance, including accuracy, robustness, reasoning ability, and policy compliance. These measures remain essential, but they are not sufficient for systems that interact directly with users through natural language. Human-facing AI systems are increasingly used as advisors, coaches, tutors, and companions. In these roles, their responses can shape how users reason, interpret emotions, form beliefs, calibrate trust, and make decisions. The relevant unit of evaluation is therefore not only the model, but the human-AI interaction. This paper introduces psychological competence as a missing dimension in AI evaluation. We define psychological competence as the capacity of a human-facing AI system to support user cognition, emotional interpretation, and behavioral decision-making in ways that are appropriate to the user, context, and purpose of the interaction. This includes interaction properties such as framing, tone, perceived authority, responsiveness, uncertainty handling, and conversational guidance. Existing evaluation approaches capture parts of this problem but rarely assess these psychological effects directly. Drawing on behavioral science and human-AI interaction research, we outline a conceptual framework for psychological competence and its core domains. Rather than proposing a specific benchmark, we define the construct, clarify its boundaries, and describe how it may be assessed through scenario-based probes, structured human evaluation, and model-assisted evaluation methods. We argue that psychological competence should become a core consideration for model providers, deploying organizations, researchers, and regulators concerned with the real-world effects of human-facing AI systems.

Vehicle intention prediction is a pivotal aspect in the agility and safety of autonomous vehicles in all driving scenarios; if genuine enhancement of autonomous vehicles are required, we need to make them adopt human interpretation of driver's intention especially in cases that require a lot of human interaction as well as complex driving behaviors like the ones at intersections, roundabouts and emergency cases such as sudden stops where vehicle intention prediction helps in taking the correct evasive action within a real time period where every second of action makes an impact and can prevent a catastrophe from taking place. In the worst case, it helps minimize the damage and make safety a priority. Intention prediction can also be used to enhance trajectory prediction (intention conditioned trajectory prediction). In this study, The INTENT framework is proposed using LSTM model to predict the vehicle's intention at intersections 2 seconds ahead of the event occurrence to predict whether the cars in intersections are going straight, turning left, or turning right. Various model experiments and ablation study are thoroughly tested on InD dataset achieving 99.71% accuracy.

Modern AI models achieve strong performance on many established benchmarks, yet they still fail on tasks that humans find almost trivial, such as manipulating a string or drawing a dog with five legs. These examples suggest that existing benchmarks may under-measure persistent blind spots in current systems. We introduce $\texttt{blind-spots-bench}$, a benchmark designed to expose such blind spots through tasks that appear simple for humans but remain challenging for modern AI. We collect raw questions from students in an AI course, clean and annotate them with structured reference solutions, and propose a task taxonomy tailored to the resulting dataset of 235 samples. We further develop an automated grading pipeline to evaluate a wide range of models, including open-weight and closed-source language, vision-language, and image-generation models. Our analysis on $\texttt{blind-spots-bench}$ reveals that closed-source frontier models can substantially outperform open-weight models with even $\approx10\%$ gap, even when they attain comparable performance on existing benchmarks. A more fine-grained analysis shows that no single model dominates across all task types, and that some tasks remain challenging for all evaluated models. These results highlight the value of $\texttt{blind-spots-bench}$ as a diagnostic stress test for identifying concrete weaknesses in current modern models.

Human mobility data are essential for transportation optimization, urban planning, and resource allocation, yet real-world mobility data are costly to collect and difficult to share due to privacy concerns. Recent diffusion-based methods have shown promise in synthesizing realistic mobility patterns, but they typically rely on continuous or latent spatio-temporal traces, limiting their ability to natively model discrete semantic events with explicit region, activity, time, and interval structures. To address this issue, we introduce MobiDiff, an end-to-end discrete diffusion framework that efficiently generates mobility data by directly denoising multi-channel semantic skeletons, avoiding the costly interpolation, latent trace construction, and coarse-to-fine realization pipelines widely used in existing diffusion-based methods. Specifically, MobiDiff decomposes each human check-in event into spatial, activity, and temporal channels, and employs structured event-, group-, and channel-level masking to jointly capture trajectory-level mobility patterns and within-event dependencies. We evaluate generation fidelity, privacy-preserving, and efficiency on three large-scale real-world datasets from Atlanta, Boston, and Seattle. Results show that MobiDiff effectively preserves trajectory length and temporal interval distributions while remaining competitive across broader mobility statistics; it is also much faster than state-of-the-art methods, e.g., 5.3$\times$ faster than GeoGen on average during inference. These findings suggest that discrete diffusion offers an interpretable and efficient framework for synthetic mobility data generation.

With the widespread deployment of basic models in edge intelligence, communication bandwidth has become a core bottleneck restricting the scalability of federated learning. Although one-shot federated learning alleviates this problem by minimizing communication rounds, existing iterative fine-tuning or knowledge distillation methods still face challenges such as high server-side computational costs and hyperparameter sensitivity. Analytical federated learning achieves efficient gradientfree aggregation using least-squares closed-form solutions, but in environments with non-independent and identically distributed data, its static feature assumptions fail, leading to feature manifold misalignment and severely impairing model performance. To address this contradiction, this paper proposes the FedOPAL framework. This framework adapts the visual prompts as feature rectifiers, actively correcting the feature distribution of heterogeneous data to a linearly separable space by applying local proximal constraints, thereby satisfying the theoretical assumptions of analytical federated learning. Experimental results show that FedOPAL not only significantly outperforms the original analytical methods on several benchmarks, but also achieves accuracy comparable to state-of-the-art iterative methods while maintaining zero server-side training costs, providing a new engineering paradigm for efficient collaboration of large models on the edge.

Fine-tuning LLMs to inject new knowledge faces a critical challenge: LLMs can quickly memorize new facts, yet fail to use them for downstream reasoning tasks. We formalize this failure as the \textit{\textbf{Knowing--Using Gap}}, characterized by an accuracy gap and a temporal lag between memorization and generalization. To understand this phenomenon, we fine-tune LLMs with unseen knowledge and monitor the spatial permeation dynamics of the knowledge internally using a novel intervention technique called self-patching. Self-patching identifies activation locations where relocating representations substantially improves failed generalization cases. These results are consistent with a knowledge-circuit misalignment hypothesis: memorized representations can exist internally but may not be routed to computation-effective layers. To demonstrate the practicality of this diagnostic finding, we design a simple heuristic strategy which recovers 58--75\% of the oracle headroom in generalization failure. Experiments are done cross-domain for the robustness of this finding.

The application of lightweight Large Language Models in rule-based scientific domains remains severely limited by their tendency to mimic linguistic patterns rather than reproduce axiomatic reasoning, causing frequent hallucinations. Here, we show that G-Frame, an adaptive multi-agent framework integrating Bayesian and team game principles, establishes an automated closed-loop for high-quality data synthesis and model training. By forcing the internalization of domain constraints through structured reasoning, we synthesized a specialized corpus of 363,045 chains-of-thought and 199,589 question-answer pairs. The resulting 7B model OmniChem achieves performance parity with GPT 4o mini on custom benchmarks and ChemBench while exhibiting a 79.46% reduction in hallucinations relative to its base architecture. We further demonstrate the advanced capabilities of OmniChem in molecular design and synthesis planning. This work establishes a scalable paradigm utilizing adaptive multi-agents to overcome inherent reasoning deficiencies, offering a feasible pathway for accelerating knowledge discovery in specialized scientific fields.

The rapid integration of Large Vision-Language Models (VLMs) into critical infrastructure promises to revolutionize personalized healthcare and dietary management. However, in the domain of food systems, autonomous agents face a unique and persistent challenge: the "Systemic Information Asymmetry" between visual appearance and intrinsic nutritional composition. Existing benchmarks primarily focus on coarse-grained classification tasks, such as food category recognition, which fail to evaluate the intricate reasoning chain required for real-world dietary management -- specifically, the ability to traverse from identifying hidden ingredients to estimating physical mass, and finally synthesizing safety-critical medical advice. In this paper, we introduce OmniFood-Bench, a comprehensive benchmark constructed from the MM-Food-100K dataset. Unlike previous works, OmniFood-Bench evaluates VLMs across three progressive capabilities: Basic Perception (Ingredients & Cooking Methods), Quantitative Reasoning (Portion Size & Nutritional Profiling), and Safety-Critical Advisory (Disease-Specific Recommendations). We evaluate six state-of-the-art VLMs, including gpt-5.1, gemini-3-flash, and qwen3-vl-8B. Our extensive experiments reveal a startling "Semantic-Physical Gap": while models achieve near-human accuracy in naming dishes, they exhibit catastrophic failure in mass estimation and frequently hallucinate benign advice for high-risk diabetic profiles. This work establishes a rigorous standard for trustworthiness in autonomous agents deployed for public health. The code and datasets are available in: https://anonymous.4open.science/r/OmniFood-Bench-7D0B

I-JEPA and V-JEPA learn by matching latent predictions to target encoder outputs rather than regenerating the original input, and this has worked well for images and video. We explore whether the same objective works for compact network fingerprints. We built JA4-JEPA, a Transformer-based model trained on JA4, JA4H, JA4S, and JA4X subfields drawn from JA4DB and CIC-IDS- 2017. The training data combines roughly 397K samples from both sources, though no single sample contains all four view families. We evaluated the learned representations with a frozen kNN probe on protocol-family classification across TLS, DNS, and SSH. On 39,416 heldout samples the model achieved a cosine similarity of 0.9899 and a kNN accuracy of 0.9220. These results indicate that JEPA-style predictive learning can produce useful embeddings from JA4-derived fingerprints, even with incomplete view overlap across sources. Keywords: JA4, network fingerprinting, JEPA, predictive representation learning, self-supervised learning

Biomedical language evolves rapidly as new discoveries emerge, causing traditional text models to lose semantic fidelity over time. Static embeddings and co-occurrence graphs cannot capture such evolution, leading to performance degradation in retrieval and knowledge discovery tasks. This paper introduces a Drift-Aware Temporal Graph Rewiring (DATGR) framework that models concept evolution by dynamically updating co-occurrence edges based on estimated semantic drift. Instead of retraining embeddings for each time slice, DATGR performs lightweight, feedback-driven rewiring using a logistic update rule applied to edge weights. Evaluated on the Biomedical Multi-Relation Corpus (BIOMRC), the method achieved a mean Area Under the Receiver Operating Characteristic (AUROC) improvement of approximately 0.066 absolute difference (0.699 vs. 0.633) over a static baseline. Area Under the Precision-Recall Curve (AUPRC) remained comparable (0.738 vs. 0.744), showing that drift-aware adaptation enhances link-prediction recall without a loss in precision. These results demonstrate that edge-level adaptation effectively captures temporal semantic change in evolving biomedical text while remaining computationally efficient and interpretable.

Understanding perceptual differences between autistic and neurotypical adults requires behavioral assays that are sensitive, reliable, and mechanistically informative. Facial emotion perception is a useful test case because group differences have been reported, but findings vary across studies. Here we show that this variability may reflect image-level sparsity: autistic-neurotypical differences in emotion judgments were concentrated in a small subset of diagnostic facial expressions rather than spread uniformly across stimuli. We trained population-specific artificial neural network models to predict image-level judgments for autistic and neurotypical participants, then used these models to select novel faces predicted to maximize group separation. In an independent cohort, model-selected images produced larger behavioral differences than matched random images. We then used the same models with a generative adversarial network to transform diagnostic images toward greater predicted group agreement. In phenotype-matched validation, synthesized images reduced behavioral separation relative to their matched originals. These results establish a model-guided framework for discovering and transforming stimuli that reveal population-specific perceptual differences. More broadly, they show how behavioral phenotyping can move beyond averaging across fixed stimulus sets toward optimized assays that identify the conditions under which neurodivergent perception diverges or converges.

For urban managers and designers, improving the functional attributes of urban communities to enhance territorial resilience in the face of complexity and uncertainty is crucial. Currently, community planning often follows a top-down approach and lacks effective metrics to quantify informal behaviors of residents, leading to frequent conflicts with original plans. This study introduces CommuniWave, a machine learning model designed to efficiently detect and quantify the Degree of Informal Behavior (DIB) in urban communities. The model integrates a Behavior Capture Net (BCN) based on mmaction2, a self-developed YOLOv10 model (YLX), and a Behavior Eval Model (BEM) using random forest. Ultimately, by generating DIB fluctuation charts from street videos, the model facilitates dynamic monitoring, supporting urban managers in making refined decisions to enhance the overall resilience of communities.

Multimodal emotion and sentiment recognition is commonly addressed by early fusion, which concatenates modalities before classification, or late fusion, which combines independently trained unimodal predictors. Early fusion can be accurate but monolithic, while late fusion is modular but may lose cross-modal interactions. This paper revisits XAI-guided adaptive fusion (\xgaf), a tree-based mixture of unimodal and cross-modal experts whose sample-level weights are derived from TreeSHAP attribution magnitudes. We focus on the effect of SHAP attribution reduction when experts have unequal feature dimensionalities. In this setting, mean-abs and median-abs reductions can suppress high-dimensional cross-modal experts, whereas sum-abs reduction preserves total attribution mass. On MELD 7-class emotion recognition, sum-abs \xgaf{} nearly matches early fusion across three face-sequence aggregators; the Transformer variant reaches 0.5983 \wf{}, compared with 0.6018 for early fusion and 0.4598 for probability-average late fusion. McNemar testing shows no significant difference between sum-abs \xgaf{} and early fusion on MELD ($p=1.000$), while \xgaf{} remains significantly better than late fusion ($p<0.0001$). On CMU-MOSEI 3-class sentiment recognition, sum-abs \xgaf{} reaches 0.6519 \wf{}, slightly exceeding early fusion (0.6485) and late fusion (0.5696). Ablation studies show that the main gain comes from adding cross-modal experts, especially the trimodal expert, rather than from complex per-sample routing. Diagnostics further show that mean-abs and median-abs weights are nearly uniform, while sum-abs weights concentrate on the trimodal expert. Thus, the main contribution is a transparent empirical analysis of how SHAP reduction, expert dimensionality, and cross-modal expert design affect modular multimodal fusion.

Hepatocellular carcinoma (HCC) is a common malignancy and a leading cause of cancer-related mortality. Current guidelines and staging systems provide coarse categories, but often miss within-stage heterogeneity and the clinical context in electronic medical records (EMRs). We present HCC-STAR (Hepatocellular Carcinoma Staging, Treatment And pRognosis), a clinically aligned large language model that reads routine EMR narratives and jointly outputs risk score-based staging, ranked guideline-consistent treatments with evidence-based rationales, and individualized survival estimates. We curated about 30,000 HCC cases from SEER and expanded them into EMR-style narrative training data using a clinician-validated, prompt-based augmentation workflow. On this corpus, we developed a knowledge-aligned reasoning framework optimized with a step-verifiable composite reward, moving beyond text-level memorization of clinical guidelines. In a multi-center cohort of 6,668 patients from 12 hospitals in China, HCC-STAR achieved state-of-the-art performance in treatment recommendation and risk stratification compared with clinical guidelines and competitive models, including GPT-5 and Gemini-2.5 Pro. Hypothetical overall-survival analysis showed a median survival of 51 months under adherence to HCC-STAR recommendations, compared with 29 and 32 months under BCLC and CNLC. In clinician-centric evaluations, blinded hepatobiliary specialists rated HCC-STAR's reasoning and evidence-based justifications as trustworthy. The model surpassed resident and attending physicians in treatment accuracy and helped physicians make more accurate decisions faster when used as an assistant. These findings support HCC-STAR as a reliable and verifiable decision-support system for risk stratification and precision therapy in HCC.

Consumer-facing health chatbots powered by large language models (LLMs) are increasingly used for symptom assessment. However, chatbot development and evaluation often rely on cooperative, articulate, simulated patients. We analysed 2,053 real patient-chatbot conversations and found that communication patterns and expression of emotions vary widely across users. We developed a patient simulator that separately models clinical content, emotional state, conversational strategy, and communication style. In a Turing-inspired evaluation of realism with 15 human graders, simulated conversations were nearly indistinguishable from real ones, with human graders achieving an accuracy of 55%. We used five distinct patient personae, across 1,164 clinician-graded cases, to evaluate the performance of four LLMs in urgency assessment. We found that communication style can significantly alter triage outcomes. Patient-centred conversational artificial intelligence must accommodate communication diversity: systems designed for idealised, rather than realistic, interactions risk underperforming and amplifying health disparities when deployed in the real world.

Self-interested agents, left unconstrained, tend toward defection in repeated social dilemmas, causing cooperative gains from trade to collapse. This paper investigates what formal mechanisms, layered on top of unrestricted communication, are sufficient for a society of such agents to maintain market stability, and how resilient those mechanisms are to adversarial attack. We instantiate the research question as a multi-agent marketplace simulation where 18 LLM agents (DeepSeek-V3) with complementary production specialties must trade within a constrained social network to obtain utility. We conduct two experimental phases: (1) a mechanism comparison across eight conditions under progressive troll injection over 200 rounds, identifying Mediation as the top-performing mechanism; and (2) adversarial red-teaming of Mediation using iteratively prompt-optimised LLM-driven trolls, finding that the best attack (v6) reduces honest-agent utility by 13.3% but cannot collapse the market. Mediation enables recovery even under sustained adversarial pressure. We define adversarial robustness as a mechanism's ability to sustain positive honest-agent utility under optimised attack, and find that Mediation is robust: it can be bent but not broken.

As agentic AI systems are increasingly applied to cyber-physical environments, their evaluation requires assessment of both task performance and trustworthiness. In decentralized energy markets, autonomous agents may improve market utility, but may also exploit invalid physical data, create artificial liquidity, and produce unstable governance decisions. Therefore, we propose SolarChain-Eval, a physics-constrained benchmark for evaluating trustworthy economic agents. It formulates market governance as a Gymnasium-compatible Markov Decision Process, where agents make hourly decisions. SolarChain-Eval evaluates each policy across multiple dimensions, including market utility, physical safety, slippage, action smoothness, spatial fairness, and auditability. To support agentic evaluation, SolarChain-Eval incorporates an LLM-based Planner/Auditor layer. The Planner defines episode-level action bounds and audit rules, while the Auditor reviews and revises high-risk actions. All interventions are recorded through structured logs, including trigger signals, proposed actions, revised actions, and audit rationales. Experiments with static, random, myopic, RL, and RL+LLM policies reveal a clear utility-safety trade-off. RL agents improve market utility but can still produce unsafe behavior. When the physics penalty is removed, reward-maximizing agents exploit invalid generation and increase artificial liquidity. The LLM Planner/Auditor improves auditability and mitigates selected risks, but it cannot fully compensate for a misspecified reward function. These results indicate that trustworthy agentic AI evaluation requires both physical constraints and transparent intervention traces. We release data and code as open access on GitHub for replicability.

In long-horizon tasks, decision-relevant state is often scattered across an expanding trajectory, while the action agent must surface it and act. As trajectories grow, task requirements, environment facts, prior attempts, diagnoses, and open subgoals can be buried in the context window or pushed beyond it, failing to influence decisions when needed. We call this failure mode "behavioral state decay". We study memory as an active intervention mechanism rather than passive retrieval. A separate memory agent runs alongside an unmodified action agent, updating a structured memory bank from the recent trajectory and deciding whether to inject a memory-grounded reminder or remain silent. The module is plug-and-play with frontier action agents and existing agent harnesses. Across Terminal-Bench 2.0 and $\tau^2$-Bench, it improves pass@1 for both weaker and stronger action agents, with gains of +8.3 pp on Terminal-Bench and +6.8 pp on $\tau^2$-Bench. Ablations show that selective intervention outperforms passive bank exposure, always-on injection, advisor-only guidance, and general retrieval. As an early step toward open-weight memory policies, we train Qwen3.5-27B on SETA using SFT and GRPO, improving validation reward and achieving partial transfer to Terminal-Bench.

Post-training quantization is widely used to deploy large language models in resource-constrained settings, yet its evaluation relies almost exclusively on accuracy and perplexity. We show that these metrics fail to capture behavioral changes induced by quantization. We introduce correctness agreement, a decision-level metric that measures overlap in correct predictions between a base model and its quantized variants, independent of absolute accuracy. Across multiple models and quantization schemes from 8-bit to 2-bit, we find that behavioral divergence emerges under moderate quantization even when task performance appears preserved. To explain this effect, we analyze quantization as a structural operator on attention weights and quantify layer-wise distortions using statistical and distributional measures. Our results reveal non-linear breakpoints at low bit-widths and show that query and key projections are consistently more sensitive than value and output projections. These findings expose an illusion of equivalence between base and quantized models and motivate behavioral evaluation beyond conventional performance metrics.

Large language model (LLM) applications increasingly use explicit workflows for tool use, retrieval, branching, checkpointing, and human approval. Existing workflow systems already address many execution concerns. This paper proposes a Lisp-inspired but language-independent conceptual model: symbolic forms, object identity, and live-image thinking are used as explanatory lenses, not implementation commitments. In this model, workflow definitions, workflow instances, inference records, context snapshots, and dependency relations are represented as persistent knowledge objects in a shared knowledge substrate. Its central semantic distinction is between derive and infer: derive is deterministic computation over available state; infer is mediated LLM judgment under declared context and executor-controlled capability policy. The result is a preliminary conceptual account of semantic persistence: workflows do not merely produce knowledge and leave traces, but can themselves be represented as inspectable, resumable, and reviewable knowledge objects, while formal transition semantics remain future work.

Recent advances in Vision-Language Models, Large Language Models, and Multimodal Large Language Models have improved autonomous driving tasks such as scene understanding, decision making, trajectory prediction, and visual question answering. However, evaluating whether these models can reliably reason about safety-critical incidents remains challenging. To address this gap, we present AUTOPILOT-VQA, an incident-centric visual question answering benchmark for dashcam video understanding. The dataset evaluates different systems through structured questions designed around real-world driving incidents and near-incidents. The benchmark covers diverse safety-relevant categories, including weather and lighting conditions, traffic environment, road layout, road surface state, signage, involved entities, accident occurrence, impact location, and avoidability-related reasoning. By requiring models to answer grounded questions about both contextual scene properties and event-level incident details, AUTOPILOT-VQA moves beyond object recognition toward temporally grounded, safety-aware reasoning. The dataset is released as part of the AUTOPILOT CVPR 2026 competition and provides a standardized benchmark for assessing the reliability of autonomous driving systems in different scenarios. Our benchmark support developments for more interpretable, robust, and safety-conscious vision-language systems for real-world autonomous driving.

In this study, we present a large-scale descriptive analysis of the use of an AI-based learning assistant (Syntea) in higher education. Based on objective log data from 77,543 students enrolled in distance studies, we examine usage patterns across gender, age group, study cluster, degree, and study mode. To date, existing research on educational chatbots has largely relied on comparatively small samples and self-reported survey data, while large-scale evidence on actual usage behavior remains limited. Our findings show that Syntea is already embedded in the study routines of many learners, but that usage differs across demographic and structural contexts. By identifying these patterns, our study provides an empirical basis for the further development of AI-based learning support and contributes a large-scale analysis of educational chatbot usage in higher education.

Scientific ideas rarely start from a blank page. They inherit mechanisms, repair known limitations, and recombine pieces of earlier work, much like biological genomes. Current benchmarks still say little about whether AI systems can follow this inheritance structure. We present IdeaGene-Bench (IG-Bench), a benchmark for scientific lineage reasoning and lineage-grounded idea generation. IG-Bench is organized around the IdeaGene framework: each paper or proposal is represented as a set of minimal, typed, evidence-grounded Idea Genome objects, and a GenomeDiff aligns these objects to record inheritance, mutation, loss, external import, and novel insertion under six operational evolutionary dynamics. The benchmark contains 1,961 golden lineage traces, 1,085 curated Idea Genome objects, and 920 pairwise GenomeDiff records across 10 scientific domains. It supports two evaluations. IG-Exam (42 task types, 1,029 instances) tests closed-form lineage reasoning across Idea Genome abstraction, inheritance tracing, evolutionary reasoning, and lineage verification. IG-Arena evaluates generation with a lineage-conditioned Population-Evolution Score(PES), asking whether a proposal can be inserted as a coherent descendant of a given lineage population: it should inherit the right Idea Genome objects, vary meaningfully from nearby work, and offer selection value for future research. Experiments on 14 LLM-based scientists expose a compositional bottleneck. The strongest system reaches only 27.3% exact accuracy on lineage reasoning, and structured lineage context reshuffles system rankings rather than helping every participant uniformly.

In this age of social media, sites like Twitter have become meeting places for people to share their views and feelings on a wide range of issues and current events as they unfold in real time. Sentiment analysis, a critical application of NLP, has become indispensable due to the massive influx of user-generated content, enabling the extraction of meaningful insights from the opinions and emotions expressed in textual data. Sentiment analysis on Twitter employs sophisticated computational techniques to categorize tweets into positive, negative, or neutral sentiments. This method not only examines individual expressions but also analyzes vast databases related to specific subjects or events. By spotting these emotions, machine learning models help improve public opinion interpretation and trend forecasting. This paper examines the effectiveness of various machine learning and deep learning approaches. Designed for this use, the system evaluates logistic regression, random forest, na\"ive bayes, gradient boosting, and LSTM networks, among other algorithms applied in sentiment classification. This work identifies the optimal sentiment analysis model using a Kaggle Twitter dataset that has been preprocessed through tokenization, lemmatization, and stopword elimination. Emphasizing the better performance of the LSTM approach, the model attained a training accuracy of 90.98%, a testing accuracy of 80.00%, and a micro-average ROC- AUC score of 0.92. These results show that the model outperforms conventional machine learning techniques in capturing contextual and sequential textual aspects.

Recent developments in AI for Mathematics (AI4Math), especially Large Language Model (LLM)-driven theorem provers, has achieved remarkable success in formal proof generation for well-defined mathematical problems through Interactive Theorem Proving (ITP) languages. However, current systems remain fundamentally limited in tackling frontier research mathematics, such as discovering new theorems or resolving open conjectures, which are often open-ended, under-specified, and involve multiple layers of abstraction. We argue that the next leap in AI4Math systems requires a decisive shift from predefined problem-solvers to research agents that can address frontier mathematical challenges with rigorous formal mathematical reasoning. In this position paper, we provide a systematic review of the field, covering datasets, auto-formalization, and proof synthesis. More importantly, we identify core limitations of existing systems in serving as mathematical research agents, examining issues across datasets, relational structure, mathematical exploration, tool ecosystem, and human-AI collaboration, outlining a strategic road-map for the future of AI4Math.

Training tool-use agents to improve from their own experience remains challenging, as supervised fine-tuning relies on fixed teacher-distilled trajectories, while sparse-reward reinforcement learning provides weak supervision for long-horizon interactions. We present DeepSearch-Evolve, a self-distillation framework for web agents built on DeepSearch-World, a deterministic and verifiable environment with reproducible search and page-reading tools. DeepSearch-World contains 420K multi-hop QA tasks constructed from entity-level random walks and supports key agentic cognitive behaviors useful for self-evolving, including progress verification, grounded reflection, and failure recovery. DeepSearch-Evolve iteratively performs trajectory generation, filtering, data mixing, and fine-tuning to train stronger agents. Without distillation from more capable models, DeepSearch-World-9B achieves competitive performance compared with open-source agents, reaching 31.2% on BrowseComp, 61.5% on GAIA, and 93.4% on HotpotQA, showing that verifiable environments enable scalable self-evolution for long-horizon web agents. We will release the environment, 420K training pool, validation set, model, and code to facilitate future research on self-improving deep search agents.

Roy Harris's Integrationist linguistics offers a compelling critique of the referentialist tradition embedded deep at the heart of computational approaches to language, arguing that language is not a code that maps onto a pre-given world but a situated, bipartite activity oriented toward prospective joint action. Yet Integrationism leaves certain explanatory gaps: it does not fully account for the structural mechanism by which signs sustain prospective openness, it undertheorises the continuity between linguistic and non-linguistic semiotic activity, and it offers no detailed account of the structural properties of the accumulated archive of past integrations. This paper argues that Elan Barenholtz's autogenerative theory of language, developed in response to the behaviour of Large Language Models (LLMs), can fill precisely these gaps, enriching Integrationism without undermining any of its core commitments. Specifically, the autogenerative account provides: a structural mechanism for the prospective openness that Harris identifies as central to bipartite communication; a computational correlate for Harris's thesis of semiotic continuity between language and other sign-making activity; and a theory of the archive: what the accumulated residue of past integrations looks like and how new participants draw upon it. The synthesis preserves Harris's ontological primacy of the situated integrative act while adding explanatory content that Integrationism itself does not supply. For practitioners and researchers in natural language processing and large language model design, the argument offers a principled account of what the statistical structure that LLMs so effectively exploit actually is, and of what it cannot, by its nature, provide.

Research on stereotypes in large language models (LLMs) has largely focused on English-speaking contexts, due to the lack of datasets in other languages and the high cost of manual annotation in underrepresented cultures. To address this gap, we introduce a cost-efficient human-LLM collaborative annotation framework and apply it to construct EspanStereo, a Spanish-language stereotype dataset spanning multiple Spanish-speaking countries across Europe and Latin America. EspanStereo captures both well-documented stereotypes from prior literature and culturally specific biases absent from English-centric resources. Using LLMs to generate candidate stereotypes and in-culture annotators to validate them, we demonstrate the framework's effectiveness in identifying nuanced, region-specific biases. Our evaluation of Spanish-supporting LLMs using EspanStereo reveals significant variation in stereotypical behavior across countries, highlighting the need for more culturally grounded assessments. Beyond Spanish, our framework is adaptable to other languages and regions, offering a scalable path toward multilingual stereotype benchmarks. This work broadens the scope of stereotype analysis in LLMs and lays the groundwork for comprehensive cross-cultural bias evaluation.

Preprocessing-based methods for stereotype mitigation, such as pre-/post-training on debiased corpora, are widely used in NLP. While these approaches reduce measurable stereotypes for targeted groups, we find they often induce unintended shifts-side effects, where stereotyping or counter-stereotyping can increase relative to neutral baselines for other demographics, including across unrelated demographic categories. We demonstrate these side effects across two model families (encoder-only and decoder-only), multiple preprocessing strategies (removing stereotypical sentences, removing group mentions, and swapping group references), and both pre- and post-training at different data scales on Wikipedia. Standard benchmarks frequently miss these shifts. Using attention-rollout analysis, we observe that such side effects are not accompanied by large changes in attention flow, complicating mechanistic explanations. We discuss implications for evaluation, provide actionable diagnostics, and argue for side-effect-aware, transparent mitigation practices.

Intent detection is a critical task that bridges human intents and system actions in human-machine interaction systems. However, there still exist challenges for detecting out-of-scope (OOS) intents. (i) The traditional methods view the OOS intent detection as a multi-class classification, then the detection accuracy decreases as the class number of the known intents increases; (ii) LLM-embedding methods require large parameters, that makes them difficult to train and practically deploy. Thus, this work proposes a multi-cluster boundary learning method to detect OOS intents via MiniLM embedding (i.e., all-MiniLM-L6-v2) in an one-class classification workflow. The method learns the boundaries of multi-cluster embeddings generated by MiniLM from the training utterances, and then rejects the out-of-domain utterances as OOS intents. Experiments are conducted on public CLINC150, StackOverflow and Banking77 datasets. The results show that the method achieves the state-of-the-art OOS intent detection performance compared the other baselines. Ablation studies are also conducted and the results show that the used MiniLM can better adapt to the workflow and utterance embedding requirements. The code is available at supplementary materials.

Reinforcement learning (RL) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs). However, widely used critic-free RL methods rely on uniform credit assignment, broadcasting the same advantage to all tokens regardless of their differences. We identify a critical failure mode of this design, which we refer to as Positive-Credit Contamination: low-probability tail tokens that are contextually erroneous receive identical positive credit to plausible ones within the same trajectory, resulting in the indiscriminate reinforcement of flawed reasoning behavior. To mitigate this issue, we propose Tail-Aware Credit calibratiOn (TACO), a method that calibrates uniform credit assignment to suppress undesirable positive updates. TACO first computes a tail-risk score that incorporates the local generation context to assess each token's risk of falling into the unreliable tail, distinguishing unexpected rarity from uncertainty-driven exploration. TACO then uses this score to tune positive credit for risky tokens without removing their gradients entirely, so that recurring useful rare patterns can accumulate reinforcement while incidental noise is progressively dampened. Experimental results across three LLMs and eight benchmarks show that TACO consistently outperforms GRPO-style baselines. Notably, TACO improves training stability, supporting sustained performance gains in long-horizon RL. The source code is available at: https://github.com/xiuyilou/TACO.

We report the empirical reliability of Gemini models as audio judges that score full-duplex agent conversations directly from the raw stereo waveform, tested across three models in the Gemini family: 2.5 Flash, 3.5 Flash, and 3.1 Pro. Our primary evidence base uses Gemini 2.5 Flash as the ground-truth model, validated against three calibrated human raters on 209 stereo sessions, scored on 8 production dimensions: 152 full-duplex conversations across 13 accent-and-condition strata, together with 57 adversarial defect-injected clips. The evidence for Gemini 2.5 Flash is consistent across three tests. (i) On 5 of 8 dimensions the LALM-human Spearman rho departs from the pairwise human-human rho by at most 0.07, and on 7 of 8 dimensions the two quantities 95 percent bootstrap confidence intervals overlap. (ii) The LALM agrees with the three-rater human mean within 1 point on 60 to 92 percent of sessions on 6 of 8 dimensions. (iii) On 45 of 48 (defect, dimension) cells the LALM is as sensitive as humans or better under Newcombe-Wilson 95 percent confidence intervals, though most of these are underpowered nulls rather than demonstrated parity. Rank-ordering ability transfers across the Gemini family: 3.5 Flash improves simple agreement to 8 of 8 dimensions, while 3.1 Pro rates several dimensions markedly lower than humans despite comparable rank correlation. A model swap should be re-validated on calibration specifically, not assumed from rank-correlation alone. We identify four areas where deployment requires care, and we estimate that human rating alone for our current evaluation cadence costs roughly two orders of magnitude more than the equivalent LALM workload. The data presented here provides a defensible empirical basis for deploying the LALM as a substitute or fourth rater on the dimensions where the evidence supports it.

Identifying faithfulness hallucinations in LLM-generated outputs remains challenging due to the scarcity of high-quality annotated data. Recent work relies on advanced LLMs to synthesize training data, including rationales, labels, and hallucinated claims. However, these methods treat the generator as a static component, limiting iterative improvement of the detector. To address this limitation, we introduce Hallucination Self-Play (HSP), a novel framework that enables the detector to bootstrap with an evolved generator. HSP involves two roles initialized from the same base model, a detector that assesses the faithfulness of model outputs, and a generator that produces increasingly hard-to-detect hallucinated responses. Specifically, the detector is first fine-tuned on human-labeled data and then employed as a reward model to train the generator via reinforcement learning from AI feedback (RLAIF). In turn, the evolved generator synthesizes hallucination data to further optimize the detector through rule-based reinforcement learning. Experiments on RAGTruth benchmark and two model families demonstrate that the proposed framework can progressively enhance a small LLM to match or even outperform advanced LLMs without external supervision. Our code is available at https://anonymous.4open.science/r/Hallucination-Self-Play-50B5 .

We introduce a Bloom-aligned framework for measuring educational control in Large Language Models (LLMs): the ability to preserve a task's instructional intent while shifting its cognitive demand toward specified learning objectives. We apply this framework to programming tasks in computer science education to study the gap between solving tasks and adapting them for learners. Using revised Bloom's Taxonomy as an operational scale of cognitive demand, we evaluate two intervention settings: general difficulty control, where models are asked to make tasks harder or easier, and Bloom's control, where models are asked to target higher or lower Bloom's levels. We evaluate a matched Qwen3-Next model pair, comparing Qwen3-Next-80B-A3B-Instruct with Qwen3-Coder-Next across 2,520 tasks from three benchmarks. The framework reveals a robust directional asymmetry: both models reliably increase cognitive demand, but struggle to lower it. We further characterize these outcomes with semantic-delta clustering and layer-wise Fisher's Discriminant Ratio probing. Within this controlled comparison, the general model shows clearer middle-layer separability for both general difficulty and Bloom-control contrasts, whereas the coder model shows weaker separability for general difficulty and a deeper peak for Bloom-control contrasts. These results show that strong execution performance does not automatically entail Bloom-aligned educational control.

Production LLM agents often waste latency and reliability by regenerating code for the same procedural steps on every request. We replace this inference-time coding loop with an agentic tool-making pipeline that compiles repeated SOP steps into validated, versioned tools before deployment. The tool-maker grounds synthesis in the live environment as it collects execution traces, observes backend schemas and values, generates candidate tools, and repairs them against labeled cases. At runtime, the production agent calls these tools directly and falls back to code generation only when needed. We deploy the approach in a Fulfillment Center alarm-triage system, where an agent diagnoses alarms against a 44-node SOP over heterogeneous metric backends. In production, tool calls reduce p50 latency by 42%. On 1,500 historical alarms, they reduce end-to-end error rate by up to 53% by suppressing run-to-run variance in repeated steps. Because tools return compact structured verdicts, they also enable a simpler direct-call architecture, reducing p50 latency by a further 62% in a controlled ablation. Versioned tools also improve auditability and expose specification gaps and upstream data drift. Our results show that self-evolving agents can make industrial LLM systems faster, more reliable, and easier to operate.

Large-Language Models (LLMs) can be prone to flawed and unfaithful reasoning that decoding strategies like Self-Consistency (SC) fail to detect as they evaluate only final-answer agreement while ignoring the logical validity of intermediate steps. This raises three fundamental questions: How can we reliably quantify uncertainty in LLM reasoning? Can semantic, structural, and causal awareness select more faithful reasoning compared to na\"ive majority voting? and How robust is reasoning topology under adversarial conditions? To address these questions, we introduce GRAPHEVAL, a graph-based reasoning framework that re-frames uncertainty quantification (UQ) as a holistic reasoning fidelity problem. We propose a novel UQ metric, Graph Reasoning Coherence Score (GRCS), that quantifies semantic-structural consensus of the reasoning space and captures pathological mode collapse and confident hallucinations. We find that GRCS is the only metric that is consistently negatively correlated with reasoning faithfulness across both more capable and smaller models. Additionally, we introduce Graph Self-Consistency (GSC), a medoid-based decoding strategy that trades nominal accuracy for reasoning fidelity, exposing the degree to which SC is inflated by unfaithful lucky guesses in smaller models, while preserving or improving accuracy in more capable ones. Finally, through adversarial medoid ablation, we demonstrate that the GSC-selected path acts as a "load-bearing path" and forcing models away from it degrades reasoning faithfulness and, in targeted cases, causes drops in accuracy.

This paper proposes an improved structured pruning method for large language models (LLMs) that addresses key challenges in adapting Adaptive Feature Retention (AFR), an unstructured pruning technique, to structured pruning. When applying AFR to structured pruning, three major problems arise: distribution mismatch between heterogeneous pruning scores, loss of sign information indicating optimization direction consistency, and influence of outliers. To address these issues, we propose a unified approach combining power transformation for nonlinear distribution alignment, sign-preserving score aggregation, and percentile-based outlier removal. Experiments on Llama-3-8B, Vicuna-v1.5-13B, and LLaVA-v1.5-13B demonstrate that our method maintains accuracy comparable to unstructured pruning while achieving practical inference speedup through structured pruning.

Large language models (LLMs) are used worldwide, yet disproportionately reflect Western values, limiting their ability to represent diverse value systems. We introduce PLURAL, a large-scale, value-focused preference dataset grounded in the Integrated Values Survey (IVS), a nationally representative survey spanning 92 countries. Using a two-stage generation pipeline, we transform survey responses into synthetic preference triplets that preserve normative value signals while producing realistic scenarios. We release an initial version of PLURAL containing ~500,000 preference triplets representing people in 20 diverse countries. We evaluate PLURAL in three ways: (i) dataset-level validation showing that it preserves both cross-country value differences and within-country diversity from the original survey; (ii) automated evaluation showing that training on PLURAL improves alignment with target countries' cultural profiles, reducing mean absolute error by up to 27.7% relative to strong baselines; and (iii) blind human evaluation with 176 evaluators in India, Brazil, and Japan, who judge PLURAL-aligned responses as more representative of their national values. Together, these results show that PLURAL contains learnable signal for value steering, offering a scalable resource for pluralistic alignment. Dataset: https://huggingface.co/datasets/agdhruv/plural-alignment

Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a forecast. We ask whether internal representations offer a more direct window into both. Working with Eternis-Forecaster 8B on OpenForesight, we train representation-pooling probes on intermediate activations and find they achieve substantially better calibration; a result that also holds for GLM-4.7-Flash and GLM-4.5-Air. We then assess CoT faithfulness through evidence ablation and diversionary injection: removing an influential source in the prompt often changes the model's forecast while leaving the reasoning trace untouched. The same probes function as lie detectors: their activations track behavioral shifts far better than the reasoning trace does, and they also predict the direction of change in 84% of cases, including when the CoT conceals the perturbation's influence. Finally, forced answering reveals that forecasts are largely fixed before reasoning begins: a single pre-reasoning pass recovers the committed answer and confidence, and routing questions by the spread of this pre-set answer distribution saves 30-47% of generated tokens, with no loss of accuracy. Together, these results establish probing internal representations as a practical tool for calibrating, auditing, and triaging language model forecasters and reasoning models more broadly.

Unsupervised constituency parsing aims to accurately induce latent tree structures from raw text alone. Recent neural parameterizations of PCFGs achieve strong performance in both supervised and unsupervised parsing, yet rely on high-capacity black-box networks for rule scoring -- as exemplified by the Neural PCFG family -- leaving rule probabilities without an interpretable mathematical form. In this paper, we propose Holographic Neural PCFG (Hol-PCFG), which recasts PCFG rule scoring as algebraic relation modeling among grammar-symbol embeddings. Hol-PCFG adapts Holographic Embeddings (Nickel et al., 2016), which scores knowledge-graph triples via circular correlation, to the left-child, right-child, and lexical-emission relations over torus-constrained embeddings, giving every rule probability a closed form that carries the intrinsic structure of grammar rules by construction. Hol-PCFG achieves state-of-the-art parsing performance in six languages while cutting rule-scoring parameters by 99.94% relative to the baseline model and training more stably. Additionally, we demonstrate that Hol-PCFG can parse Japanese directly from characters without any morphological segmentation, retaining nearly the same morpheme-level performance.

Online ads are essential to all businesses and ad headlines are one of their core creative component. Existing methods can generate headlines automatically and also optimize their click-through-rate (CTR) and quality. However, evolving ad formats and changing creative requirements make it difficult to generate optimized & customized headlines. We propose a novel method that uses prefix control tokens along with BART fine-tuning. It yields the highest CTR and also allows users to control the length of generated headlines for use across different ad formats. The method is also flexible and can easily be adapted to other architectures, creative requirements and optimization criteria. Our experiments demonstrate a 25.82% increment in Rouge-L and a 5.82% increment in estimated CTR over previously published strong ad headline generation baseline.

Aspect Sentiment Triplet Extraction (ASTE) requires jointly identifying (aspect, opinion, sentiment) triples from a given review sentence. While large language models (LLMs) achieve strong zero-shot performance on many NLP benchmarks, their effectiveness on ASTE remains limited, as single-pass generation forces the model to determine span boundaries, opinion grouping, and sentiment polarity in a single decoding step. Common remedies, such as few-shot in-context learning and chain-of-thought prompting, offer only marginal improvements and rely heavily on either in-domain demonstrations sampled from labeled training data or carefully engineered reasoning prompts, neither of which is broadly available in zero-shot deployment. Inspired by the classical agent paradigm, we propose MASTE, a multi-agent pipeline for zero-shot Aspect Sentiment Triplet Extraction. MASTE decomposes ASTE into four sequential stages, where specialized agents handle different compositional subtasks with explicit conditioning on prior outputs. This design enables entirely training-free zero-shot ASTE and generalizes across different backbones and datasets. Extensive experiments on four ASTE benchmarks show that MASTE substantially outperforms zero-shot and chain-of-thought LLM baselines under the same backbone, narrowing the gap to fully supervised methods without using any labeled triplets. Code is available at https://github.com/Hankerlove/MASTE.

Contextual biasing seeks to integrate external knowledge into automatic speech recognition (ASR) systems to accurately recognize domain-specific entities. In this paper, we propose COALA (Contextualized ASR Leveraging Biasing Scoring), a robust framework designed to enhance speech-augmented language models (SLMs) in complex multi-entity scenarios. Considering the inherent context-window limitations of SLMs, identifying relevant target entities from a large-scale biasing list is crucial for effective recognition. To this end, COALA maps SLM latent representations into a specialized discriminative space to quantify the matching intensity between audio segments and candidate entities. Furthermore, we address the training collapse in prior study when handling multi-target utterances-where multiple rare words co-occur. Experimental results on the LibriSpeech benchmark demonstrate that COALA consistently achieves superior contextual biasing performance across various biasing list scales.

We present the results of HIPE-OCRepair-2026, an ICDAR competition on LLM-assisted OCR post-correction of historical documents. OCR post-correction remains a long-standing challenge in digital heritage: large-scale collections of digitized documents are affected by legacy OCR errors, while re-digitization at scale remains impractical. Large language models (LLMs) offers a major opportunity to revisit this challenge, yet their effectiveness across languages, document types, and noise conditions - and their tendency to hallucinate - remains insufficiently understood. HIPE-OCRepair-2026 pursues two objectives: (i) to evaluate the capabilities of modern OCR post-correction systems, and (ii) to provide a reproducible evaluation framework anchored in the HIPE-OCRepair-2026 dataset, a harmonized multilingual resource consolidating existing and newly curated historical datasets. Participants were tasked with correcting noisy OCR transcripts from historical newspapers and printed works in English, French, and German (17th-20th century), working at the level of coherent transcription units (paragraphs or articles) without access to source images. The evaluation adopts a retrieval-oriented rather than diplomatic scoring approach, reflecting the practical use case of search and access over digitized collections. Four teams submitted systems ranging from zero-shot prompting to continued pre-training and fine-tuning, offering insights into the merits of different adaptation strategies. Results show that modern LLM-assisted systems can significantly improve OCR quality, but performance varies across datasets, languages, and noise levels. Over-correction on low-noise inputs emerges as a recurring challenge, highlighting the importance of evaluation beyond character error reduction. The dataset, scorer, and evaluation pipeline are publicly released to support future research.

On the recent EyeBench benchmark, predicting reading comprehension from eye movements exposes a stark gap: text-aware models using pretrained language models reach 56--63% AUROC, while gaze-only models operate at chance. We ask how far a gaze-only model can be pushed by lightweight, language-model-free conditioning. Building on the EyeBench AhnCNN baseline, LEXIC-Base, we propose two mechanisms to inject three precomputed word-level difficulty signals, GPT-2 surprisal, word frequency, and word length, into the per-fixation input: direct concatenation, LEXIC-Concat, and a residual mechanism, LEXIC-Res, where a small head predicts typical-reader gaze response and the encoder is conditioned on the deviation. On the OneStop reading comprehension task, with K=5 seed-ensemble training across ten folds, both mechanisms produce statistically consistent AUROC gains on Unseen Text, +1.8 to +2.2 percentage points, Wilcoxon p <= 0.065. LEXIC-Concat additionally lifts Unseen Reader by +2.9 percentage points, p = 0.010. We trace an architectural boundary in LEXIC-Res on Unseen Reader, +1.8 percentage points, p = 0.19, to the prediction head being calibrated to training readers, transferring imperfectly to out-of-distribution readers.

Text-to-SQL is a fundamental task in natural language processing that enables users to interact with structured databases using natural language. While large language models (LLMs) have demonstrated remarkable performance on this task, their substantial computational requirements hinder deployment in resource-constrained settings. In this paper, we introduce SQuaD-SQL (Small-Qualified and Distilled for SQL), a novel approach that empowers small language models (SLMs) to approach the performance of LLMs on the Text-to-SQL task while significantly improving efficiency through knowledge distillation and synthetic data generation. Our method comprises three key components: (1) LLM-based synthetic data generation, where structured knowledge is extracted from LLMs via carefully designed prompting strategies; (2) parameter-efficient fine-tuning, enabling full model training on a single consumer-grade GPU; and (3) domain-adaptive fine-tuning, where domain-specific synthetic data further enhances performance in targeted domains. Experiments on the WikiSQL dataset demonstrate that SQuaD-SQL achieves an execution accuracy of 86.9% on the test set, approaching the performance of LLMs while offering faster inference and lower memory usage. These results suggest that, with proper training strategies, SLMs can serve as practical and efficient alternatives for Text-to-SQL applications in resource-limited environments.

Scaling Large Language Models (LLMs) has been driven mainly by enlarging the Transformer backbone, but for an already-strong model this requires another round of costly pretraining. We study whether an existing backbone can keep improving by allocating more computation to each token while leaving the Transformer backbone fixed. Depth-recurrent (looped) Transformers pursue this goal but are hard to scale, because looped computation does not fit naturally with the pipeline parallelism used to train the largest models. We add computation along the sequence-length dimension, where the extra computation is simply a longer input and stays compatible with standard large-model training. We propose Hidden Decoding, a sequence-length scaling method applied during continued pretraining (CPT). It expands each token into n streams with independent embedding tables and keeps the intermediate streams' key-value cache as context, so each token performs more internal computation without adding or widening Transformer layers. To keep this affordable at scale, we introduce Stream-Factorized Attention, in which most layers attend only within each stream and only a few layers mix across streams, reducing the attention cost from quadratic to roughly linear in n. Experiments support two scaling results. At frontier scale, we train WeLM-HD4-80B and WeLM-HD4-617B at n=4 and improve their matched non-HD baselines, making Hidden Decoding the first demonstrated sequence-length scaling method at the 100B+ MoE scale. Across expansion factors, the gains grow as n increases, showing that sequence-length expansion is a practical fixed-backbone scaling path for frontier-scale LLMs.

This paper describes our self-designed system for Task 1 of the MLC-SLM 2026 Challenge for multilingual two-speaker conversational speech. The system combines a modular speaker diarization front end with a challenge-adapted Qwen3-ASR-1.7B recognizer. The diarization front end performs voice activity detection, subsegment generation, CAMPPlus speaker embedding extraction, two-speaker spectral clustering, and RTTM-based audio segmentation. The resulting speaker-attributed segments are grouped by language or region and decoded by the adapted ASR model. For ASR adaptation, we first perform supervised full fine-tuning on the official training data, then apply LoRA fine-tuning with synthetic speech generated by a three-pipeline TTS-based synthetic speech augmentation framework, and finally refine the model using GRPO reinforcement learning with rewards based on WER/CER and penalties for hallucination, repetition, and length deviation. On the official development set, the full system achieves an average tcpMER of 23.70, reducing the error rate by 6.83 absolute points relative to the released Qwen-ASR-1.7B performance. On the final evaluation set, the system achieves an average tcpMER of 17.97. Ablation results show that supervised fine-tuning provides the largest gain, while synthetic-speech LoRA adaptation and reinforcement learning further improve robustness.

Best-of-$N$ (BoN) inference improves content consistency in zero-shot text-to-speech by selecting from $N$ candidates with an automatic speech recognition (ASR) verifier. We identify an underexplored evaluation confound: a verifier's apparent quality depends strongly on which ASR family judges it. On LibriSpeech-PC test-clean~\citep{librispeechpc} with F5-TTS~\citep{f5tts}, verifier rankings reverse across Whisper, wav2vec~2.0, and HuBERT evaluators, and same-family verifier-evaluator pairs recover 2-3$\times$ more oracle headroom than cross-family pairs despite near-identical representations (linear CKA $0.978$) -- a pattern consistent with identity- or lineage-level coupling rather than representational overlap. We propose two \textbf{cross-family rank ensembles} (rank-averaging and conjunctive max-rank) that attain the lowest mean WER across three independent evaluators -- $1.61\%$ at $N{=}10$ ($-12\%$ relative to F5-TTS) -- with no measurable degradation under automatic SIM-o/UTMOS metrics; the best single verifier drives WER from $2.06\%$ to $1.72\%$ ($-16.5\%$) under the official F5-TTS evaluator. We recommend cross-evaluator triangulation as default reporting practice.

Financial markets are noisy, non-stationary, and high-dimensional, making it difficult to discover predictive and robust trading signals. Alpha discovery has evolved from manual factor design to machine learning, evolutionary search, and recent LLM-based frameworks, improving the efficiency of factor generation, search, and evaluation. However, existing methods still mostly automate isolated steps, rather than functioning as end-to-end quant researchers that can absorb external knowledge, close the hypothesis-to-code validation loop, and learn from accumulated discovery feedback. To fill this gap, we introduce XAlpha, a memory-driven AI Quant Researcher for continuous hypothesis-to-code alpha discovery. XAlpha maintains a multi-source research memory system that integrates report-grounded financial knowledge with discovery feedback from prior generations and research cycles. Guided by this memory system, a Macro Brain plans research themes and selects suitable Archetypes; a Micro Brain transforms the planned hypothesis pool into executable factor code and verifies ex-ante tri-alignment among the hypothesis idea, code logic, and financial plausibility; and a Cross Brain consolidates empirical outcomes into generation-level feedback, cycle-level summaries, and archetype-level research cues for future exploration. In this way, XAlpha turns alpha mining from isolated factor generation into a closed-loop research process that continuously reads, hypothesizes, implements, validates, reflects, and evolves. Experiments on CSI300 show that XAlpha achieves stronger overall alpha discovery performance than representative baselines.

State-of-the-art code models achieve impressive performance, yet the extent to which they internally encode type information remains poorly understood. We probe the residual streams of pretrained code models for internal type representations using a parallel dataset of Java and Python code examples. Our results show that cross-lingual type representations emerge even from untyped code. Moreover, we test whether hidden states linearly encode the result type implied by typed function application by training probes on one language to infer argument and result types in the other. Finally, we find that this structure is partly robust to lexical perturbations and cross-language syntactic variations. To the best of our knowledge, prior work on interpretability of code models has not directly targeted formal type semantics or cross-lingual type representations. We release our code and datasets.

Form 8-K filings are the primary channel through which U.S. public companies disclose material events, but the SEC item codes attached to them are coarse: a single item spans routine administrative changes and chief executive departures, and many of the most market-moving disclosures fall into a catch-all item. Large language models make fine-grained labelling feasible at corpus scale, but only if the labels can be traced to the source text and shown to be reliable. We present a two-stage system that tags 8-K disclosures against a three-tier taxonomy of 119 event types. The first stage constrains output to valid taxonomy entries and anchors every tag to a verbatim quote via fuzzy n-gram validation; the second re-grades each cited quote against the category definition to produce a quality score. Applying the system to 292,984 filings from 2022 to 2026 yields 601,088 grounded event tags, which we release. Over 5,125 stratified tags, an LLM judge finds precision rises monotonically with the quality score, from 12% to 96%, while unsupported tags fall from 8% to near zero. Ablation shows the score is calibrated only when assigned in a dedicated second pass. An event study on unsigned abnormal returns confirms, without any language model, that the taxonomy separates economically distinct events sharing an item code.

Vietnam's ethnic minority languages are almost absent from the field of Natural Language Processing (NLP), and the challenge goes beyond data scarcity: Cham, Khmer, and Tay-Nung differ sharply in script, Vietnamese contact, and standardization, conditions under which standard multilingual adaptation can learn the wrong signals. We introduce CKTN, the first corpus and benchmark for these languages (44,367 documents, 24M subword tokens), spanning continued pretraining, category classification, and summary-document retrieval. We show that existing multilingual encoders severely fragment these languages, and that common adaptation metrics can mislead: models may lower language-modeling loss or excel at lexical-overlap retrieval while still failing at semantic generalization across documents. We address this with a script-aware adaptation recipe - vocabulary augmentation combined with calibrated replaced-token pretraining - that prevents the discriminator from exploiting trivial script mismatches. The result is an encoder with substantially less fragmentation and the strongest classification performance among evaluated models, exposing the limits of lexical-overlap retrieval as an evaluation signal.

Personality recognition has traditionally been constrained by theory-dependent formulations, where models are trained to fit predefined psychological taxonomies rather than uncovering shared underlying behavioral structure. This limits generalization, as personality itself is better understood as theory-invariant, while existing annotations reflect only partial and sometimes inconsistent views of the same latent traits. In this work, we introduce JAM ((J)udge for (A)daptive (M)etric-Alignment), a theory-agnostic framework that shifts learning from adapting to predefined personality theories toward discovering unified latent pseudo-facets that capture shared psychological structure. Rather than constraining the model to any personality taxonomy during training or inference, the framework learns generalizable psychological representations and can infer an individual's latent psychological profile directly from the textual samples, without requiring theory-specific labels. JAM achieves this through an Attention-Pooled Graph Prototypical Network that learns structured representations via clustering in embedding space, together with a Cross-Theory Harmonization (CTH) approach that integrates (i) Human-Guided Linkage and (ii) Machine-Induced Consensus to unify heterogeneous datasets without relying on predefined labels. To further improve robustness and data quality, we incorporate an LLM-as-a-Judge mechanism operating in two configurations, (i) LLM-before-the-loop and (ii) LLM-in-the-loop which identifies ambiguous samples to guide adaptive metric learning. Experiments show that JAM improves cross-framework generalization and performance, establishing a strong step toward theory-agnostic personality inference and supporting low-resource personality theories. The related code repository, model weights, and artifacts are available at https://research.jingjietan.com/JAM

Large language models process prompts by propagating activations through dozens of layers before generating a response. We ask whether the task-relevant information contained in an instruction prompt can be compressed into a single activation vector and re-injected into the model, replacing the original token sequence? We show this is achievable using a learned weighted sum of activations extracted at an intermediate layer and injected at an early layer of the target LLM. The compressed vector preserves task-relevant information, incurring an accuracy drop of under $2\%$ relative to full prompt processing. Beyond its practical implications, including reducing per-query computation for fixed instruction prompts without reprocessing the original token sequence, our analysis reveals structure in the activation space of LLMs: (i) mid-layer representations transfer meaningfully to early layers, suggesting a degree of cross-layer compatibility in how information is encoded; (ii) a single activation vector encodes a quantifiable and recoverable amount of semantic information; (iii) a weighted sum of activations is a robust representation compressor.

LLM-based ASR adapted to regulated domains such as banking is bottlenecked by privacy: real speech is costly and legally constrained to collect, making synthetic text-to-speech (TTS) an attractive substitute. Yet synthetic speech stays acoustically mismatched with real recordings, and work on this gap has stayed within supervised fine-tuning (SFT). We instead turn to reinforcement learning, and show that Group Relative Policy Optimization (GRPO) extracts far more from the same synthetic speech than SFT. Synthetic-only adaptation of the model with GRPO, a critic-free method rewarding low-WER hypotheses, reduces WER by 40\% relative to SFT (36.71\%$\to$22.09\%), and an SFT-then-GRPO combination pushes this further to 45\%. We trace the gain to behavior rather than representation: GRPO reduces insertion errors by improving stopping calibration and speech-to-text alignment by better anchoring attention to audio, leaving early-layer representations intact. When synthetic speech is the main resource, reinforcement learning should be preferred over supervised fine-tuning.

A Ladder Logic Bomb (LLB) is malicious control logic in a Programmable Logic Controller (PLC) program that lies dormant until a trigger activates a payload to manipulate actuators, forge sensor readings, or deny operator control. We observe that real malicious logic hides inside function-block bodies, which existing ladder-diagram verifiers drop from their intermediate representation (IR), making bombs invisible to provers. We present ESBMC-LLB, which uses ESBMC-PLC+ as its verification engine and adds a modeling layer that exposes function-block logic and recasts bomb detection as a formal verification problem: a scan-watchdog exposes non-termination payloads, and output wiring exposes actuator-forgery payloads as safety violations. k-induction gives an unbounded proof of bomb-absence across all scans, and the bounded model checker returns a counterexample that is the trigger - guarantees that signature, anomaly, and CFG-triage detectors lack. On the public Iacobelli 2024 dataset, ESBMC-LLB detects all 30 bombs and recovers every trigger; it also detects adaptive triggers (computed, opaque-arithmetic, multi-scan) that evade CFG-triage. We also report the first semantic model-checker evaluation on PLC-Defuser's SWaT corpus: our analog extension makes the full corpus parseable; on v1.0.0, it detects 149/150 bombs (99%) with zero false positives, recovering each trigger; on a later version with nonlinear non-termination bombs, detection drops to 49% as the SMT solver times out. We conclude that semantic model checking and CFG-triage are complementary - the former gives unbounded proofs, adaptive-trigger robustness, and handles Boolean/integer and linear analog logic; the latter leads to nonlinear analog non-termination, and we delineate where each wins.

A model should refuse two different things: answers it would get wrong, and questions it should not answer at all, such as unanswerable ones or ones resting on a false premise. The usual recipe thresholds a single confidence score, which cannot tell these apart. Across five instruction-tuned models from three families (2B to 14B), we find they are separate axes. Ordinary answer-confidence tracks whether an answer is right but is nearly blind to whether the question is answerable; a linear probe on hidden states does the reverse. The blind spot does not shrink with scale. It is worst on naturally occurring false-premise questions (CREPE). There, answer-confidence, P(IK), P(True), and even asking the model outright whether a premise is false all stay near chance, while a hidden-state probe reaches 0.69 to 0.77 AUROC: the model represents a problem it will not report. This turns out to be fixable. Instructing a model to check premises backfires, because it then disputes sound and false premises alike (57% false challenges), unable to tell them apart; routing the same instruction with the probe roughly triples challenge precision. We turn the two axes into a calibrated policy that answers only when an answerability score and a correctness score each clear a separately certifies behave differently: the unanswerable-answer rate is controllable at every scale, while the wrong-answer rate is capped by model accuracy, so the guarantee tightens as threshold policy certifies both budgets at 0.75 coverage of correct answers, against 0.31 for a single threshold; at 14B it is the only policy that certifies at all.

We present a Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoder (SAE) for extracting cross-seed universal features from independently trained BERT models. Cross-seed feature universality is a fundamental challenge in mechanistic interpretability: because dictionary learning is non-convex, independently trained networks learn misaligned feature spaces, so apparently identical features may differ by random initialization. We address this by computing an orthogonal Procrustes rotation between seeds' activation spaces before joint SAE training, combining Top-K sparsity, end-to-end downstream optimization, and an auxiliary dead-feature revival loss based on previous SAE literature. Evaluating on five independent seed pairs (ten BERT models) across three benchmark datasets (SST-2, Stanford Politeness, TweetEval Emotion), our full pipeline produces more universal features (Pearson r $\geq$ 0.70 across seeds) than post-hoc alignment baselines on all three datasets. A minimal qualitative analysis confirms that high-universality features encode interpretable sociolinguistic patterns.

An LLM-as-judge score can move even when the candidate responses stay fixed, simply because the evaluator has changed. We treat this evaluator-replacement ambiguity as a measurement-validity problem. Across four judgment datasets, we compare two upgrade paths available in practice: scaling Qwen3 dense judges from 1.7B to 32B parameters and moving across MiniMax M2-M2.7 released APIs. The main pattern is that judge upgrades are not interchangeable: only Qwen3 1.7B to 4B gives a robust adjacent gain, while MiniMax adjacent releases do not. Stronger judges reduce but do not remove position and verbosity bias. Repeated-sample juries add little when errors are correlated. Structured debate can move decisions substantially, but without parser and fallback logs those shifts cannot be attributed to deliberation. We argue that LLM-as-judge reports should include dataset slices, bias probes, error-dependence estimates, and protocol audit trails.

Sparsely-activated Mixture-of-Experts (MoE) language models achieve remarkable inference efficiency by activating only a small fraction of parameters per token, yet their full expert banks reside in memory at all times, creating a prohibitive deployment bottleneck. Existing structured pruning methods, largely designed for dense transformers, assess expert importance using locally derived heuristics that are blind to the interdependent nature of MoE routing. We introduce MAESTRO (Markov-chain Approximated Expert Sparsification via Transition-based ROuting), a structured pruning framework designed for MoE architectures that models autoregressive expert activation trajectories as Ergodic Markov chains whose stationary distributions encode cross-layer dependencies, yielding a globally aware importance heuristic. Evaluated across five diverse domains including Safety, Bias, and Ethics, MAESTRO outperforms state-of-the-art baselines by up to 10.61% in average performance retention under a strict 50% compression regime, while exhibiting substantially lower cross-task variance, indicating that global, routing-congruent pruning produces models that generalize more consistently across heterogeneous tasks.

Speculative decoding accelerates LLM inference by drafting several tokens and verifying them in parallel. Block-diffusion drafters such as DFlash produce a draft block in one pass but model only per-position marginals; best-first tree methods such as DDTree expand candidate trees from those marginals. The released Domino drafter adds a GRU-based causal correction that makes each draft token's distribution path-dependent, a structure DDTree's factorized formulation cannot represent. We introduce DominoTree, a training-free best-first draft tree scored by Domino's conditional, non-factorized correction along each root-to-node path, made practical by restricting the per-node correction to a candidate top-M. On Qwen3-4B across eight benchmarks, DominoTree reaches up to 6.6x speedup over autoregressive decoding and the highest mean accept length of any evaluated method, up to 10.7 tokens per round, at every temperature we test. DominoTree constructs its tree with a GPU-native, CUDA-graph builder that is bit-identical to a reference Python implementation, so acceptance is unchanged, while keeping per-round tree construction cheap. With this builder as default, DominoTree wins throughput over the released Domino decoder at every temperature, 9-10% overall on Qwen3-4B and up to +22% on Alpaca, and over DDTree/CaDDTree at every temperature we test. On Qwen3- 8B, DominoTree keeps the highest accepted length at every temperature and adds a decisive throughput win at T=0, +24% over DDTree; at higher temperature that edge over DDTree/CaDDTree narrows to a tie and a small loss, while its Overall aggregate wins over DFlash and Domino persist.

As available training data approaches its physical limit, gains from Scaling Laws have begun to diminish. Consequently, improving Large Language Models (LLMs) now depends less on data expansion and more on higher-quality data utilization. However, in the context of large-scale corpora, existing refinement methodologies face significant limitations in quality, efficiency, and reliability: Rule-based approaches are constrained by fixed heuristics and struggle with instance-level variations; LLM-based approaches improve quality but fail to meet the efficiency and reliability requirements of large-scale data processing. To address these challenges, we propose UltraX, a function-calling refinement framework for large-scale pre-training data that completes the editing function space by introducing insertion in addition to deletion and modification, enabling fine-grained instance-level editing. Specifically, UltraX builds a reliable program-supervision generation pipeline. In this pipeline, dataset-adaptive prompt optimization first guides an expert LLM to produce high-quality end-to-end refined texts, and Line Alignment Mapping and Dynamic Context Replacement then convert original-refined text pairs into structured program supervision. Meanwhile, UltraX improves supervision quality and stabilizes the training distribution with low-confidence example filtering and ratio-controlled sampling by operation combination. During inference and execution, it normalizes and validates model outputs through sliding-window prediction, global operation aggregation, and systematic post-processing, improving the stability and reliability of large-scale execution. Experiments show that UltraX achieves the highest average performance across all corpora and also matches or surpasses baselines with fewer training tokens, demonstrating stronger data efficiency and refinement reliability.

Large language model (LLM)-based web search agents are transforming information seeking from simple factoid question answering into complex, deep-and-wide search and research-oriented tasks. A single ReAct-style agent is constrained by one long trajectory and limited context, making it difficult to handle depth and coverage simultaneously. Existing multi-agent systems improve search coverage through parallel execution and aggregation, but still exhibit clear limitations in recursive depth, collaboration adaptability, and evidence-grounded expansion. We propose WebSwarm, a progressive recursive delegation framework that jointly constructs task decomposition, recursive expansion, and agent collaboration during inference. WebSwarm dynamically instantiates agentic search nodes, each coupling a local objective with a search mode that specifies how the node should organize search and collaboration. Each node can either solve its objective itself or further delegate child nodes; after solving, it returns evidence and results upward, enabling parent nodes to further expand, revise, or aggregate the search process. To guide this process, WebSwarm first probes how task-relevant information is organized on the web to ground subsequent node expansion, and reuses process-level experience across homogeneous sibling nodes. Experiments on BrowseComp-Plus, WideSearch, DeepWideSearch, and GISA show that WebSwarm consistently outperforms single-agent and multi-agent baselines on deep, wide, and interleaved deep-and-wide tasks. Further analyses of ablation, task difficulty, web tool efficiency, and model generalization explain WebSwarm's effectiveness and provide insights for multi-agent search systems.

Reinforcement learning increasingly relies on an LLM judge to score each rubric criterion, and that judge acts as the reward model during training. Before such a signal can be trusted, we need to know how capable the judge must be and how biased it is. We study this calibration question for citation quality in deep-research systems, where a search-grounded LLM must support each claim it writes with a cited source. Citation quality is a structured rubric task in which each attribution-citation pair is judged along two dimensions that require an LLM, source relevance and factual support. On an adversarial long-form benchmark, we score 8 off-the-shelf LLM judges from 3 model families against gold labels over 1,248 rubric decisions, all of which were human-reviewed and 378 of which were hard cases adjudicated from judge disagreements. Cheaper judges remain competitive across both dimensions, with GPT-5-mini attaining the strongest source-relevance pass-class F1 at 0.908 ($\kappa$=0.636), while on factual support the judges are statistically indistinguishable (overlapping confidence intervals), so no single model dominates. At comparable F1, the judges still differ substantially in pass-rate drift, false positive rate, and false negative rate. Scalar F1 obscures this directional bias, yet it is exactly what a downstream reinforcement learning loop would reinforce. Calibrating the judge is therefore a prerequisite for using citation rubrics as reward signals, and our results show that this calibration does not require the most expensive available model.

A national language model offers a linguistic community its own instrument for measuring what its citizens say and value. Portugal's AMALIA, a publicly funded 9B-parameter model for European Portuguese, appears competitive on agreement alone: asked to code the moral foundation of authority, it agrees with trained human coders to within six F1 points of open models eight to thirteen times its size. Yet agreement is reliability, not validity. For theoretical constructs that must be inferred rather than read from surface features, the question is whether the model follows the construct's theory or reaches the right code by correlated shortcuts. We test this with the recovery gap: the loss in performance when a holistic prompt is decomposed into the codebook's atomic clauses and recombined by the theory's explicit rule. If calibration closes that gap, some portability should survive across models and languages; where it does not, the construct-model instrument is the likely locus of failure. We ask whether a calibrated English instrument transfers to AMALIA-9B and to European Portuguese. For one construct and one corpus, it does not. Decomposition recovers only about half of AMALIA's holistic performance, and error analysis suggests reliance on surface correlates, especially moral outrage near authority figures. An open multilingual LLM closes the gap on the same Portuguese corpus under the same instructions, pointing away from the corpus as the main explanation. AMALIA can still screen and pre-code at scale, but it cannot yet measure this construct well enough to stand alone. The study is a single counterexample, not a verdict on national models; it argues that sovereign-LLM benchmark batteries should test not only agreement with human coders, but the evidential route by which that agreement is warranted.

The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operating everyday tools and assisting users in real-world environments. However, existing benchmarks struggle to evaluate such agents effectively, as they often rely on sandboxed environments and single-turn evaluation paradigms. Moreover, their scenario-based task taxonomies mix multiple model capabilities within the same task category, making it difficult to identify the root causes of agent failures. To address these limitations, we introduce UniClawBench, the first capability-driven benchmark designed to evaluate proactive agents in dynamic, real-world settings. UniClawBench is built around five foundational model capabilities: Skill Usage, Exploration, Long-Context Reasoning, Multimodal Understanding, and Cross-Platform Coordination. Based on these capabilities, we design 400 bilingual real-world tasks. Unlike previous benchmarks that rely on static, pre-recorded answers, our benchmark evaluates agents in live Docker containers using fine-grained, step-by-step completion checkpoints. Furthermore, we design a closed-loop evaluation strategy comprising an executor agent, a hidden supervisor agent, and a user agent to simulate realistic multi-turn human feedback without leaking grading criteria. To disentangle base model capabilities from framework-level design choices, we evaluate state-of-the-art models under multiple agent frameworks. Through comprehensive comparisons across both models and frameworks, we show how base model capabilities and agent framework designs jointly shape performance in real-world environments. To facilitate future research, we make our benchmark and code publicly available at https://github.com/HKU-MMLab/UniClawBench.