Search research

Physical human-robot interaction (pHRI) in real-world settings exposes operators to fluctuating environmental conditions during contact-rich tasks. Traditional task-centric evaluations overlook the physiological burdens imposed by these stressors. Therefore, we conducted a multimodal empirical study involving contact-rich tracing tasks under 18 distinct combinations of temperature, acoustic noise, and illuminance. Synchronously, we recorded electrodermal activity (EDA), surface electromyography (sEMG), eye-tracking data, and subjective environmental comfort ratings. Evaluating these physiological signals alongside execution data revealed hidden physiological costs not captured by objective performance. The results revealed that task performance remained stable across all environmental conditions. Autonomic workload, indexed by tonic skin conductance level (SCL), increased with temperature, while physical and cognitive workload were unaffected. Perceived environmental comfort showed no significant association with tracing error or completion time. These findings reveal a compensatory mechanism where operators maintain consistent performance by increasing their physiological effort to suppress thermal discomfort. Such insight motivates the development of physiology-aware control architectures that leverage real-time physiological metrics to reduce operator workload in unstructured environments.

LLM agents are increasingly built not as single model calls, but as scaffolded systems that combine reasoning, memory, reflection, action execution, and learning. While such scaffolds often improve performance, they are often embedded in tightly coupled pipelines, making it difficult to isolate component contributions, compare alternative designs, or understand how module interactions shape agent behavior. We introduce AgentSpec, a modular specification framework that represents embodied agents as typed compositions of reusable policy components with standardized interfaces. AgentSpec standardizes the interfaces among perception, memory, reasoning, reflection, action, and optional learning, enabling components to be swapped and recombined under controlled conditions. We instantiate this framework across DeliveryBench, ALFRED, MiniGrid, and RoboTHOR, and analyze reasoning, memory, reflection, and reinforcement-learning modules across model backbones. Our results show that agent performance is governed by scaffold compatibility and interaction effects rather than isolated module strength. In particular, structured multi-granularity memory improves long-horizon state tracking, reasoning and memory interact non-uniformly across environments, reflection trades off correction and cost, and RL-trained policies compose best when optimized with deployment-time scaffold structure. AgentSpec provides a controlled foundation for studying, comparing, and designing composable LLM agents. Our code, baselines and interactive playground are publicly available at https://agentspec-embodied.github.io.

Open diffusion language models are marketed as parallel, non-autoregressive decoders, yet the order in which a shipped checkpoint actually commits its tokens is almost never measured. We instrument DiffusionGemma 26B, a masked discrete-diffusion mixture-of-experts model built on Gemma 4, hooking its sampler's accept step to record which canvas positions commit, when, and at what confidence. Across a 686-prompt, six-regime probe suite we find that its decoding is neither parallel nor block-autoregressive: it follows a partial left-to-right commit bias whose apparent strength depends almost entirely on the granularity at which you look. Order is weak token by token and strengthens smoothly as the analysis is coarsened, so the model's "block size" turns out to be an artifact of the measuring ruler rather than the architecture. The model commits in large simultaneous batches, leaving much of the within-batch order genuinely undefined rather than merely unobserved. The behaviour is regime-dependent: structured JSON is committed in essentially arbitrary order, and a position's commit confidence tracks correctness on mathematical reasoning but carries no signal on factual recall. Commitment is aggressive, finishing in a short late burst well inside the step budget, while task accuracy matches the model's autoregressive Gemma-4 sibling. Beyond these findings, our central contribution is methodological: measuring decoding order honestly demands handling trailing-EOS padding, within-regime confounding, commit non-monotonicity, block-size sensitivity, and large commit-batch ties, each of which can otherwise manufacture a decoding-order result that is not really there.

Safe physical human--robot interaction on floating-base robots requires interaction regulation under changing contact constraints. We develop a contact-consistent normalization in which the residual end-effector channel is represented as a linear double integrator in acceleration coordinates. Both discrete prediction matrices are independent of configuration and support mode; posture and contact enter only through task-inertia force recovery and constraints. The controller combines a constant-Hessian receding-horizon QP, an acceleration-disturbance observer, and a priority-consistent realization. Classical operational-space impedance is shown to be the unconstrained infinite-horizon limit. MuJoCo experiments on a 17-DOF biped and a Menagerie-derived Unitree G1 model evaluate sustained forces, transmitted shocks, and scheduled contact-model changes. The observer sustains near-offset-free tracking across a genuine contact-set switch and a scheduled support-mode transition, while disturbance estimation---not contact consistency alone---is the dominant source of fixed-stance accuracy; covariance inflation gives only scenario-dependent transient benefit.

Dexterous manipulation is fundamentally a problem of interaction dynamics: the hand must track precise finger trajectories, regulate the contact force exchanged with grasped objects, respect actuation and safety limits, and remain predictable when contact persists -- objectives in tension for any fixed-gain controller. A sustained contact torque $τ_{\text{ext}}$ through a joint stiffness $K_d$ produces the structural bias $e_\infty=τ_{\text{ext}}/K_d$, so stiffening for accuracy sacrifices contact safety while softening yields by design. We make these interaction dynamics explicit and actuator-agnostic through a constant-$A_d$ double-integrator backbone, instantiating the offset-free architecture established for physical human-robot interaction (pHRI) and preserving its modeling assumptions on the reduced residual dynamics. An algebraic feedforward reduces the tendon transmission -- hydraulic, cable, pneumatic, twisted-string, or series-elastic -- to a constant-coefficient double integrator, so the QP cost inverse is precomputed offline and a 10-step receding-horizon QP runs at 500,Hz under contact-force (ISO/TS 15066), actuation, and jerk constraints. An encoder-only augmented-Kalman disturbance state drives steady-state error to zero under constant contact loads in the nominal detectable case. In simulation, a hydraulically actuated finger -- the worked example, adding pressure and cavitation constraints -- attains 0.6,mrad RMS, 0.1,mrad steady-state, and 7.3,mrad peak deflection under 1.5,Nm contact: 153$\times$, 1500$\times$, and 21$\times$ better than classical impedance. The realized first-move stiffness (18$\to$323,Nm/rad with update rate) is independently verified, and the architecture scales to a 16-DOF LEAP Hand MuJoCo model, recovering from 2.5,N grasp disturbances within 0.7,s.

LLM agent systems increasingly run as long-lived autonomous runtimes: scheduling jobs, calling tools, maintaining memory, and pushing results to humans. We present a longitudinal study of silent failures in one such system: a personal-assistant agent runtime in continuous production since March 2026, with roughly 40 scheduled jobs, 8 LLM providers, a tool-governance proxy, and a knowledge-base memory plane, defended by 4,286 unit tests and 827 governance checks. Over eight weeks we documented 22 incidents with full root-cause postmortems, in which one meta-pattern -- a failure whose error signal never reaches a human in actionable form -- manifested at least 28 times. We derive a five-class, mechanism-oriented taxonomy: (A) environment and platform quirks, (B) design-assumption mismatches, (C) error swallowing and dilution, (D) chained hallucination and fabrication, (E) operational omission and forensic blind spots. Class D is unique to LLM systems and the most dangerous: the system does not merely fail to report an error -- the LLM transforms it into fluent, plausible narrative delivered to the user. We term this fail-plausible: gray failure's differential observability escalated -- the observer is not just blind, it is convincingly lied to by the failure itself. Three findings: about 70% of silent failures were caught by human user-view observation, not tests or audits; a retrospective audit of 15 incidents found 0% ex-ante prevention but 87% regression blocking -- audits are regression engines, not prediction engines; incident latency (13 hours to 60 days) tracks failure mechanism, not code complexity -- the longest-lived failures lived in the seams between components, where no test runs. We describe the resulting defense framework and distill design principles for agent systems whose failures are loud, attributable, and boring. All postmortems and artifacts are public.

Understanding how a prediction model will perform in a new environment before deployment is essential to preventing harm when algorithms inform decision-making. Two common sources of model performance degradation are (i) covariate shift, where the target covariate distribution differs from the source, and (ii) selective labels, where the observability of outcomes depends on historical decisions. We study pre-deployment model evaluation under the joint presence of covariate shift and labeling of outcomes selectively based on observed features. In particular, we present a double machine learning procedure for estimating the target risk of an arbitrary black-box prediction model under a general loss function. We show identification of this estimand under standard assumptions and derive a bias-corrected estimator based on the influence function of the target risk. Finally, we evaluate our estimator through experiments using the eICU electronic health records database, showing that it tracks the true target risk more accurately than methods that address either selective labels or covariate shift alone, as well as baselines that combine standard plug-in approaches.

Recent finite-time analyses of nonlinear two-time-scale stochastic approximation show that under contractive assumptions the slow iterate $Y_k$ with stepsizes $β_k=Θ(k^{-1})$ and $α_k=Θ(k^{-a})$, $a\in(1/2,1)$, generally satisfies a mean-square rate of order $k^{-a}$; decoupled $k^{-1}$ rates require strong local linearity. We identify a sharp regularity-dependent boundary. In a rate-determining normal form where the slow drift contains a locally linear leakage and a nonlinear remainder of order $1+ρ$ ($ρ\in[0,1]$), the uncorrected recursion satisfies $$\mathbb{E}\|Y_k\|^2 \le C\bigl(k^{-1}+k^{-a(1+ρ)}\bigr),$$ and a matching scalar Gaussian lower bound shows that the slower term is unavoidable without modifying the update. Thus the decoupled $k^{-1}$ rate is guaranteed for the uncorrected recursion exactly when $a(1+ρ)\ge 1$. This lower bound concerns only the naive update; it is not an information-theoretic obstruction. We demonstrate this by equipping the normal-form recursion with an auxiliary online bias estimator $$M_{k+1}=M_k+γ_k(R(X_k)-M_k),\qquad β_k\llγ_k\llα_k,$$ and subtracting $M_k$ from the slow update. Under the same stability, moment, and remainder assumptions, the corrected recursion achieves $\mathbb{E}\|\widetilde Y_k\|^2=O(k^{-1})$ for every $ρ\in[0,1]$, including regimes where the uncorrected update provably suffers the slower rate. Finally, we prove localized transfer theorems that extend the phase-transition mechanism to general nonlinear TTSA in fast-manifold coordinates. The proofs are non-asymptotic and rely on two Abel-transform cancellations: one for the locally linear fast-error leakage, and one for the tracked nonlinear bias.

Tactile imaging seeks to reconstruct the internal structure of soft objects through touch sensing, with applications in medical diagnosis and robotic manipulation. Recent self-supervised learning approaches have shown promising results, but rely on global, unstructured representations and robot-controlled sensing, limiting generalization and practical use. We propose Local Encoder for Spatial Sensing (LESS), an object-centric tactile representation that exploits the local nature of touch. The tactile scene is modeled as a grid of recurrent encoders with local receptive fields, whose states are fused to reconstruct 2D or 3D images of internal structure. This compositional design enables strong generalization: models trained on single-inclusion phantoms accurately image objects with multiple inclusions and varying sizes. The local structure further supports spatial uncertainty estimation. In addition, we enable hand-held tactile imaging via external pose tracking and human-like palpation data, and extend tactile imaging to full 3D reconstruction.

Text-driven 3D scene generation is a promising technique for digital content creation, embodied AI simulation, and interactive design, yet practical workflows often require refining, extending, or correcting existing scenes while preserving non-target content. Existing methods can produce realistic and structurally plausible scenes, but they generally lack editability with requirement-level state tracking, so part-level failures often lead to full-scene regeneration or manual intervention. To tackle this challenge, we formulate controllable 3D scene authoring as incremental requirement satisfaction, unifying construction and editing. In this paper, we present MUSE, a memory-grounded multi-agent framework in which an Architect compiles instructions into structured requirements, a Sculptor executes local scene operations, and an Inspector verifies each step while updating Working, Scene, and Skill Memory. To evaluate requirement-level controllability and preservation-aware editing, we introduce AuthorBench, offering 145 constrained construction cases and a 1,584-case preservation-aware editing pool paired with external structured checks. On full construction cases, MUSE improves All-Goal success from 37.9 to 80.7 and surface-constraint fulfillment from 35.0 to 92.6 over the strongest baseline. On a stratified 240-case editing test split, MUSE achieves 49.6 All-Goal success, 99.9 preservation rate, and only 0.6 unintended change rate. Beyond automated metrics, human evaluations on compared local-editing baselines support stronger alignment with user intent, and downstream navigation-proxy tests indicate stronger spatial stability. Combined with ablations validating our memory designs, these results establish MUSE as an effective framework for controllable 3D scene authoring.

Sound events are entities with semantic identities, locations, and trajectories, but current audio-language models usually reason about clips as global event content. Conversely, sound event localization models track source directions over time but offer limited semantic coverage for language reasoning. To address this gap, we introduce ST-AudioQA, a spatio-temporal audio QA dataset and benchmark built from first-order ambisonic (FOA) renderings of static and moving sound sources. Each scene provides source identity, activity, direction, distance, and motion metadata, enabling dense trajectory supervision and questions about what is sounding, where it is, how it moves, and how sources relate. We further propose ST-Audio Encoder, a time-resolved FOA audio encoder that learns event semantics together with source trajectories, and ST-AudioLM, which connects the audio tokens from the encoder to an LLM for spatio-temporal audio QA. Experiments show that this representation improves the semantic-localization tradeoff and yields stronger reasoning performance than static spatial and localization-oriented baselines.

Deployed knowledge-tracing models are typically frozen after training, yet systematic per-item logit bias arises, from limited per-item expressivity in backbone architectures and from post-deployment shifts in item properties, degrading prediction quality. Global post-hoc calibrators such as Platt scaling, temperature scaling, and isotonic regression improve probability estimates but leave discriminative ability, as measured by AUC, unchanged. This AUC invariance is a structural consequence of monotone score-only transforms; recovering the stranded discrimination requires conditioning on item identity. We propose SLC (State-space Logit Correction), which converts binary observations to Gaussian pseudo-observations via Laplace/IRLS, applies empirical-Bayes shrinkage through a Kalman smoother, and fits an offset-Platt link. The state-space formulation also yields a detectability bound that characterizes the Bernoulli information floor, explaining why temporal tracking provides no benefit at current data densities. Across four datasets, five backbones, and three seeds, SLC improves AUC on all four datasets and NLL on three, with the advantage concentrating on sparse items. Cross-domain controls suggest that the same phenomenon can arise beyond education when the deployed backbone leaves entity-level bias.

Existing studies on gender bias in LLMs have largely focused on stereotypes, occupational associations, or explicit harmful outputs. In this work, we ask whether LLMs apply consistent response standards to the same negative behavior under matched male-actor and female-actor conditions. We introduce GAMA-Bench, a gender-mirrored benchmark of 1,298 scenarios covering intimate relationship and public social conflicts. It constructs gender-neutral misconduct templates through controlled grids and cross-model review, then compiles them into paired first-person prompts with matched actor-gender and role-reference variations. We further design a structured response-framing protocol to measure how models allocate punishment, empathy, escalation, instruction, and blame. Experiments on 10 representative LLMs reveal a consistent male-disadvantaging asymmetry: male actors receive more punitive, escalatory, and blame-centered framing, whereas female actors receive more therapeutic and empathy-oriented framing for the same misconduct. Further analyses show that this pattern persists across model families, scenario tracks, model scale, and explicit thinking-style reasoning. The official code is available at https://github.com/xufeiqiong/GAMA-Bench.

Maritime situational awareness often relies on Automatic Identification System (AIS) transmissions to track vessel movements. However, in operational or conflict scenarios, these data may be unavailable due to signal loss, deliberate deactivation, or intentional spoofing. In such conditions, synthetic aperture radar (SAR) imagery becomes a critical sensing alternative for wide-area maritime monitoring, despite providing only static scene snapshots. This work introduces HARBOR (Heading Analysis and Reconstruction from Behavioral Observation and Radar), a complete pipeline for transforming a single SAR image into predictive motion information without requiring any auxiliary data source at inference time. The method begins with SAR image preprocessing to enhance and segment vessel candidates, followed by automatic detection, size-based classification, and heading estimation using skeleton geometry and local intensity patterns. AIS data are used exclusively during an offline calibration phase to derive vessel-type-dependent motion parameters, which are then applied to generate probabilistic heatmaps of candidate future vessel positions. A case study using real COSMO-SkyMed SAR imagery demonstrates the pipeline on a maritime scene in southern Brazil, showing its ability to extract motion tendencies and generate probabilistic projections of vessel positions in data-denied environments.

Electromagnetic Navigation Systems (eMNS) have gained considerable attention for minimally invasive surgery and targeted drug delivery. While most of the literature relies on quasi-static control of these systems, recent work has demonstrated the benefits of dynamic approaches. However, trajectory tracking far from equilibrium states remains largely unaddressed. We close this gap by demonstrating the first swing-up of a magnetically actuated inverted pendulum using the clinically-ready Navion eMNS. Although the inverted pendulum is not clinically relevant in itself, the proposed method utilizes torques and forces as control objectives, making it applicable to other magnetically actuated devices such as catheters and guidewires. Our approach combines trajectory optimization that accounts for internal eMNS dynamics with time-varying Linear Quadratic Regulator (LQR) state feedback and Iterative Learning Control (ILC), which leverages previous trial data and the system's dynamic model to progressively refine the feedforward command. While LQR alone fails due to the complex phenomena of magnetic actuation, ILC enables successful swing-up within six iterations. Furthermore, post-experimental analysis reveals that the learned ILC correction closely matches the torque discrepancy predicted by high-fidelity magnetic field model calibration, suggesting learning and adaptation as a promising tool to deal with uncertainties in electromagnetic actuation arising, e.g., from patient-specific physiological motion patterns and field model calibration inaccuracies.

Contact-rich manipulation poses a fundamental challenge for world models: visual and tactile observations capture different aspects of physical interaction, and their utility depends critically on how this information is represented. We introduce ContactWorld, a controlled benchmark and empirical study of vision-tactile representations across 12 contact-rich manipulation tasks. Using a fixed world-model architecture, training procedure, and planning framework, we examine representation effects through three complementary properties: spatial fidelity, motion coherence, and predictive stability. Point clouds preserve task-relevant geometry and track physical motion more reliably than image observations, helping explain their higher average planning success of 32.1%, compared with 20.7% and 22.0% for wrist- and front-view RGB, respectively. Tactile observations generally reduce long-horizon prediction-error accumulation, but these gains do not translate uniformly into task success. Structured tactile force fields provide the most consistent downstream improvements, with PointCloud+TacFF achieving the highest overall simulated success rate of 36.1%. We further validate these trends through 900 physical trials spanning six tasks, two robot platforms, and three tactile sensing systems. Together, ContactWorld identifies sensory representation as a central design factor in vision--tactile world models and provides empirical guidance for predictive planning in contact-rich manipulation.

We present an algorithm for efficient domain-adaptive policy learning via kernel representations. Learning domain-adaptive policies is challenging since it requires an environment representation that is both sufficiently expressive to model complex sim-to-real gaps during offline training, and computationally efficient enough to support rapid online adaptation during deployment. For instance, a quadrotor may encounter time-varying, non-stationary disturbances, such as sudden gusts of wind, payload shifts, or transitions between distinct flight regimes with and without ground effects. To address these challenges, we model unknown disturbances using a differentiable kernel approximation based on random Fourier features. During the offline training phase, we randomly sample kernel coefficients and bandwidth parameters to generate a rich diversity of disturbance profiles. We then optimize the control policy via differentiable simulation with analytical gradients, a process that takes only 50 seconds of training time on an RTX 4090 GPU. During hardware deployment, the policy adapts to non-stationary environments in real time by updating both the kernel coefficients and bandwidth through online least-squares estimation. We evaluate our method on quadrotor trajectory tracking tasks across high-fidelity numerical simulations and hardware experiments using Crazyflie, subjected to various disturbances, including complex aerodynamic effects, wind, ground effects, and payload fluctuations.

Large Language Models (LLMs) have made notable progress in automated theorem proving, yet existing formal benchmarks remain limited in both mathematical coverage and difficulty. Most are concentrated in areas that are easier to formalize, such as algebra and elementary number theory, and provide limited coverage of subfields that require deeper reasoning, including mathematical analysis. To address this gap, we introduce MA-ProofBench, to the best of our knowledge, the first formal theorem-proving benchmark dedicated to Mathematical Analysis. The benchmark contains 200 formalized theorems covering 6 core topics and 27 subcategories, including measure and integration theory, complex analysis, and functional analysis. The problems are divided into two difficulty levels, an undergraduate level (Level I, 100 problems) and a Ph.D. qualifying level (Level II, 100 problems), to evaluate how well LLMs perform formal reasoning at different mathematical depths. Each problem is constructed through a human-led, LLM-assisted formalization pipeline followed by independent expert review, ensuring that the formal statements remain faithful to the original mathematics. We evaluate a range of recent general-purpose reasoning models and formal theorem provers on MA-ProofBench. However, most models perform poorly: even the best-performing model, GPT-5.5, achieves only 16% Pass@8 on Level I and 5% on Level II, while most models stay close to 0% on Level II. Further analysis identifies Mathlib hallucinations and incomplete proofs as the two dominant failure modes, while an evaluation on the natural-language version of the benchmark exposes a clear gap between informal and formal reasoning. MA-ProofBench is intended to serve as a reliable reference for tracking progress in formal mathematical reasoning in advanced domains.

Semantic 3D occupancy provides a voxelized world state for autonomous driving and robot decision making, but object and rare-class errors can affect free-space interpretation, collision checking, and temporal state propagation. We show that a common VLM strategy, aligning 3D voxel or object features with crop-caption embeddings, improves text-space similarity without reliably improving closed-set occupancy mIoU. Motivated by this mismatch, we propose VISA, a training-time semantic auditing approach for existing occupancy world models. VISA queries an offline VLM on a representative crop of each physical object instance, obtains a structured audit with class hypotheses, plausible confusions, reliability, attributes, and evidence, and propagates it along the object track. The audit is grounded to matched 3D object voxels and distilled into semantic logits through reliability-weighted taxonomy, attribute-factor, and scene-level audit graph losses, while inference remains unchanged and requires no VLM. On nuScenes, averaged across three runs, VISA improves OccWorld from 19.06 to 20.05 mIoU and GaussianWorld from 21.36 to 21.91 mIoU; on GaussianWorld, object mIoU improves from 18.18 to 19.16 and rare-class mIoU from 15.60 to 16.79. These results suggest that VLMs are better suited to closed-set occupancy as reliability-aware semantic auditors than as generic caption-embedding targets.

Large language models (LLMs) have shown promise in automating scientific peer review. However, existing approaches often struggle to generate in-depth reviews supported by concrete evidence. We argue that a key limitation is the lack of flexibility to proactively investigate suspicious parts of a paper based on accumulated evidence, as human reviewers do. In this paper, we explore how to enable an LLM-based review agent to perform such proactive investigation. We find that this can be naturally formulated as a Markov Decision Process (MDP), and propose ProReviewer, a scientific peer review agent that proactively reviews a paper guided by a maintained, structured review log. The structured review log serves as a workspace for the agent to track evidence and intermediate findings collected during review. Experiments show that ProReviewer with an 8B backbone, trained by supervised fine-tuning and optimized by reinforcement learning, achieves the highest average score across five quality dimensions, outperforming prompt-based methods with much larger frontier LLMs by up to 39% and the strongest fine-tuned baseline by 16% relatively. It also attains the highest win rates against baselines in human evaluation.

Business intelligence (BI) increasingly combines dashboard interaction with LLM-based assistance, but these two modes often fall out of sync during multi-step analysis. As users switch between direct dashboard manipulation and natural-language queries, it becomes difficult to preserve a consistent analytical state across filters, hierarchies, metrics, and chart context. We present TwinBI, an agentic digital-twin framework that couples an LLM-based agent system with an executable BI dashboard state. TwinBI unifies conversational interaction, dashboard manipulation, semantic grounding, and provenance tracking through a shared analytical state reconstructed from a unified interaction log. It also exposes artifacts such as schema views, SQL, logs, and an /insights command for state-grounded analytical summaries. We evaluate TwinBI in two complementary ways. In a controlled A/B benchmark with the same backbone agent, TwinBI improves exact-match accuracy from 43.3% to 63.3%, partial-credit accuracy from 48.3% to 70.8%, and substantially reduces timeout rate from 40.0% to 10.0% relative to Dashboard alone. In a usability study, participants benefited from the integrated dashboard-and-chat workflow, with high task accuracy, moderate workload, and favorable ratings for state-aware interaction mechanisms. These results suggest that TwinBI improves both agent-level analytical reliability and user-facing analytical support by turning visible dashboard state into richer actionable context. Our dataset and source code are available at: https://github.com/simonjisu/TwinBI

Whole-body humanoid manipulation of bulky, deformable, and shared-load objects requires distributed contact sensing and explicit force regulation, yet most imitation policies treat contact force only implicitly. On the other hand, different demonstration sources provide complementary modalities with inherent trade-offs: human demonstrations capture natural contact forces but not robot-executable actions, while teleoperation directly records robot actions but with less natural force regulation. This paper presents \textbf{WT-UMI}, a wearable whole-body tactile interface worn by human operators or mounted on humanoids, providing accurate observations of tactile images, contact forces, and end-effector poses across both human demonstration and humanoid teleoperation modes. We introduce a force-conditioned target-pose correction module that converts measured human poses into contact-aware robot targets by learning corrections from teleoperation data. To leverage the natural force interaction in human data, we propose a force-supervised planner that predicts end-effector pose chunks and contact-force trajectories. The predicted contact force serves as the reference for a tactile-based admittance controller. Across five contact-rich tasks spanning deformable objects, bulky rigid objects, and human--humanoid collaboration, WT-UMI improves success rate and reduces contact-position tracking error over four policy baselines. Our project page is available at https://wt-umi.github.io/WTUMI/.

Post-training methods such as supervised fine-tuning (SFT) and preference optimization typically align language models toward a single global assistant behavior. While effective for improving average helpfulness, this can suppress the natural variation of human responses across languages, tasks, and dialogue settings. We study this problem as conditional human-distribution alignment: models should match the human response distribution appropriate to the current interaction context, rather than a universal response style. We introduce PolyAlign, a distribution-aware alignment framework that organizes bilingual interaction data into bucket-specific human reference distributions defined by language, interaction track, response family, and length. PolyAlign combines Bucket-Aware SFT, which balances optimization across heterogeneous buckets, with Human-Distribution Preference Optimization (HDPO), which regularizes preference learning using critic-estimated distance to bucket-specific human support. Across a bilingual evaluation suite covering English and Chinese single- and multi-turn settings, PolyAlign improves conditional naturalness and distributional faithfulness while preserving competitive task utility. The results suggest that post-training should move beyond global alignment objectives toward interaction-aware alignment with human response distributions.

The rapid updates of online news make tracking event developments challenging, highlighting the need for timeline summarization (TLS). Hallucinations, where LLM-generated content deviates from source news, still remain a critical issue in LLM-based TLS and are not well studied in existing works. To bridge this gap, we identify two primary types of hallucinations: unfaithful content during news summarization and information omission in date-event summarization. Then, we propose NTS-CoT, a novel framework that leverages Chain-of-Thought (CoT) reasoning to mitigate hallucinations in TLS. The framework consists of three key modules: i) Element-CoT to capture essential news elements for faithful summarization, ii) Date Selection to combine temporal saliency and event prominence for timestamp selection, and iii) Causal-CoT to infer causal relationships and reduce omissions in date-event summarization. Extensive experiments, including quantitative analysis on three TLS benchmarks and human evaluation, demonstrate that NTS-CoT outperforms state-of-the-art baselines, effectively mitigating hallucinations and improving LLM-based TLS performance. Our source code is available at https://anonymous.4open.science/r/NTS-CoT .

Climate and environmental decision-making increasingly requires reasoning across heterogeneous inputs, including gridded physical data, satellite imagery, geospatial context, and simulator outputs. Weather and climate foundation models can forecast well, but do not reason interactively in language, while large language models (LLMs) reason in language but cannot operate directly on high-dimensional Earth-system data. As a result, real scientific workflows in Earth-science remain underserved. We introduce TerraBench, a benchmark for grounded Earth-science reasoning, built on TerraAgent, a ReAct-style executable framework that interleaves reasoning, tool calls, and observations to couple LLM planning with scientific tools for environmental retrieval, geospatial processing, simulation, and artifact-backed computation. TerraBench unifies analysis of Earth observation imagery, gridded data, GIS reasoning and simulation in a single executable interface, whereas prior benchmarks isolate these capabilities into narrow individual tasks. It is also the first in this space to pair process-level tool-use metrics with tolerance-aware numeric scoring. The benchmark comprises 403 extensive agentic tasks across three tracks (Fundamentals, Simulator-Grounded, and Document-Grounded Verification) and eight application domains with 24,500 verified execution steps. These results indicate that reliable Earth-science agents must go beyond tool access to coordinate heterogeneous workflows, parameterize tools precisely, and preserve artifact provenance.

Underactuated spacecraft faces controllability limitations and heightened sensitivity to environmental disturbances, complicating attitude maneuvering and stabilization. Due to the lack of control authority along the underactuated axis, conventional controllers cannot directly stabilize all attitude components and therefore require reference planning strategies. Furthermore, MPC approaches remain sensitive to inertia uncertainty and unmodeled dynamic couplings, resulting in degraded tracking performance under mismatch. To address these issues, we consider a hierarchical architecture integrating three layers: (i) a nonlinear model predictive controller (NMPC) for constraint and underactuation-aware maneuver planning and nominal closed-loop stability under actuator limits; (ii) a physics-informed neural network (PINN) trained offline on simulation data to estimate residual disturbance torques, with loss terms that enforce consistency with rigid-body rotational dynamics; (iii) a Lyapunov-based supervisory safety mechanism that evaluates the learned correction online and bounds or suppresses its influence to preserve the stability properties of the baseline controller. The architecture is evaluated in a high-fidelity simulation environment modelling reaction wheel dynamics, actuator saturation, and environmental disturbances. Monte Carlo studies show statistically significant reductions in steady-state attitude error relative to standalone NMPC while maintaining robust behavior under uncertainty. The supervisory layer ensures graceful degradation to purely model-based control when the learning-based augmentation is unreliable.

Hierarchical 3D scene graphs (3DSGs) for indoor robots organize geometric and semantic information across spatial scales, with a room layer that connects object-level perception to room-scale reasoning. Existing systems construct this layer from different spatial substrates (\eg{} place clusters, wall planes, or segmentation outputs), and as a result, room nodes are not evaluated on a common geometric criterion. We present an occupancy-grounded 3DSG pipeline in which room nodes are anchored to tracked free-space regions derived from occupancy decomposition, giving each room an explicit polygonal footprint. We evaluate the pipeline on 12 Matterport3D scenes by matching predicted room polygons to annotated room instances and compare against Hydra, a representative state-of-the-art place-connectivity baseline. The results show that occupancy-grounded anchoring recovers substantially more room instances than place-connectivity construction, at the cost of lower precision, and that wall-accurate room boundaries remain an open problem for both methods. Code is available at https://github.com/crcz25/OccuSG.

The extraction of structured clinical information from unstructured EHR notes is a persistent bottleneck in healthcare informatics. While large language models (LLMs) offer high performance, their deployment in clinical settings is hindered by privacy risks, inference costs, and the tendency to hallucinate beyond textual evidence. We address these challenges for the CL4Health 2026 Case Report Form (CRF) filling task by proposing a fully local, domain-adapted pipeline using the MedGemma-27B model. Our two-stage architecture, which separates binary presence classification from value extraction, enforces strict adherence to textual evidence and ensures deterministic outputs for negated, uncertain, or unknown states. By leveraging item-specific, few-shot in-context learning without external API calls or fine-tuning, our approach achieves a macro-F1 score of 0.55 on the official English test track. This result secures second place among all locally-hosted, open-source submissions. Our work demonstrates that privacy-preserving, on-premise LLM pipelines can achieve near-competitive performance with proprietary frontier models, providing a practical, data-sovereign framework for clinical NLP.

As LLM agents proliferate in prediction markets and collective decision-making, they risk a cognitive monoculture: agents built on shared foundation models produce correlated forecasts, and recent measurement finds frontier-model errors correlated at r ~ 0.77. We ask whether human cognitive diversity can be recovered from behavior and transferred to LLM agents. Nous extracts a structured eight-dimension behavioral profile from real Polymarket trading activity and injects it into agents through prompts. Our central finding is a dissociation between the two halves of that pipeline. Extraction works, partially: across 100 wallets, 8 of 14 parameters are temporally stable (split-half ICC >= 0.5, bootstrap CI lower bound > 0.3; contrarian score reaches ICC ~ 0.9); wallets are identifiable from their profiles well above chance (top-1 retrieval 17-22% vs. 1% chance); and two of four pre-specified dimensions rank-correlate with future realized profit out-of-sample, though the correlations do not survive behavioral-confound controls. Prompt-level injection does not measurably transmit it: on a semantic embedding metric, structured injection shows no significant advantage over a length-matched control on any model, and the diversity it induces neither reduces ensemble error correlation nor improves Brier score -- a null that persists across exploratory checks on sampling temperature, profile diversity, and question difficulty. Measuring the prompts themselves locates the compression before the model: the structure-to-narrative translator emits near-uniform prompts whose spread does not track profile spread. We position Nous as measuring the cognitive-monoculture problem and the limits of a prompt-level remedy, motivating deeper, below-the-prompt injection (fine-tuning, activation steering). Code, frozen profiles, prompts, and model outputs: https://github.com/WillChienT/nous-paper

Micro-gestures (MGs) are spontaneous and subtle body movements that frequently convey hidden human emotions. Recognizing MGs in untrimmed videos remains highly challenging due to their extremely low signal-to-noise ratio, severe long-tailed class distribution, and the inherent domain shift encountered in cross-subject evaluation scenarios. In this paper, we propose a comprehensive multi-modal framework for Track 1 of the 4th MiGA-IJCAI Challenge. To capture fine-grained representations, we design a saliency-guided multi-modal extraction pipeline integrating 68-keypoint skeleton joint coordinates, 3D heatmap volumes, and high-resolution RGB visual features. We introduce a gentle square-root smoothed weighting mechanism paired with an Orthogonal Semantic Embedding Loss to protect tail classes without compromising overall recognition capabilities. More importantly, to bridge the cross-subject generalization gap, we propose a Cross-Modal Pseudo-Labeling (CMPL) strategy for unsupervised domain adaptation, which significantly boosts single-modal robustness. A temperature-scaled soft-voting mechanism is finally utilized to alleviate overconfidence during late fusion. Extensive experiments demonstrate that our framework achieves a competitive F1-score of 68.13%, securing the 4th place.