Search research

Dense pass surfaces give, for every pitch cell, whether a pass played there would arrive, whether the carrier would choose it, and what the possession would then be worth. The networks that draw them read the state as a raster of per-cell counts, losing where inside a cell each player stands. LiDAR detectors, bird's-eye-view perception and graph weather models move entity features onto a grid, binning each entity to a cell or learning the transfer. We evaluate the interpolated form: each player's features are scattered bilinearly onto the grid at the player's measured coordinates, so the surface loss trains the per-player encoder end to end. Those systems adopt an interface; this paper measures one. On 53,628 passes from the 2022 World Cup, painting improves selection likelihood over the same core fed rasters alone by about a quarter of a nat: in every match of an eight-fold cross-validation, with every arm tuned over five seeds, and after retraining on seven Bundesliga and 2. Bundesliga matches from another provider. Thirteen pre-specified studies locate the gain: painting the nine raw player features with no encoder carries three quarters of it, and the learned encoder and message passing add a smaller, resolved increment. Painting also helps the original SoccerMap and a canonical U-Net, whereas offset channels, a finer raster, an attention painter and a raster-free decoder do not. Frozen across the provider boundary the likelihood advantage is lost; injected tracking error compresses it. These results concern observed-endpoint prediction, not calibrated evaluation of hypothetical passes.

How large language models (LLMs) integrate patient risk with clinical cost tradeoffs remains poorly understood. We investigated how four open-weight LLMs (Qwen-2.5-7B/32B and Llama-3.1-8B/70B) internally represent cost tradeoffs, how these representations relate to clinical predictions, and whether decisions shift as predicted by the specified cost direction and magnitude. Using a public diabetes dataset, we varied 11 false-negative (FN) to false-positive (FP) cost ratios across three phrasings and examined representations and behavioral outputs. Patient risk was linearly recoverable on par with conventional classifiers (AUC $\approx 0.83$), and cost direction was recoverable in every model. However, representational shifts in cost direction tracked output changes only in the two larger models, and responses to cost magnitude were predominantly direction-agnostic. Only 2 of 12 model-phrasings showed both opposing responses to increasing FN versus FP costs and cost-correct ordering. Representationally, a direction fitted on one cost side did not invert when transferred to the other, as expected under mirror-symmetric encoding. These findings suggest that LLMs encode risk and cost information but do not reliably integrate them into cost-correct decisions. Clinical evaluations should therefore include tradeoff tests, phrasing sensitivity, and default operating points alongside predictive performance.

Tracking neurite morphology over time helps characterize structural changes during neuronal development and deterioration, but long-term time-lapse imaging is resource-intensive and difficult to scale. Forecasting future morphology could reduce this burden. Existing neurite digital-twin models such as gated spatiotemporal attention (gSTA) produce a single deterministic forecast without representing variability among plausible futures. We introduce Morphology-Gated Residual Diffusion (MGRD), a compact stochastic surrogate that jointly forecasts twenty future neurite-morphology frames from ten observed frames while conditioning on morphology features derived from the latest observation. On controlled phase-field trajectories, MGRD reduces trajectory-wise mean MAE by 9.7% relative to a matched control while updating 4.46 times fewer parameters. On human iPSC-derived neuron microscopy, MGRD improves all four reported metrics over gSTA, including a 39.6% reduction in trajectory-wise mean MAE and a 45.3% increase in skeleton F1. Without mouse-domain retraining or fine-tuning, MGRD also improves MAE and skeleton F1 on mouse cortical-neurosphere microscopy across 10-40-min sampling intervals and forecast horizons beyond 13 hours. Repeated sampling provides a case-level variance score for ranking forecast difficulty. Retaining approximately 60% of the lowest-variance cases reduces mean MAE by 17.6% on iPSC microscopy and 16.8% on simulation data. MGRD uses 1.01% of gSTA's parameters, requires less than one tenth of its training-update time, and generates a 50-step DDIM trajectory 7.9% faster when morphology features are cached. These results establish MGRD as a compact stochastic surrogate for neurite-morphology forecasting and case prioritization across simulation and microscopy datasets.

Large language models (LLMs) drift out of date the moment their pretraining ends, yet retraining from scratch is prohibitively expensive. Continued pretraining (CPT) is the natural remedy, but it is typically evaluated through a continual learning lens that assumes disjoint data streams. This is a poor fit for time-incremental updates on web-scale crawls, where successive snapshots share substantial URL overlap by design. We study time-incremental CPT in this realistic regime: continued pretraining on FineWeb-Edu dumps drawn strictly from after each model's knowledge cutoff, evaluated across six open-weight models spanning three families (OLMo2, Llama-3.1/3.2, Gemma-3-1B) and four parameter scales (1B-3B-7B-8B). We organize our findings around four practical questions. (i) Is knowledge acquired? Yes, but heterogeneously, and without catastrophic forgetting: five of six models also improve on pre-cutoff factual recall, and the gains track pretraining saturation (driven primarily by token budget per parameter). (ii) What does it cost? Almost nothing: the macro-average across a thirteen-task suite stays within 0.01 of the base for every model. (iii) What is the recipe? Data quality dominates quantity (a curated 6B-token slice matches a broader 40B one); the optima for knowledge acquisition and general capability are separated by roughly an order of magnitude in learning rate; and LoRA at sufficient rank matches full CPT. (iv) Does it survive deployment? CPT gains transfer through SFT, while DPO's effect is family-dependent. Together, these results paint a more optimistic picture of time-incremental CPT than the prior continual learning literature suggests.

Robot foundation models learn manipulation from large demonstration corpora, but surgery is missing from those corpora: across the 780-hour Open-H surgical collection, one dataset carries synchronized force and none covers an aesthetic procedure. Liposuction is the hard case, because the instrument works under the skin and the surgeon operates by feel and by judgment. Humynex Robotics builds curated expert datasets for this kind of procedure. HumynexSurg-1 is the first release: a master liposuction surgeon performing on porcine abdominal tissue while narrating every decision, recorded with synchronized suction pressure, six-axis hand force/torque, top-down RGB-D video, side video and a lavalier microphone -- 14 episodes, 42,738 frames, 35.6 minutes, 356 utterances of which 95% compile into a liposuction-specific label schema. The capture follows a patent-pending sensing plan organized around the quantities a policy needs, so a channel captured today by a model can be upgraded to a sensor tomorrow without changing the data format. This release captures the instrument motion as a tool-hand track in the side video and provides the force channel as state; the funded capture adds a measured 6-DoF handle pose, a validated force channel, ultrasound imaging of the fat layer, and palpation sensing. As a proof of concept, NVIDIA Isaac GR00T N1.7 fine-tunes on the dataset with no custom code in under an hour per run and learns the recorded sessions; scaling probes on the same episodes show where further gains come from: every new session lowers the error on an unseen session. The dataset, its label schema, its quality-assurance reports and its evaluation protocol are the product; the next capture, many short sessions across fat regions with the sensors named here, is what the probes point to.

Obtaining the optimal action-value function in Markov decision processes is computationally intensive in large state--action spaces. In this study, we present statistically rigorous convergence results for a robust reinforcement learning algorithm warm-started by a transformer-based action-value function prediction, where natural language prompts encode task specifications. Our framework adopts the R-contamination model to characterize uncertainty in the state transition kernel, and employs conformal prediction to certify convergence via trajectory-level nonconformity scores constructed from the contracting Bellman residual. The resulting conformal quantile bounds the gap between the running and optimal action-value functions simultaneously over all iterations, thereby yielding a pre-certified stopping rule that requires little knowledge of the true transition kernel. Numerical case studies on perturbed maze environments of varying size and contamination level confirm that the transformer-based warm start measurably reduces the initial error and accelerates convergence, while the proposed conformal bounds track the true error trajectory more tightly than existing guarantees.

AI-generated music detectors are commonly compared using aggregate scores on benchmarks whose training overlap, generator lineage, source provenance, and audio-transformation history are only partially observable. This paper introduces ArtifactBench, a lineage-aware evaluation suite for measuring detector behavior across generator families and versions, real-music domains, collection-cohort shift, and inference coverage. The benchmark groups source recordings and their derived variants by content identity, separates calibration from final testing, records inference failures independently from classification errors, and reports source-level performance with uncertainty in addition to aggregate metrics. We evaluate multiple publicly available detectors under a version-pinned common protocol and examine how leakage control, cohort availability, threshold policy, and model-specific missingness alter measured performance and model ranking. On the 562-track common-success test intersection, ArtifactNet obtains 0.982 AUROC and 0.918 balanced accuracy, compared with 0.761/0.776 for the public Deezer detector; SpecTTTra and CLAM fall below 0.30 AUROC under this shifted cohort. These results also expose substantial generator- and real-domain shifts that aggregate scores alone conceal.

Existing wearable exoskeleton architectures are typically constrained by a single mechanical output modality, providing either joint torque around an anatomical joint or linear traction along a limb-training-oriented direction, which limits adaptability to diverse training scenarios. This letter presents a cable-driven switchable actuator (CDSA) that can rapidly switch between torque and tension modes while centralizing all sensing and actuation components at the proximal drive unit. A Coupled Movable Pulley Mechanism (CMPM) provides tension amplification at the distal end-effector, while a bidirectional Cable-Driven Ratchet Mechanism (CDRM) enables mode switching and preload regulation. To eliminate the need for distal instrumentation, multi-source proximal sensors are integrated with a data-driven fusion model to estimate distal output forces. An adaptive dual-mode force control strategy based on iterative learning control (ILC) is further developed. Platform experiments demonstrate transmission efficiencies of $(92.4 \pm 2.0)\%$ and $(96.5 \pm 3.3)\%$ in the torque and tension modes, respectively, along with a tension amplification ratio of $2.77 \pm 0.10$ under tension mode. Tracking tests on simulated knee-joint gait trajectories and short-stroke tension profiles yield stable control, with RMSEs of $(4.52 \pm 0.51)\%$ and $(3.15 \pm 0.19)\%$ of the uncontrolled peak value, respectively. Finally, seated human-coupled experiments validate the system's controllable force generation in both joint-torque and linear-traction application modes.

Screen-recorded web editing requests contain weak deictic expressions such as this'' and there,'' whose referents depend on speech, cursor trajectories, page state, and edit history. Such requests require intent recovery beyond the explicit specifications assumed by many existing web-editing benchmarks. We introduce Omni2Web, a bilingual benchmark of 918 instances spanning 13,907 edit steps. It defines three complementary tracks: Direct Editing evaluates webpage editing from recordings, Instruction Recovery measures explicit intent recovery, and Instruction Utility tests whether recovered instructions can drive a fixed code executor. We evaluate 17 open- and closed-source models. The best models attain 51.17 on the Edit Fidelity Score (EFS) for Direct Editing and 49.14 on the Instruction Recovery Score (IRS); under the fixed executor, the strongest recovered instructions reach 51.08 EFS, still far below the 89.69 EFS obtained with oracle instructions. Step-level analyses show that correct grounding does not guarantee successful edits, while some Omni models recover instructions that the fixed coding model executes substantially better than their direct edits. Controlled ablations further demonstrate the value of temporally aligned audiovisual evidence, while alternative judges preserve the leader and broad ordering. Together, these findings reveal substantial headroom in multimodal intent recovery and code execution and highlight the promise of pairing Omni rewriters with coding models.

Bayesian filtering provides a principled framework for online state estimation under uncertainty, yet its application to systems with high-dimensional states and complicated posterior distributions remains challenging. Recent generative models, such as flow matching, have shown potential in Bayesian filtering. However, they still rely on particle-based representations of the posterior, which lose the rich information of the full distribution, or tackle a trajectory-level inverse problem that conflicts with the recursive structure of Bayesian filtering. To address this, we propose a new perspective of directly encoding the evolving distribution into flow matching model weights, namely, the Belief Flow Filter (BFF). It is a generative filtering framework that updates model weights via gradient descent at test time to track the posterior evolution. Thereby, BFF bypasses the scalability issue of particle representations or the flexibility limitation of Gaussian assumptions in conventional filters. We theoretically justify that the BFF design is structurally aligned with Bayesian filtering, and its training objective targets the recursive filtering operator. BFF is empirically verified across 5 different physical systems, including ones with chaotic dynamics and highly sparse, non-linear observations. The results show that BFF attains the best score in 8 of 9 metric-benchmark cells across the three standard 1D and 2D PDE benchmarks, and similarly leads on the extreme single-moving-sensor setting and on a real-world-grounded tokamak plasma estimation task, demonstrating its potential to accurately approximate the Bayesian filtering operator in high-dimensional probability space.

Ensuring the correctness of LLM-generated code is a core challenge for modern software engineering. Benchmarks for agentic code generation check correctness with held-out test suites, which are inherently incomplete and increasingly susceptible to memorization. Formal verification avoids both problems, but existing work covers only standalone tasks whose specifications are given as input, not real issues, which touch large repositories and state intent in vague natural language. We present Benchproofer, a pipeline that turns a coding task with a known correct patch into a formally verified one: it writes a specification for the new code, summarizes the existing functions that code calls with axioms, and admits an instance only after mechanical and adversarial gates agree. Applying it to SWE-bench Verified yields SWE-Proof, 500 real issues whose correctness is formally verified rather than tested, and it extends to SWE-bench Pro. Evaluating Claude Opus 4.8, we find that verification catches what tests miss: a quarter of test-passing patches admit counterexamples, which a structured natural-language specification does not fix, while a correct formal one lifts resolution from 85% to 95%. Writing that specification is the hard part: an agent that must write its own gains nothing over an unaided baseline, and only 56% of those specifications pass our audit. The usual failure is faithfulness, a specification that constrains part of the required behavior and leaves the rest free. Specification quality still tracks the outcome, failing on 92% of unresolved instances against 51% of resolved ones, making faithful specification synthesis a concrete open problem.

A splash lives for a fraction of a second: sheets tear into ligaments and droplets, appearance is view-dependent and nearly textureless, and little persists long enough to track. Reconstruction research has consequently focused on smoke, synthetic liquids, or gently deforming surfaces. To our knowledge, no synchronized multi-view dataset of splashing liquids exists. We therefore introduce a benchmark of 20 real scenes, from coherent streams to violent splashes, captured by seven synchronized, calibrated 4K cameras at 60 fps, with manually refined per-view liquid and container masks and fixed evaluation splits. We further present SplashSplat, built on a single principle: impose physical structure only where the observations can constrain it. Per-frame liquid SDFs fused from the masks provide the geometry, level-set transport between consecutive SDFs yields a coarse velocity field, and Lagrangian carriers advected along this flow, corrected against each new observation and reseeded where coverage is lost, decode local Gaussians for differentiable rendering. SplashSplat outperforms state-of-the-art dynamic Gaussian splatting methods on our real captures and on a synthetic benchmark, with physically more plausible motion and a lower training cost. The same representation supports temporal interpolation and style transfer without re-optimization.

Autonomous underwater vehicles (AUVs) operating beyond reliable communications must recover from failures without human intervention. We investigate an architecture in which conventional deterministic layered control autonomy manages normal operations, while an invokable large language model (LLM) serves as a diagnostic and recovery planner when onboard anomaly detection identifies performance outside expected limits. Because language models are stochastic, rigorous evaluation requires ensemble testing rather than individual demonstrations. We present a closed-loop simulation architecture that couples real-time C vehicle software with a higher-level orchestration layer for physics-based fault injection, structured prompting, language-model interaction, mission file generation, validation, execution, and LLM-judge scoring. The framework, which we call SPAR (Simulation Platform for AUV Recovery), supports evaluation across fault realizations, prompt structures, reasoning models, and mission conditions. We vary these for a mass-shift fault over 480 SPAR trials, evaluating a frontier model and three off-the-shelf locally deployable LLMs. Model choice dominates diagnosis: the frontier model places the CG-shift mechanism in its top three hypotheses in 85-90% of trials, versus 60-78% for the best local model. Reasoning analysis indicates that local-model success is associated with following the complete diagnostic procedure, whereas weaker models often commit prematurely to elevator failure even though the actuator tracks its command. Diagnosis and operational decision performance do not appear to be coupled in this dataset. The contributions are an architecture extending unanticipated-fault recovery from detection to mitigation and an ensemble methodology for evaluating LLM-assisted mission management on low-power AUVs.

Learning visual policies for locomotion and manipulation requires coordinating contact with the environment and can incur substantial computation and GPU memory costs. First-order policy gradients (FoPG) reduce training cost through differentiable simulation, but local optimization can converge to unintended contact patterns. To address this shortfall, we propose Sampling-Guided Policy Search (SGPS), which couples recurring action-target refinement by sampling-based model-predictive control with first-order policy optimization. Behavior cloning initializes the policy from sampled actions; training then alternates sampling-based refinement with short-horizon FoPG updates under perturbed initial states and randomized dynamics. For visual policy training, we use a decoupled FoPG formulation that excludes rendering from the computation graph, enabling direct learning from depth observations without a state-policy teacher. On a single GPU, SGPS learns policies for locomotion, obstacle traversal, crate pushing, and bimanual carrying on simulated Unitree Go2 and G1 robots. Our experiments further show that refinement improves policy learning beyond initialization and tracking alone. For hardware deployment, the distilled policy transfers zero-shot to a real Go2 and uses onboard depth to autonomously trot, crawl, clear hurdles, and switch between these behaviors.

Animal demonstrations provide quadruped robots with natural and distinctive gait styles that are difficult to specify through hand-crafted rewards. However, their narrow directional coverage leaves little style-consistent supervision for backward, lateral, and turning commands. We present OmniMimic, a training framework that turns directionally limited animal demonstrations into a single multi-gait policy over target per-axis velocity ranges. OmniMimic first combines temporal reversal, constrained dynamics completion, and sagittal reflection to construct robot-specific kinematic and physical supervision beyond the observed directions. It then expands commands progressively from the demonstrated velocity distribution toward the target per-axis bounds, and uses a shared actor with soft-gated, gait-specialized residual experts to balance reusable locomotion skills with gait-specific corrections. Across four gaits in simulation, OmniMimic reduces mean foot-position RMSE at forward and backward reference velocities by 12.9% and velocity-tracking RMSE on a uniform Cartesian command grid by 63.1%, compared with the matched APEX baseline. The project page is at https://OmniMimic.github.io.

Full-consensus rates are often treated as indicators of collective cognition, yet depend on how participation and final states are operationalized. We replayed 100 held-out human Wason groups with matched large language model (LLM) agent groups, seeding one belief-anchored agent per participant's pre-discussion answer and scoring agents and people with the same code. Across human scoring definitions, estimates ranged from 24.0% to 57.0%; about one fifth of participants never posted, whereas agents almost always did. Agent groups remained more consensual in two post-unblinding sensitivity analyses: the submit-based comparison (n = 98) yielded gaps of 34.0 and 43.9 percentage points for chat and reasoning modes, and the participation-matched comparison (n = 45) yielded gaps of 34.1 and 44.4 points. These complementary routes reduced different measurement asymmetries yet converged within 0.5 percentage points. The gap persisted without early stopping and under a reparameterization removing the memorizable answer; reasoning-mode groups then agreed nearly unanimously, mostly on incorrect answers. Simulated consensus did not track collective accuracy, and belief-anchored agent groups were biased estimators of the human group-outcome distribution in this setting. These analyses provide a scoring-explicit basis for assessing simulated-group estimates of human deliberative outcomes.

Autonomous recovery of a small multirotor onto a hovering multirotor carrier differs from recovery onto ground or shipborne platforms because the recovery surface is itself an actively controlled, thrust-limited aerial vehicle. This paper presents a field-validated autonomy framework for a heterogeneous rover-mothership-child system executing rover supervision, mothership transit, child deployment and sortie, autonomous return, aerial recovery, and synchronized descent. The recovery stack combines jerk-bounded reference generation, disturbance-observer-augmented planar tracking, feasibility-aware vertical control, a discrete-time barrier-based safety filter for relative vertical geometry, and communication-aware carrier-state prediction. The contribution is the coordinated system-level integration of these methods for recovery onto a hovering multirotor and its full-scale outdoor validation. The framework is implemented on a PX4-ROS 2 architecture using RTK-enabled GNSS, IMU, and barometric fusion, with mothership-side 1D lidar used only as an auxiliary near-contact cue. RTK-fixed positioning was maintained throughout testing. Across 20 outdoor cooperative missions, 17 successfully completed deployment, sortie, and recovery, giving an observed mission success rate of 85%. For successful recoveries, mean terminal-alignment time was 6.3 s, mean planar alignment error at acceptance was 0.18 m, maximum terminal planar deviation was 0.32 m within a 0.40 m capture radius, and minimum logged relative vertical separation during coupled descent was 0.41 m. Mothership planar station-keeping RMS error was 0.25 m. The three unsuccessful trials occurred at different mission stages and are analyzed separately. Results demonstrate practical autonomous aerial recovery within the tested outdoor operating envelope.

Two-timescale stochastic approximation (TTSA) is a fundamental tool for analyzing coupled iterative algorithms in reinforcement learning, optimization, and stochastic control. However, finite-time guarantees for nonlinear two-timescale schemes remain difficult to obtain, especially under constant step-sizes. In this paper, we study nonlinear TTSA with step-sizes $α\ggβ$. Under standard stability, regularity, and Markovian noise assumptions, we upper bound the mean-squared error and the bias of both iterates around their limiting equilibria. Our bounds scale as $O(α+β^2/α^2)$, which we prove to be tight when $β\leα^{3/2}$. The analysis separates the contributions of initial conditions, fast-timescale tracking error, Markovian dependence, and timescale coupling, thereby clarifying the origin of the $β^2/α^2$ term. Our results reveal qualitative differences from the linear TTSA setting previously studied, showing that nonlinear dynamics introduce additional finite-time effects that are absent in the linear case.

Conventional 3D Gaussian Splatting assumes a closed set of observations and long optimization schedules. Continual RGB-D mapping in contrast poses the problem that new observations arrive online, while previously reconstructed regions must be preserved. We present EliGSiR (Evidence-guided Load-adaptive Incremental Gaussian Splatting with Image Replay), a continual Gaussian mapper that controls how the available optimization budget is used as the reconstruction evolves. Map-Guided View Scheduling filters redundant incoming views and reconsiders retained views according to the current state of the map. Load-Adaptive Fidelity adjusts supervision resolution to the current mapping load instead of following a fixed resolution schedule. Targeted Geometry Growth separates depth supervision from Gaussian creation and adds geometric capacity only where repeated RGB-D observations indicate missing or misplaced structure. Together, these mechanisms adapt which views are optimized, how much image detail is used, and where the representation grows while mapping remains active. We evaluate EliGSiR on Replica, TUM RGB-D, ScanNet++, and real RGB-D sensor sequences, considering both the final reconstruction and the map available throughout acquisition. On TUM RGB-D fr3/long_office_household, EliGSiR reaches 21.52 dB with the same ground-truth mapping poses used by the controlled baselines, compared with 19.42 dB for SplaTAM. In the tracked-pose comparison, EliGSiR with live ORB-SLAM3 poses reaches 23.02 dB in 155.5 s, compared with 20.10 dB in 230.9 s for CaRtGS using its native tracker. We further evaluate reconstruction throughout acquisition and show how EliGSiR adaptive view scheduling, supervision fidelity, and geometry growth improve the use of the available mapping budget.

Straight-through processing (STP) on extracted key-value fields from financial documents without human review requires a calibrated probability together with a bounded guarantee on the residual error of the auto-approved tier. The emergence of modern Vision Language Models (VLMs) provides an out-of-the-box capability for extracting the key-values, but their verbalized confidence signals are unreliable and weakly track field correctness. This paper introduces a decomposed confidence layer along three interpretable channels, including perception, layout, and validation. Together with a final conformal risk control, the score can be used for reliable STP of financial documents. The method is validated on three public datasets covering real invoices, synthetic invoices, and ad-buy forms, using two different VLM families (Qwen3.6-27B and Gemini-3.1-Flash-Lite). Our decomposed score consistently improves the separation of correct from incorrect extractions, substantially raising the AUROC from 0.54-0.74 for VLM verbalized signals to 0.90-0.99 with contributions from all three designed channels. Crucially for industrial deployment, this enables usable STP. The native VLM confidence signals could clear only 0.1%-7.0% of fields under risk control at a target error of <10%. In contrast, the proposed method auto-approves 49-72% of fields while holding the empirical error of the accepted tier at or below the target.

Long-horizon robot manipulation requires not only stable local visuomotor control, but also continuous target tracking and reliable task progress assessment throughout execution. This challenge becomes particularly critical when multiple objects share identical appearances and must be manipulated in a prescribed order. In such scenarios, relying solely on a limited-horizon manipulation policy is often insufficient to determine which instance should be operated on and when the task should transition to the next stage. To address this challenge, we propose MaskHarness-WAM, an instance-grounded harness for long-horizon manipulation. The proposed system connects high-level task planning with low-level manipulation policies through target masks, while leveraging visual feedback for subtask scheduling and continuous execution. Since each subtask corresponds to a different target instance, the low-level policy requires a newly established initial target mask under the updated scene at each subtask transition. The harness continuously re-observes the environment, generates, and verifies the target mask at subtask boundaries, thereby updating the instance-level spatial condition provided to the low-level policy. Furthermore, the system advances the manipulation process by switching target instances according to the verified completion status of each subtask. Experiments on a real robot platform demonstrate that MaskHarness-WAM substantially outperforms limited-horizon policies on sequential multi-object manipulation, showing its effectiveness in extending local manipulation skills to reliable long-horizon execution.

Embodied visual perception relies on temporally coherent visual experience accumulated through continuous engagement with the environment. However, collecting large-scale egocentric binocular observations together with dense annotations remains costly and difficult. Moreover, visual experience is shaped not only by the environment but also by the embodiment of the observer, including viewing height, field of view, binocular geometry, and motion through the scene. To address these challenges, we present BinoGen, an automated framework for generating large-scale, embodiment-aware egocentric binocular visual experiences in indoor environments. BinoGen jointly models environmental and observer variation through generative scene synthesis, probabilistic object instantiation, appearance randomization, stochastic trajectory generation, and configurable binocular camera setups. The framework produces synchronized binocular videos together with dense multimodal supervision, including depth maps, optical flow, surface normals, semantic maps, object coordinates, and camera poses. Using BinoGen, we construct a dataset comprising more than 20 million annotated images for supervised learning. We demonstrate two complementary utilities of BinoGen. First, incorporating BinoGen data consistently improves real-world visual perception, including depth estimation, object detection, and video object tracking. Second, paired human-inspired and mouse-inspired observations from the same environments enable controlled investigation of how observer embodiment affects perceptual learning. Embodiment-specific adaptation substantially improves performance, while joint training enables a single model to perform competitively across both embodiments. Together, these results demonstrate that large-scale, controllable visual experience can improve embodied perception...

Daily locomotion encompasses diverse activities and frequent transitions between them, yet most exoskeleton controllers are designed for a single activity or a narrow set of related movements. Changes in activity therefore typically require explicit mode switching and separately tuned or retrained controllers. Simulation-based learning reduces the need for hardware-based tuning but generally retains this limitation. Here we present UniExo, a framework that first constructs a multi-skill musculoskeletal human policy and then jointly trains an exoskeleton control policy with it. Four single-skill imitation experts for walking, turning, running and backward walking are distilled into a single network structured by a skill latent and subsequently fine-tuned through reinforcement learning on transition sequences. The resultant unified human policy achieves a mean tracking success rate of 94.7% on unseen clips of the four skills and exhibits greater robustness to perturbations than its constituent experts. A single hip exoskeleton controller (UniExo) is initialized from hip moment prediction of the human policy and co-adapted with it through multi-agent reinforcement learning across the four skills. This co-adaptation shifts the timing of the assistance torque and raises the fraction of positive work delivered to the hip. When deployed on a custom hip exoskeleton, the controller generalizes across four treadmill speeds in six participants and assists one participant through a continuous route of all four skills and their transitions, without skill labels or explicit mode switching. UniExo thus provides a step towards replacing activity-specific controllers with unified, user-specific controllers that support diverse locomotor activities and the transitions between them.

Coding-agent benchmarks are built for broad and comprehensive comparisons, not frequent development decisions. Individual runs vary, full suites are expensive, and the benchmark harness may differ from the harness used in practice. In a resampling analysis of DeepSWE's published trials, only 19.5% of tasks (22 of 113) had a fifth-percentile Pearson correlation of at least 0.50 with full-benchmark performance. The paper presents DeltaSelect, an open-source method that identifies tasks whose one-run results consistently track full-benchmark performance using Pearson correlation, maps fractional verifier results to a common score using linear regression, and selects a fixed task set within a dollar budget. DeltaSelect is intended for repeated baseline-versus-candidate comparisons during development, not model rankings. In a gpt-5.6-luna low-reasoning case study, DeltaSelect was used to revise custom skills and instructions. Across 13 evaluations, the recorded cost was USD 27.86 at rates published August 16, 2026. The adopted version cost 58.1% less than the initial version (USD 1.75 versus USD 4.18; p=0.008), while the calibrated score was higher (42.36% versus 36.46%; published-analog variance p=0.326).

Data attribution methods using gradient similarity are widely used to analyze and select training data for large language models, but what gradient similarity actually measures is debated. Some interpret it as identifying task-relevant skills, while other work reports that surface form is the main factor. We resolve this debate for supervised fine-tuning examples by varying task and answer format independently. Specifically, we render benchmarks in different answer formats, such that datasets can share a task without a format or a format without a task. We find that gradient alignment follows the answer format, as benchmark pairs sharing an answer format align strongly (disattenuated cosine near 0.4), while same benchmarks rendered with different answer format classes show no alignment (near 0.0). We demonstrate that this ordering holds from the earliest pretraining checkpoints through post-training, and across model scales and families. We then analyze the released selections of LESS, a gradient-based data selection method for instruction tuning, and find that each target's selections over-represent the target's own answer format. Hence, we demonstrate that gradient-based attribution methods track format similarity more than task semantics, meaning that such methods, as well as the semantic interpretation of the gradient, should be tested on data where answer format and task vary independently for greater robustness and reliability.

Spatial intelligence requires more than describing object locations. Under incomplete observation, models must identify and acquire missing evidence, interpret it in a common spatial frame, and act on it. We introduce VA-Bench to evaluate the complete observe-reason-act-revise loop. General-purpose MLLMs learn procedural context from RGB-only demonstrations, actively select camera viewpoints, issue metric Cartesian commands, and revise them from execution feedback. Models receive no privileged object poses, oracle trajectories, or learned action heads. A fixed model-agnostic controller executes only model-specified targets. VA-Bench contains 14 base task families (11 single-arm and three dual-arm), seven held-out geometry/layout variants, and a long-horizon five-object composition track. We evaluate 12 primary model conditions in three independent runs over the same 20 physically verified seeds per base task, reporting terminal success, nine trajectory-level behavioral diagnostics, and subtask progress. First, the best-performing model scores 100.0% on target localization and 78.9% on spatial relations in the annotated run. Its three-run macro-average task success is only 53.93+/-3.17%. Second, active camera control significantly improves task success over passive multi-view observation. In one matched comparison, success rises from 27.86% to 57.50%. Third, held-out geometric transfer can reduce task success by over 30 percentage points. No model completes a strict long-horizon episode, despite substantial partial progress. VA-Bench thus tests whether general-purpose MLLMs can turn visual demonstrations and actively acquired evidence into successful embodied action.

High-quality pre-training data is a critical bottleneck for educational and STEM-specific language models targeting edge AI and on-device deployment where token budgets are tightly constrained. While major organizations train ever-larger models on private corpora, the open ecosystem lacks STEM-focused synthetic datasets that deliver high per-token learning value efficiently for small models. To address this gap, we introduce QVAC Genesis III, a 191.43B-token, STEM-focused multi-domain synthetic corpus covering 19 domains across several difficulty levels and different educational styles. QVAC Genesis III is built via a dual generation strategy that performs targeted teacher distillation using a weak edge-scale student model as signal: the student's failures are converted into corrective explanations, while its successes are expanded into contrastive option-level reasoning over all answer choices. We further introduce an LLM-as-a-parser evaluation protocol that extracts final answers from free-form outputs and tracks both accuracy and answer validity. To validate the effectiveness of our QVAC Genesis III data, we conduct controlled from-scratch ablations with 1.7B-parameter models, showing that models trained with QVAC Genesis III consistently outperform both models trained with the open-source synthetic corpus Cosmopedia-v2 and the publicly released Cosmo-1B model across ARC, GPQA Diamond, and MMLU STEM benchmarks, achieving up to +28.57% on ARC-E and +21.35% on ARC-C, while reaching a Valid Answer Rate of up to 99.45%.

Text-based person retrieval under a sim-to-real gap (synthetic training data, a real-image gallery) is usually tackled with costly fine-tuned cross-encoders. We ask whether a frozen-encoder system can compete. We present SCOUT, which casts cross-modal retrieval as prediction in embedding space. A trainable predictor maps the patch tokens of a frozen video encoder into the embedding space of a frozen text encoder under a bidirectional InfoNCE objective, and no encoder is fine-tuned in the base model. The video encoder is V-JEPA, the text encoder is EmbeddingGemma, and the predictor is initialized from a Qwen3.5-0.8B decoder. We make three findings. First, the best frozen text encoder is simply the one whose geometry best matches the video features. A training-free alignment score ranks three candidate text encoders in the same order as their retrieval accuracy on our held-out split (Spearman $ρ= 1.0$); a fourth, LLM-based encoder shows the rule is metric-dependent, holding for a neighborhood-overlap score ($ρ= 0.8$) but not for a linear probe ($ρ= -0.2$). Second, two precision-targeted levers, parameter-efficient ExPLoRA adaptation of the video encoder and a training-free attribute-decomposed reranker built on a vision-language model, improve the top-rank precision that otherwise limits the frozen system, adding 2.2 points of leaderboard R@1. Third, a local-versus-public calibration study explains which interventions transfer to the real domain. On AI City Challenge 2026 Track 4 the full retrieve-fuse-rerank system reaches 84.25 mAP@10 on the final leaderboard, while a single frozen model submitted alone reaches 60.63. Our trained components cost about 95 GPU-hours. CMP, the dataset authors' fine-tuned cross-encoder that trains for sixteen GPU-days, is one fusion member of the full system, not an alternative. Code and annotations: https://github.com/abtraore/SCOUT-ECCV

Ensuring intrinsic safety in physical human robot interaction (pHRI) is a critical requirement for social and service robots. While Series Elastic Actuators (SEAs) offer hardware based compliance, traditional metallic designs often require complex, multi part assemblies. This paper presents the design, finite element analysis (FEA), and experimental validation of a low stiffness, torsional spring for SEAs, manufactured via 3D printed thermoplastic polyurethane (TPU). The compliant element exhibits a highly linear torque deformation response (Ks = 0.066 Nm/degree), matching numerical predictions with under 3% deviation, a variance attributed to FDM structural anisotropy. To accommodate external interactions using standard position limited servomotors, a hybrid position controller with torque threshold switching was implemented. Experimental evaluations demonstrate the system ability to accurately track non stationary trajectories and safely yield to external disturbances. Furthermore, the inherent material damping of the TPU acts as a passive low pass filter, preventing high frequency oscillations during control mode transitions. The proposed architecture offers a cost effective, reliable, and easily manufacturable solution for safe pHRI.

Language agents remain brittle in interactive environments, where success requires long-horizon state tracking, valid action execution, and recovery from failed steps. We extend SwiftSage, a dual-process agent that combines a fast action proposer with a slower planner, using two modular cognitive extensions: an Adaptive Memory Module (AMM) for salience-gated episodic storage and trigger-driven retrieval, and a Self-Reflection Module (SRM) for bounded execution-time validation and corrective intervention. Both modules are implemented as feature-flagged extensions over the same execution substrate, enabling controlled ablations on ScienceWorld. Across four configurations---baseline, baseline+AMM, baseline+SRM, and the full system---the full system achieves the best mean final score (64.62), success rate (43.17%), and successful-step efficiency (19.33 steps), while SRM is the strongest standalone contributor. The results suggest that execution-time control is the dominant bottleneck in this setting, while episodic memory becomes most useful once the runtime loop is stabilized.