Search research

Ontology alignment (OA) has evolved through several methodological paradigms, ranging from lexical and structural aligners to knowledge graph embedding (KGE) models and, more recently, Large Language Model (LLM)-based approaches. Although modern OA frameworks provide unified ecosystems for deploying these heterogeneous aligners, mechanisms for systematically reconciling their complementary and sometimes conflicting predictions remain relatively underexplored. We present OntoAligner-Ensemble, a modular and aligner-agnostic framework that combines candidate correspondences through a configurable two-stage process comprising voting-based fusion strategies followed by post-fusion selection policies. The framework supports any aligner implemented within OntoAligner that produces candidate correspondences, enabling diverse alignment paradigms to be integrated through a unified decision process. To demonstrate its effectiveness, we instantiate the framework using representative lightweight string-aligner, KGE-based, and Retrieval-Augmented Generation aligners powered by both open-weight and API-based LLMs. We evaluate individual aligners and ensemble configurations across eight benchmark tasks from five OAEI tracks spanning biomedical to beyond-equivalence. The results show that ensemble fusion consistently improves the balance between precision and recall and frequently outperforms standalone aligners across diverse domains. Furthermore, our analysis reveals that ensemble composition directly affects the precision-recall trade-off: heterogeneous cross-paradigm ensembles generally improve precision, whereas homogeneous LLM ensembles more often achieve higher overall F1-scores. These findings demonstrate that systematic ensemble learning offers a robust and reproducible strategy for OA while providing practical guidance for selecting ensemble compositions under different alignment scenarios.

Recent advances in large reasoning models (LRMs) have shown that reinforcement learning with verifiable rewards (RLVR) can substantially improve reasoning in mathematics and code, where outcomes can be checked automatically. Extending this progress to open-ended and agentic tasks remains difficult because reliable rewards are harder to obtain and direct human supervision cannot keep pace with the scale and complexity of model-generated experience. This paper studies how LRMs can continue to improve as human supervision gradually recedes from the learning loop. We examine two connected dimensions of this problem. The reward axis traces the development from per-instance human judgments to reusable verifiers and rewards that operate even without human feedback. The experience axis examines how learning can progress from human-curated tasks and environments toward self-generated curricula, constructed environments, and autonomous co-evolution. We connect these dimensions through a five-level ladder from L0 to L4 that identifies which parts of the learning process remain under continued human control. Our analysis further highlights the risks introduced by increasingly autonomous rewards and experience generation, including reward hacking, feedback drift, curriculum collapse, and environment errors. Consequently, we also provide the evaluation around three complementary objects: policy capability, feedback fidelity, and experience quality. This analysis provides a structured account of current approaches to scaling LRMs beyond human supervision and the open problems involved in developing self-sustaining learning systems toward superintelligence. Furthermore, we maintain a continuously updated \href{https://github.com/visitworld123/Awesome-Scaling-LRM-Beyond-Human-Supervision}{GitHub repository} to track the latest advances.

Learning generalizable algorithmic computations remains a challenge for neural networks, as reflected in persistent failures on compositional and length generalization benchmarks. We present a provably correct, transformer parameterization (with only 280 learnable parameters for Boolean algebra tasks) capable of learning and evaluating problems of any depth or length. We assume inputs are fully parenthesized, well-formed expressions. Our approach conceptualizes algorithmic tasks as circuit models embedded in transformers, enabling depth-1 circuit reduction in a single forward pass. To achieve depth generalization, we introduce a positional encoding that tracks each gate's depth within the circuit, enabling the model to identify evaluable subexpressions at each iteration via masked hard attention, with $O(n)$ per-iteration complexity via linear attention. Combined with an autonomous halting criterion, the model terminates after $d$ iterations for problems of depth $d$, yielding $O(n \cdot d)$ total complexity. We show that training on shallow problem instances (depth 1 and depth 2) effectively recovers interpretable parameters that {\em snap} into place, resulting in exact length generalization. Though we establish that our construction provably evaluates Boolean expressions -- a universal symbolic computation -- of arbitrary length perfectly, in other experiments we also demonstrate that our transformer variant can learn and generalize perfectly (100% accuracy) on other common length generalization benchmarks, including modular arithmetic and ListOps.

Pretrained vision embeddings are increasingly used as general-purpose representations for modelling how people appraise urban scenes, and are validated almost entirely by how well they predict human ratings. High predictive accuracy does not establish that these embeddings organise scenes as human perception does. We test the two properties separately against brain data. Using openly released EEG from 63 adults who viewed and rated 56 Berlin street scenes, we estimate the representational geometry of the scenes over time, the proportion of that geometry that is explainable at all, and its correspondence with seventeen feature spaces spanning language-supervised, self-supervised, category-supervised and dense-prediction training, two orders of magnitude of scale, and interpretable controls. Correspondence is low throughout: the best representation, DINOv2 ViT-B, reaches 29.6% of the lower bound of the noise ceiling, the panel spans 11.0% to 29.6%, and a Gabor energy descriptor is indistinguishable from the best model while outperforming every language-supervised model tested. Within a model, deeper layers still match later neural responses, so the hierarchical correspondence found for object recognition survives even at this low overall level. The same embeddings predict held-out appraisal ratings well, up to r = 0.87, and the two measures do not track each other across models; reweighting features towards the neural geometry lowers appraisal prediction for every model tested, against a control of matched dimensionality. Predicting how a street is appraised is therefore weak evidence that a model represents the street as the brain does. The benchmark uses only public data and requires no training, so evaluating a new representation needs only its embeddings for 55 images.

The downwash wake of a hovering quadrotor governs both the vehicle's own performance and the safe spacing of multi-rotor formations. Prior measurements have largely characterized the mean flow, using single-point anemometry, volumetric tracking, or planar cuts through part of the rotor system. Higher-order turbulent statistics of the merged wake, and how they relate to canonical jet scaling, have remained unresolved, particularly for small quadrotors at the low-Reynolds-number end of the size range. Here, we present a detailed particle image velocimetry (PIV) study of the downwash of a hovering Crazyflie 2.1 quadrotor (arm length, $l = 46$ mm), sampled along a diagonal cut, passing through rotors along the symmetry axis of the quadrotor, and a front-rotor cut, passing through adjacent rotors. The four rotor jets merge into a single column by $z/l \approx 5$, beyond which the mean velocity profiles progressively approach the canonical round-jet self-similar form, collapsing by $z/l \approx 13$ when scaled by the local centerline velocity and half-width. Centerline decay and half-width growth follow canonical scaling laws with an effective source diameter $D_\text{eff} = 2.29\,l$, effective Reynolds number $Re_{D_\text{eff}} = 3 \times 10^4$, at the low end of the range over which canonical jet scaling has been established, and spreading and decay constants nonetheless within the canonical round-jet range. Resolving both cuts shows that the turbulent normal stresses retain a bimodal, cut-dependent signature of the four-rotor source throughout the measurement domain.

Large language models (LLMs) trained only on text and code can sometimes generate programs that draw recognizable images. However, it is unclear whether this reflects an internal representation of 2D spatial layout or simply the ability to translate spatial descriptions into code. We introduce Autoregressive Mosaics (AM-Bench), a benchmark that separates these factors: First, a translation task gives a model a fully specified geometry of a picture in words as a prompt and asks for the code that produces it. Second, a layout task requires the model to compose an image from an underspecified prompt. Across eight open-weight text-and-code-only models, all models reliably translate specified geometry into code, but their open-ended layout performance differs substantially, indicating that these differences are not explained by code-generation ability alone. An output-medium ablation further shows that the interface or medium of expression that the model uses matters: replacing procedural code with raw SVG improves layout scores across all models. Finally, probing model activations shows that a coarse layout plan is present before generation, but reflects only the layout implied by the prompt. During generation, models track the evolving geometric state instead of executing an initially fixed plan. Overall, these results show that 2D spatial performance in text-only LLMs depends on both the model and the output medium, and is not explained by code-generation ability alone.

Recent multilingual vision--language encoders cover hundreds of languages in a single model, yet on two state-of-the-art instances retrieval on low-resource languages (LRL; e.g. Swahili) trails high-resource ones (HRL; e.g. English) by $30^+$,pp. We ask where in the trained encoder this gap is located. Prior modality-gap and cross-lingual subspace work suggests a linear language direction at the output crowds out alignment-relevant geometry. We falsify this: LEACE drives the linear language classifier from $>99\%$ to near chance and iterated INLP to $37$--$50\%$ while LRL retrieval moves within $\pm 1.5$,pp and all tier means within $2.2$,pp, tracking random controls. The linear bias is a \emph{symptom}, not the cause. Instead, the alignment-causal factor lies along the encoder's forward path: the EOS (end-of-sequence) hidden state's per-language trajectory diverges with depth. Substituting the EOS with its parallel English value three blocks before the projector lifts Swahili from $22.1\%$ to $69.1\%$ on one encoder (and reproduces on the other); three controls rule out pooled-position tautology and English specificity. A front-layer trunk that pulls each language's projection toward the parallel-content centroid corroborates the diagnosis at training time, recovering $+9.6$ / $+17.1$,pp on LRL XM3600 retrieval (1{,}000-image subset), with consistent gains across three further benchmarks while preserving HRL performance.

Real-world time series often exhibit irregular sampling and extended temporal horizons, requiring models to capture continuous-time dynamics across arbitrary intervals without prohibitive scaling costs. Discrete-time methods collapse variable time intervals into static positional steps; solver-dependent continuous-time models preserve temporal structure but rely on sequential integration, precluding parallelization; and solver-free approximations avoid this cost yet none couples observed time intervals with input-driven state modulation. We propose Liquid Gated Attention (LGA), a solver-free parallel temporal operator. By parameterizing an input-driven gating mechanism with observed time intervals, LGA introduces a continuous-time inductive bias and formulates hidden state evolution as a fast-weight associative memory, enabling parallel computation across the temporal dimension. Using matrix associativity in non-causal encoding and a prefix scan in causal encoding, LGA attains linear temporal complexity in sequence length in both modes. A sequence-level normalization bounds cumulative temporal decay for stable long-horizon optimization. Building on LGA, we instantiate LFormer, a modular backbone for continuous-time representation learning. Across six tasks and sixteen datasets spanning up to 17,984 steps, LFormer demonstrates long-range dependency modeling, fine-grained state tracking, and trajectory reconstruction from sparse and noisy observations, while delivering competitive performance against state-of-the-art discrete-time and continuous-time baselines with linear scaling efficiency.

Visual SLAM is commonly evaluated on clean trajectories, although deployment failures are often caused by adverse weather, illumination, blur, and sensor artifacts. Controlled corruptions are attractive because they isolate such factors, but a synthetic stress test is useful only when it leads to the same engineering conclusion as the condition it is intended to approximate. This work examines that question for monocular SLAM. We evaluate a classical feature-based system and two learned trackers under image-space, geometry-aware, and compound corruptions, and compare their behavior with adverse conditions from 4Seasons. Rather than reducing robustness to a single trajectory error, the evaluation separates explicit tracking failure from drift accumulated by methods that remain active. The results show that learned trackers largely replace catastrophic loss with sustained, and sometimes severe, drift. More importantly, the apparent ordering of the learned systems changes with the physical fidelity of the corruption: structured rain and fog proxies preserve the real-world ordering, whereas a simple illumination proxy does not. Code is available at: https://github.com/abhaythomas/master_thesis_vslamlab_robustness.

Fixed-viewpoint infrastructure sensors repeatedly observe the same traffic space, making roadside 3D occupancy structurally different from ego-vehicle perception: a near-persistent static scaffold is overlaid with sparse, short-lived dynamic events. Existing occupancy benchmarks and methods, however, are built around moving ego vehicles and neither measure nor exploit this structure, instead treating occupancy as flat one-shot voxel classification. We address this gap from both data and model perspectives. We build InfraOcc, to our knowledge, the first real-world infrastructure-side semantic occupancy benchmark, with dense voxel annotations for 290 multi-modal sequences in a fixed roadside frame, a static-dynamic decoupled annotation pipeline, unified camera-only, LiDAR-only, and multi-modal evaluation, and diagnostics for static and dynamic occupancy. InfraOcc shows that static infrastructure fills 97.3% of occupied voxels and persists across frames, whereas dynamic participants have a median occupied-frame ratio of only 1.8% per location, revealing a structural static-dynamic asymmetry beyond semantic long-tailedness. We further propose ProSD-Occ, which reformulates occupancy as progressive static-to-dynamic evidence reasoning: it explains persistent layout, exposes residual dynamic evidence under static-confidence guidance, and recomposes static, dynamic, and free-space evidence into a unified field. ProSD-Occ ranks first in overall, dynamic, static, and geometric occupancy on every track, e.g., a 23.5% relative camera-only dynamic-mIoU gain over the strongest baseline and 65.87 multi-modal overall mIoU, establishing fixed-viewpoint roadside occupancy as a distinct problem with its own reasoning paradigm. The benchmark and code will be publicly available at https://github.com/yanglei18/InfraOcc

Long-horizon robotic manipulation requires vision-language-action (VLA) models to track scene states and their evolution beyond the current observation. However, simply conditioning policies on observation history does not guarantee that the history is effectively utilized: action supervision constrains what the policy should do, but only indirectly constrains what its history representations should retain. To resolve this, we present Temporal Forcing, a 4D representation alignment framework that explicitly supervises latent temporal states and their transitions. Specifically, we first introduce a history pathway that compresses past observations into compact latent tokens. We then align these tokens and current-frame features with geometric targets from a pretrained 4D foundation model, providing direct supervision at both the state and transition levels. The 4D foundation model and alignment heads are used only for training-time supervision. Temporal Forcing improves average success from 96.6% to 98.8% on LIBERO, with the largest gain on LIBERO-Long (93.8% to 97.2%), and from 53.5% to 62.8% across twelve RoboTwin 2.0 tasks. Furthermore, Temporal Forcing increases full-task success from 20.0% to 43.3% on a physical multi-stage hidden-placement task. Controlled experiments show that 4D representation alignment is crucial for making observation history beneficial to the model. Code will be publicly available.

Reinforcement learning (RL) is used to improve the reasoning abilities of LLMs, while training data span heterogeneous tasks. However, most RL post-training pipelines rely on fixed or manually designed task mixtures, even though task usefulness changes as training progresses. Online curriculum methods often define learnability by update magnitude, ignoring whether the update translates into reward gains, which can misallocate rollout budget toward tasks with large but ineffective updates. We propose PAC, a Progress-Augmented Advantage Curriculum for multi-task RL of LLMs that combines two task-level signals: advantage-derived learnability, which measures the magnitude of the policy update a task can induce, and recent reward gains, which show whether those updates have improved task performance. A Bayesian Thompson Sampling controller uses these signals to allocate rollouts across tasks during GRPO training. We evaluate PAC under two settings: a multi-level reasoning setting and a multi-domain reasoning setting. PAC improves sample efficiency and final performance: it reaches comparable validation scores with fewer rollout steps and achieves higher final averages than random sampling and advantage-based curriculum baselines in both settings. These results show that jointly tracking advantage signals and actual reward gains yields an effective online curriculum for LLM post-training.

We present an overview of the ImageEval 2026 shared task on culturally grounded Arabic multimodal evaluation. It includes two tasks: (i) AynVQA, covering spoken visual question answering and image-grounded hallucination detection in English and Modern Standard Arabic (MSA), and (ii) CRAI-Bench, evaluating the cultural accuracy of text-to-image generation. A total of 14 teams participated in the test phase, with 12 teams submitting system description papers. Participating systems used a range of approaches, including zero-shot prompting, fine-tuning of vision-language models, speech-recognition pipelines, ensembling, and score calibration. We describe the task setup, datasets, evaluation procedure, and participating systems, and summarize the main results across the different tracks. All datasets and evaluation scripts from the shared task are released to the research community. The shared task highlights the challenges of culturally grounded multimodal evaluation, particularly for Arabic speech and image-text reasoning.

Clinical artificial intelligence is increasingly embedded in real-world care, yet existing safety mechanisms are poorly suited to reconstructing and learning from individual AI-related errors and near-misses. Aggregate model monitoring can identify performance changes, and traditional patient safety reporting can capture adverse events, but neither is designed to explain how risk emerges across the interaction among AI systems, clinicians, workflows, and institutional controls. We propose AI Morbidity and Mortality (AI M&M), a structured, blameless framework for case-based review of clinical AI failures. The framework combines standardized case intake, evidence preservation and investigator-level reconstruction, tool-in-loop attribution, and corrective-action tracking. Each event is classified across four linked dimensions: Trigger - Mechanism - Clinical Pathway - Corrective Action, separating the condition that exposed a vulnerability from the process that produced risk, its consequence for care, and the remediation assigned. We demonstrate the framework using five illustrative outpatient medication and clinical decision-support cases; two clinician reviewers independently applied all four classification axes and reached agreement across all 20 axis-level classifications. AI M&M is intended to complement, rather than replace, model monitoring, patient safety reporting, and regulatory oversight by converting individual AI-in-workflow failures into actionable institutional learning. Prospective evaluation across institutions, AI systems, and clinical settings is needed.

Tactile sensing is essential for physical interaction in robotics and human--machine systems. However, combining rich tactile information with compact hardware, low cost, and low computational overhead remains challenging. This work presents SpectraTac, a compact, camera-free optical tactile sensor that combines active red--green--blue (RGB) illumination with spatially distributed color sensing. Contact deforms a compliant transparent elastomer and modulates its internal light field, producing spatially differentiated changes in color and intensity. Three distributed color sensors capture these responses as low-dimensional spatio-spectral features, avoiding cameras, imaging optics, and high-dimensional image processing. The device measures 19.2 mm in diameter and 4 mm in height, with a material cost below USD~5. A data-driven decoding framework simultaneously estimates three-dimensional (3D) force and the contact region from the optical measurements. For 3D force prediction, the sensor achieved mean absolute errors (MAEs) of 0.161, 0.164, and 0.429 N along the x-, y-, and z-axes, respectively. The nine-region contact-classification accuracy was 99.9%. We further evaluated real-time 3D force tracking and contact-region-based human--machine interaction through an interactive control task. These results indicate that distributed color-resolved optical sensing offers a compact, low-cost alternative to camera-based tactile sensing for robotics, wearable sensing, and interactive systems.

Logical reasoning with large language models (LLMs) is a critical capability, as it reflects a system's ability to correctly deduce hypotheses from a given context using faithful deductive processes. However, LLM reasoning has often been shown to be sensitive to small surface-level variations in problem formulation, raising questions about whether models truly follow the underlying logical structure. Studying this behavior is challenging because the symbolic components of logical problems, such as operators and predicates, are difficult to systematically manipulate in natural language. We introduce a tool-driven framework for generating controlled, label-preserving edits to logical reasoning problems. Our method operates on symbolic representations of first-order logic and constraint satisfaction problem tasks, enabling targeted modifications to logical operators and other structural components before translating them back into natural language. Using this framework, we evaluate various LLMs under cumulative and individual operator edits and analyze their behavior in response to these changes. Our quantitative and qualitative analyses show that LLM reasoning behavior under controlled operator edits is inconsistent, regardless of model size or family: models sometimes adapt correctly to structural changes but often fail to track their logical consequences. The results from this automated stress test enable an evaluation of language models across different dimensions and help measure the reliability of their reasoning.

Reliable three-dimensional (3D) navigation of magnetically actuated untethered microrobots remains a major barrier to clinical translation. X-ray fluoroscopy is the standard real-time imaging modality for endovascular procedures, but single-plane fluoroscopy provides only a two-dimensional (2D) projection, eliminating depth information and complicating autonomous navigation. Recovering this information through biplane imaging or repeated contrast-enhanced angiography increases procedural complexity, radiation exposure, or contrast burden. Here, we introduce VISTA (Virtual Integration for Spatial Tracking and Autonomy), a digital twin framework enabling contrast-free autonomous navigation under single-plane fluoroscopy. VISTA reconstructs vascular anatomy as a 3D digital twin, discretizes the vessel centerline into navigation milestones, and assigns the detected 2D robot position to the nearest projected milestone. Consecutive milestones define the local vessel orientation used to generate magnetic actuation commands, converting single-plane fluoroscopic observations into topology-constrained navigation states without requiring contrast injection during navigation. VISTA is demonstrated across anatomically distinct vascular phantoms under continuous flow and within the inferior vena cava of a live rat in vivo. Compared with conventional fluoroscopic human-in-the-loop control, VISTA reduced navigation time by up to 62%, corrective actuation commands by up to 98%, and radiation exposure by up to 57%. These results establish VISTA as a digital twin-guided framework for contrast-free autonomous navigation of untethered endovascular microrobots using widely available single-plane fluoroscopy.

Volumetric video enables immersive free viewpoint rendering of dynamic real world scenes, yet existing methods struggle with long sequences and complex motions, often leading to temporal instability and visual artifacts. To address these challenges, we propose \ourname, a Gaussian splatting based framework for volumetric video reconstruction. Our key insight is that explicitly tracking long term complex motion with individual Gaussian primitives is inherently unstable. Instead, we organize Gaussians around time conditioned anchors that localize their spatial and temporal support, thereby reducing long range motion complexity. We further introduce a temporal windowing strategy to activate only anchors relevant to the queried time, which improves scalability and temporal coherence. In addition, to ensure spatial and temporal stability, we design a compact set of multi level anchor features that encode global features, local spatial features, and local temporal features, jointly constraining Gaussian generation. Extensive experiments demonstrate that \ourname \ consistently outperforms prior methods on long sequence volumetric videos with complex motions. Project page: https://github.com/WuJH2001/ATGS.

Single-GPU deployment of 70B-parameter language models on an NVIDIA GPU is constrained by device memory, long-context throughput, and engineering integration cost. We cast single-GPU inference as a budget-aware design problem over these three axes and study how pruning, quantization, and KV-cache compression interact under realistic execution. Controlled ablations show that layer-wise pruning makes weight quantization more robust. KV-cache sparsification complements INT8 KV quantization by reducing memory without hurting decoding speed, while static vector quantizers often conflict with dynamic caching. Guided by these coupling results and explicit budget tracking, we assembled a practical pipeline and compressed a 70B model to about 33 GB, sustained about 57 tokens/s on 10k token prompts on a single A40, and kept absolute accuracy within 5% on common and reasoning benchmarks. We contribute design rules and a reproducible evaluation protocol that jointly report quality, memory, and end-to-end speed, and we provide a foundation for automated pipeline search under realistic single-GPU constraints.

Prediction error is widely used to evaluate nuisance-function estimators in causal inference, but its relationship with causal estimator performance may differ across performance measures. We studied this question in a partially linear model using Monte Carlo simulations. We compared ordinary least squares (OLS), generalized additive models (GAMs), XGBoost, and Double Machine Learning with XGBoost (DML-XGBoost), evaluating nuisance-function prediction error, bias, RMSE, and 95% confidence interval coverage. We also examined a simple joint-error measure based on the absolute cross-product of estimation errors from the exposure and outcome nuisance functions. Across the simulated settings, XGBoost had the lowest RMSE among the non-oracle methods, while DML-XGBoost generally provided better confidence interval coverage. Prediction error did not consistently track causal bias across methods and settings, and the method with the best point-estimation performance did not necessarily have the best confidence interval coverage. The joint-error measure was only weakly associated with causal bias and did not provide a useful standalone measure of causal performance. These results suggest that prediction error is useful for assessing nuisance-function estimation, but it should not be treated as a direct measure of the quality of the resulting causal estimator.

Long-horizon story-driven video generation requires a production agent to coordinate narrative decomposition, state tracking, shot design, prompt construction, rendering, and revision across interdependent scenes. Existing adaptive video systems primarily refine requests or reusable skills, leaving recurring production failures disconnected from persistent, stage-targeted improvements across stories. We introduce CineForge, a self-evolving video-production agent framework that couples CineForge-Produce for video generation with CineForge-Evolve for cross-story policy evolution. CineForge-Produce organizes each source story into typed narrative, character, spatial, and cinematic states, uses them to coordinate asset and clip generation, and records the process as a canonical production trajectory. CineForge-Evolve applies Case-to-Pattern-to-Policy Evolution (CPPE) to review trajectory evidence, consolidate recurrent findings into bounded stage-local patches, and deploy validated updates through structural replay and confidence-controlled paired evaluation. To measure complete story realization, we introduce CineScope, which combines a 100-script CineScope-Data suite with a human-aligned, multiscale CineScope-Metric spanning causal state, directorial orchestration, pacing and resource allocation, and character arc. Across CineScope-Data and two public benchmarks, the evolved CineForge policy improves CineScope-Metric from 4.024 to 4.380, outperforms three long-video baselines with consistent gains under ScriptAgent, and reduces review LLM calls by 37.0% on new stories. These results establish production trajectories as actionable experience for video agents that improve cumulatively across long-form storytelling tasks.

Autoformalization translates informal mathematical theorems into code for proof assistants such as Lean. A central challenge is that current evaluation metrics can accept type-correct but misaligned statements or reject correct statements written in a different formulation. Inspired by Pass@$k$, we propose SA-Pass (Semantic Alignment Pass), which tests formal statements using auxiliary statements called shadows that characterize the intended statement. A generated statement receives full credit only when it compiles, implies each shadow (forward check), and is implied by their conjunction (backward check). We instantiate SA-Pass in ShadowBench, a Lean 4 full autoformalization benchmark of 178 postgraduate- to research-level problems spanning eight mathematical areas. Claude Code (Opus 4.8) with Numina-Lean-Agent reaches $61.8\%$ compile rate and $11.2\%$ SA-Pass. Across outputs generated by six agentic configurations, SA-Pass achieves $98.8\%$ binary agreement with expert judgments. An early version of ShadowBench served as the benchmark for Track 4 of the ICML 2026 AI4Math Challenge.

Modern agent systems assemble capabilities at runtime, and this dynamic composition has recently received a complete formal treat ment in the spatiotemporal-composability calculus, in which a capability is a component carrying a tracked inverse, and agents are assembled as plugins. This plugin form is carried by a single process sharing one context, a carrier that places all components in one physical failure domain, a fault suspends every component at once, and process death interrupts every session the process hosts. This paper shows that neither the modeling nor the calculus binds an agent to one process, the statelessness of the language model keeps all cross-step state outside the model, and the soundness invariant is defined on the state space alone. These observations condense into four lemmas whose premises are the hypotheses of the calculus and the statelessness of language-model inference. On these lemmas this paper constructs Logos, a ROS-like cross process agent harness in which a plugin is a process and the only shared state is an append-only transcript. Eighty sessions resume with no repeated effect after kills placed at the four boundaries of the tool-call cycle, and a same-fault comparison with a single process reference configuration shows one fault interrupting every co-resident session while under the peer-process construction one fault ends at one node.

People read a humanoid robot's motion in social settings not only for the action performed but for the affect conveyed. Motion carrying that affect has so far been generated for human avatars, where style is taken from a reference clip or an emotion word, neither of which can be quantitatively parameterized. We present PAMoR, which turns affect into a measured control parameter: a valence-arousal (V-A) coordinate computed natively on robot kinematics. It is obtained in closed form from postural expansion and movement energy, and these measurements serve directly as generation conditions, with no human annotation. An action prior and two affect priors, trained in a shared latent space, are composed at each denoising step: the action prior fixes what is performed, the affect priors modulate how. Whole-body motion rolls out autoregressively on a 29-DoF Unitree G1 in real time, with action and affect both editable. Generated motion tracks the commanded V-A over its full range while text-to-motion fidelity still matches text-only baselines. In a perceptual study, raters identify the commanded emotion on 0.38 of trials, above both baselines and approaching the 0.44 reported for acted human bodies.

Large-scale vision--language--action (VLA) policies have advanced generalist robot control, yet most remain stimulus-to-action black boxes: actions are exposed, but their explanatory state is not. They provide no native account of three explanatory signals: task progress, the next semantic transition, or local command reliability. Prior work shows that progress and event structure aid long-horizon control and that uncertainty supports monitoring; however, such capabilities are typically added or extracted only after action pretraining. The field therefore lacks a VLA foundation model whose explanatory state is jointly pretrained with control. Drawing on biological sensorimotor organization, in which outcome-sensitive, event-segmented, and probabilistic predictions structure behavior, we introduce LM-X. LM-X learns three directly supervised online signals: return-to-go (RTG) estimates visible progress and state quality; event-to-go (ETG) predicts the action sequence to the next semantic event; and heteroscedastic action-flow variance reports local command reliability. RTG conditions ETG and both condition action generation; uncertainty is estimated inside the action expert, making explanation part of control rather than a post-hoc description. We pretrain LM-X on more than 20,000 hours of heterogeneous real-robot trajectories, including over 1,000 hours of failed rollouts. A controlled gate favors joint over post-hoc training. LM-X achieves 74.1% success on 50 randomized-hard RoboTwin2.0 tasks and 73.5% on seven real-robot tasks, compared with 55.4% and 50.7% for GR00T N1.7. Its signals track progress and regression, anticipate event-scale motion, detect high-error actions, and provide advance failure warning. These results establish LM-X as an explainable VLA foundation model that couples transparent predictive state with stronger generalist control.

Generative video models now synthesize footage nearly indistinguishable from reality. Their promise as interactive tools hinges on fine-grained control of how objects and the camera move over time, yet each existing approach captures only part of this: camera-parameter methods steer the viewpoint but cannot move objects, 2D-trajectory methods act in the image plane and ignore depth and occlusion, and recent 3D methods add geometry but run only offline at a fixed length. In particular, none combines 3D-consistent control of both camera and objects with real-time, streaming generation. Here we show that camera motion, object trajectories, and depth can be unified into a single 3D point-track representation, from which one model performs joint camera and object control, depth editing, and motion transfer in a single forward pass. To learn this interface at scale, we mine in-the-wild video for 3D motion supervision, yielding OpenVidHD-Motion3D, and encode it with a lightweight Geometric Motion Head that plugs into a pretrained video diffusion model. Because this encoder is temporally separable, we distill the model into a causal streaming student that generates arbitrarily long video in four denoising steps at memory independent of length. This unified design surpasses prior camera-only, 2D, and offline-3D methods in motion-control precision while covering modalities they address only in isolation. 4DStreamCtrl runs at 20 FPS on a single high-end GPU for 480p video and stays temporally coherent over hundreds of frames, enabling, to our knowledge, interactive 4D-controllable streaming generation for the first time. More broadly, grounding generation in explicit 3D geometry with efficient causal inference points toward interactive world models with closed-loop spatiotemporal control, from controllable simulators to real-time visual imagination for embodied agents.

Multi-teacher on-policy distillation (MOPD) distills several domain-expert teachers into a single student by minimizing per-domain reverse-KL divergence on the student's own rollouts. Existing approaches typically fix the per-domain data mixture before training, overlooking the fact that different domains converge at substantially different rates: some plateau early while others continue to improve throughout the training budget. A fixed mixture therefore wastes compute on fast-converging domains and undertrains slower-converging ones. To address this, we propose D$^3$-MOPD (Dynamic Domain ScheDuling for MOPD), a zero-overhead scheduler that repurposes the per-domain reverse-KL signal already produced during training to adapt the domain mixture online. Running asynchronously outside the training process, an off-process watcher periodically tracks each domain's KL trajectory, estimates remaining headroom and current improvement rate, and accordingly adjusts the domain sampling ratios without altering the core training loop. Our D$^3$-MOPD scales naturally to arbitrary numbers of domains, and the expected benefit grows as more domains introduce more diverse convergence patterns for the scheduler to exploit. On a Qwen3.6-35B-A3B student distilled from four domain-expert teachers, D$^3$-MOPD closes 97% of the average student-to-teacher performance gap, compared with 63% for vanilla MOPD, reaches the same peak performance with an approximately 3$\times$ reduction in rollout steps, and surpasses the specialist teachers on three of seven benchmarks.

While text-based hallucination detection is well studied, reference-free detection of factual alterations in speech remains underexplored, especially for low-resource languages. Our spoken benchmark comprises 12,013 English, Russian, and Kazakh news samples with three synthetic alteration types and three severity levels, pairing source articles with rewrites as text, synthesized audio, and ASR transcripts. We add 290 fact-checked misinformation items collected in Russian (225) and Kazakh (65), translated into the other language and rendered through the same TTS-ASR pipeline. We evaluate fine-tuned multilingual encoders and zero-shot multimodal decoders on text, transcripts, and audio. Detectors receive only target inputs without source articles or external evidence; the task evaluates reference-free classification rather than evidence-grounded verification. Encoder degradation from source text to transcripts generally tracks per-language ASR error on the binary task. Among decoders, only Gemma-3n exceeds the binary majority-class baseline in macro-F1, on transcripts only; the other four fall below their respective baselines. Comparisons between audio and transcripts are confounded by differences in evaluation coverage and class balance. Synthetic-trained detectors achieve 0.82--0.88 macro-F1 on real-world misinformation source text; Russian provenance analysis reveals veracity-related and model-dependent machine-style signals, a key confound in synthetic hallucination benchmarks.

With the advent of Large Language Models and its instruction following capabilities a promising application is the task of summarization. Within this domain of task the extractive sub-task of clinical protocolling has emerged as a topic of particular interest as it can significantly reduce the downtime and protocolling burden of health-care workers thus enabling them to focus on their core work helping humans. A further step towards automation is the direct generation of clinical notes from speech without intermediate transcripts, reducing processing time while preserving information such as coughing or other paralinguistic cues that may be lost in transcript-based systems. To this end, we present KIT's submission to this years BeTraC challenge in the lightweight track. Our main contribution is a scalable data augmentation pipeline that unifies heterogeneous medical dialogue datasets through synthetic speech generation and automatically generated SOAP supervision, enabling robust adaptation of a speech foundation model for end-to-end speech-to-SOAP generation.

Whittle index policies offer a scalable method for restless multi-armed bandits, but under partial observability even determining the indifference subsidy at a single belief requires solving an infinite-horizon belief-state problem with no closed-form value function. Liu [10] addresses this difficulty by linearizing the unknown decision boundary, leading to a linear system and a closed-form approximate Whittle index. However, the resulting threshold uses only a one-step active--passive comparison and does not account for longer-horizon continuation values. We extend this framework to a \emph{$t$-step lookahead threshold policy}. For each subsidy $m$, the threshold is defined by the active-minus-passive advantage under $t$-step finite-horizon value iteration. At $t=1$, the threshold is $m$-independent and recovers the linear threshold of Liu [10]; for $t>1$, it becomes subsidy-dependent through the induced first-crossing structure and tracks the exact decision boundary more closely. The proposed algorithm does not require indexability as an input and includes an indexability verification. Under the original Whittle indexability, we prove that the $t$-step approximate Whittle index converges geometrically to the exact Whittle index, $$|\widehat W_t(ω)-W(ω)|=O(β^t).$$ Numerically, all 2,715 tested three-state instances are verified as indexable according to the proposed criterion. The P95 index error decreases from $2.18\times10^{-2}$ at $t=1$ to $8.93\times10^{-4}$ at $t=8$. In an exact-comparable instance with $β=0.9999$, $t=2$ already recovers the exact Whittle-index ordering. Moderate-depth threshold policies also outperform the one-step baseline and remain close to the optimal dynamic-programming benchmark, while runtime grows mildly with $t$.