Search research

A recent line of work measures causal emergence in reinforcement learning agents through Integrated Information Decomposition, reporting that $Φ_r$ grows with training and tracks reward improvement. For active inference, this raises the question of how reward-free predictive organization relates to such information-theoretic signatures. I test this within an active inference agent whose architecture separates a fast perception latent $z$ from a slow global latent $g$, where $g$ is driven by prediction error and structurally decoupled from policy gradients. In a reward-free environmental regime-switching protocol, $Φ_r$ concentrates in $g$; its aggregate magnitude is largely architectural and decreases with training. The substantive effect of learning becomes legible only at the atom-compositional level: decoupling flips sign from negative to positive and becomes regime-invariant under environmental change, while downward causation carries the regime-dependent adjustment. These results identify $g$ as the architectural locus of $Φ_r$-relevant temporal organization in an active inference agent, and argue against reading scalar $Φ_r$ as a direct index of learned integration.

Laboratory automation accelerates discovery, yet its adoption is constrained by the high cost, proprietary design, and limited remote supervisability of commercial liquid-handling systems. This work presents RAINBOT\textsuperscript{TM}, a low-cost, openly reproducible liquid-handling robot built by converting a consumer-grade Cartesian 3D printer (Elegoo Neptune 4 Max). The printer extruder is replaced by a precision single-channel pipette actuated through the printer's own G-code-driven X--Y--Z gantry, with plunger and tip-eject motions effected by two compact linear actuators under Python control. To make experiments transparent and remotely supervisable, a browser-based digital twin is implemented to synchronise bidirectionally with the physical platform, mirroring kinematics and pipetting states in real time and exposing remote monitoring, intervention, and an emergency stop from any web browser. As a proof of concept, RAINBOT\textsuperscript{TM} performed sequential exchanges of differently coloured aqueous solutions while an integrated colour sensor quantified the resulting mixtures; measured red, yellow, and blue (RYB) responses agreed with expected mixing behaviour to within a mean absolute error of two percentage points, validating correct execution and real-time tracking. Closing the loop, the platform is coupled to the CEID\textsuperscript{TM} (Cooperative Explorer for Inverse Design) framework, which recasts experimentation from iterative manual guessing into a goal-directed inverse-design search while keeping a human in the loop. The complete hardware costs under US$1300, which is roughly an order of magnitude below entry-level commercial handlers, thereby establishing an accessible physical--virtual framework for self-driving laboratory automation.

Natural-language autoencoders score explanations of hidden activations by reconstruction: an explanation is deemed faithful if the activation can be regenerated from it. The test is structurally insensitive to individual false claims: if flipping a claim does not change the reconstruction, the claim is never penalized. We show the test is passed in two ways, neither faithful. On a released Qwen-2.5-7B verbalizer, explanations reconstruct well above chance while ~2% of specific claims are reconstruction-dependent, so the score tracks gist, not specific facts. Under exact synthetic ground truth, the standard recipe develops co-adapted private codes (false wording the reconstruction depends on) in 5/5 runs, and fixes that leave the target model unchanged do not help. We contribute two audit protocols, the grounded-vs-true cross and the evaluator swap, and RECAP (Readable Encodings via Co-trained Auxiliary Predictors): linear heads trained alongside the target model to keep designated content decodable. On RECAP-trained sandbox models, fresh verbalizers state the designated content truly and the codes vanish, at a +0.001-nat cost. This replicates on a pretrained Pythia-160M: the content becomes reliably probe-decodable, though a fresh verbalizer conveys it only in part (truth 0.44-0.46 vs a near-zero control). For interpretability, high reconstruction does not certify individual claims. For AI safety, RECAP makes designated internal content independently checkable against probes rather than asserted by prose a model can game: an independent probe scores the verbalizer's true claims above its false ones (AUC 0.96, vs 0.82 without RECAP). Against an adversary that edits an explanation to maximize the reconstruction score while lying (suppressing ~87% of its lie penalty), the RECAP probe still flags the lies (AUC 0.95) while the control probe collapses to chance (0.51).

Bayesian online learning promises uncertainty-aware prediction on data streams, but its performance hinges on inferential choices, including learning rates, prior distributions and variational families, which are usually fixed before seeing the stream. We address this by treating Bayesian update rules as experts and aggregating the Bayesian experts according to sequential predictive losses. We prove that the resulting aggregate competes with the best expert in hindsight at an aggregation cost determined by how each expert's per-round performance is evaluated. We instantiate the framework in online conformal inference and Gaussian process regression. The conformal inference application yields a smoothed Bayesian counterpart of adaptive conformal inference with long-run randomized coverage, while the Gaussian process application gives an oracle inequality in cumulative predictive Kullback-Leibler risk and adaptation to unknown Hölder smoothness up to logarithmic factors. Experiments show that the aggregate tracks strong experts without oracle expert selection.

Machine learning models for medical image analysis typically lack a reliable measure of confidence, limiting their use in ambiguous or atypical cases. Here we show that Monte Carlo dropout, applied to a multi-task chest-radiograph classifier (eight thoracic findings, 137,593 training images), provides an epistemic uncertainty signal that tracks generalisation across training-set scales and flags confident yet error-prone predictions. Adding this signal to the point prediction raised error-detection AUROC from 0.74 to 0.77 ($Δ$AUROC +0.023, 95% CI [+0.014, +0.033]). In a controlled 2x2 factorial experiment, a clinical-decision-support agent exploited this uncertainty only when it was delivered as a binary error-risk flag rather than as raw scores, cutting confident misdiagnoses on unreliable findings from 8.5% to 2.7%. Epistemic uncertainty estimation thus carries decision-relevant information beyond point predictions, but its value for downstream agents depends on how it is communicated.

As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become critical for enabling general-purpose AI assistants and automating complex workspace workflows. In this paper, we introduce DocOps, a deterministically verifiable evaluation framework underpinned by a hierarchical taxonomy that deconstructs document operations inspired by real-world practices into atomic dimensions and escalating workflow complexities. Based on DocOps, we systematically evaluate representative closed- and open-source models across various agentic harnesses, revealing that even the most advanced frontier configurations still exhibit profound limitations when handling highly coupled, long-range tasks. Furthermore, a fine-grained analysis of existing agents' manipulation behaviors uncovers 3 key failure modes: long-term state tracking collapse, shallow semantic verification, and destructive editing of structural metadata. Ultimately, our work exposes the capability boundaries of agents in maintaining global document consistency, shedding light on the future design of robust, non-destructive agents for complex digital ecosystems.

Medical image segmentation models often report high benchmark accuracy under ideal imaging conditions, yet their failures under clinical degradation can be quiet: sensor noise, patient motion, low- resolution acquisition, and contrast variability may all alter model behavior without producing an obvious warning. We present a reproducible framework for evaluating uncertainty-aware segmentation under con- trolled clinical degradation. Our experiments use a synthetic multimodal brain tumor MRI cohort generated with a biophysical phantom simulator that follows the BraTS protocol. We train U-Net and Attention U-Net baselines for multi-class tumor sub-region segmentation and augment both models with Monte Carlo dropout to estimate per-voxel uncertainty. Across eight clinically motivated corruption types at five severity levels, we measure segmentation accuracy, calibration, failure detection, and selective prediction coverage. On clean data, Attention U-Net achieves a whole-tumor Dice of 0.990; under severe Gaussian noise, its performance falls to 0.089. Predictive uncertainty rises with degradation and tracks segmentation error (Pearson r = 0.53 under severity-3 Gaussian noise), allowing us to flag failures with an AUROC of 0.843. These results argue for uncertainty-aware inference as a practical safety layer in physician-in-the-loop radiology workflows. We release the code, trained models, and evaluation protocol to support direct reproduction.

Geo-spatial rasters of building footprint area are useful for a variety of tasks, such as monitoring urbanization, improving energy efficiency, and tracking greenhouse gas emissions. There are now multiple global building raster datasets, however there lacks an independent, comprehensive, and fair assessment of their accuracy. In this work, we evaluate the accuracy of four major global building products: Global Human Settlement Layer (GHSL), Microsoft's TEMPO (TEMPO), The Global Building Atlas (GBA), and Overture. As ground truth for assessing their accuracy, we use ORBITaL-Net, a globally diverse dataset of manually labeled building footprints. To ensure fairness, we evaluate products on grids of multiple spatial resolutions, and several conventional performance metrics. Our results indicate that either GBA or TEMPO generally achieves the highest overall accuracy, depending upon the particular evaluation criteria. We also stratify the accuracy of each product by several factors: geographic location, population density, and income groups. The results reveal that product accuracy can sometimes vary significantly with respect to these factors. Notably, all products are significantly less accurate in Africa and Asia. Most products also suffer significant accuracy reduction in high-density urban areas.

The HIPE-2026 shared task introduces person-place relation extraction from multilingual historical newspapers as a new evaluation track, classifying the at and isAt relations between pre-annotated person and location mentions in English, French, and German. Motivated by the cost of processing historical archives at scale, our team (DS@GT HIPE, team 2 in the official results) investigates how far a lightweight, interpretable system can go without any pretrained language model at the relation classification stage. Our approach builds a document-level graph from dependency parses, extracts proximity-based and part-of-speech features for each entity pair, and classifies them with small scikit-learn ensembles or compact Graph Attention Networks, keeping every submitted run under 847K parameters. On the official evaluation (Test A, the newspaper test set), our best run reached a macro recall of 0.5142, ranking 3rd on the Efficiency profile while placing mid-table on Accuracy among the 17 participating teams. Two findings stand out. First, minimum character distance alone captures most of the classification signal; adding further engineered features yields inconsistent gains and sometimes degrades performance, echoing prior evidence that argument distance dominates relation extraction. Second, document-grouped cross-validation is essential on this corpus: pair-level splits inflate scores by 25-37 percentage points because entity mentions recur across documents, a data-leakage effect that grouped cross-validation removes.

Fully actuated unmanned aerial vehicles (UAVs) are usually certified through rank conditions on a control-allocation matrix or through free-flight tracking performance. For aerial physical interaction, this certification may be incomplete. During sustained contact, part of the available wrench is consumed by the interaction task, and only the residual wrench remains available for stabilization, disturbance rejection, and maneuvering. This paper introduces a control-theoretic framework for \emph{contact-persistent full actuation}. A rigid-body model on $\R^{3}\times\SO\left(3\right)$ is combined with a morphology-dependent wrench map that captures fixed-tilt, variable-tilt, coaxial, and overactuated multirotor architectures. We define feasible wrench sets under actuator limits, residual wrench sets under task loading, and residual authority margins that strengthen the usual rank-based notion of full actuation. The main result shows that contact-persistent full actuation is equivalent to interiority of the task wrench in the constrained feasible wrench polytope, and that the residual authority radius is exactly the distance to the polytope boundary. We further introduce a signed residual-margin certificate for infeasible and boundary cases, a slack-maximizing allocation certificate, and a robust implementability condition that can be used as a margin-aware safety filter. Numerical evaluation on an abstract tilted hexarotor shows that full row rank alone does not imply feasible contact operation. Intermediate tilt angles preserve residual authority during pushing, whereas small or excessive tilts fail because of lateral-force deficiency or hover-margin loss.

Almost every piece of recorded music you have ever heard was modified before it reached you; commercial releases rarely spring fully-formed from the mind of a musician. Despite the promise of music generation models for one-shot output, such fine-grained iterative refinement workflows are a complementary problem, and largely out of their reach. There is also a gap for musicians: while they can express what they want to hear, not all have the facility with studio production tools to implement the complex set of actions needed to realize these intuitions. We formalize this task as agentic post-production, wherein individual aspects of a song are targeted, refined, and combined into a final track. We argue the bottleneck is data: existing corpora do not reflect how realistic post-production chains map onto the vocabulary musicians and engineers actually use. We argue there is a language for modifying recorded music that is dense, consistent, and learnable. We introduce the Rule-based Instructions for Music Editing (RIME) framework, which generates realistic paired edit-instruction data from any baseline music dataset grounded in canonical methods, design patterns, and constraints derived from real production workflows. RIME leverages POEMS, a new toolkit that combines stem separation, mixing, and common studio effects for use by multimodal agents. We use RIME and POEMS to generate 3,000 pairs of edit instructions and ground truth audio, and use this data to evaluate existing multimodal LLMs as agents on this task, showing persistent challenges in current models' post-production capabilities. We also demonstrate RIME's ability to improve post-production agent performance via supervised fine-tuning. We see RIME as an early step toward iterative musical agents, collaborative systems that could transform music production much as interactive coding agents have reshaped software engineering.

Cognitive remediation tasks often require patients to perform structured actions involving object manipulation and sequential reasoning. For patients diagnosed with schizophrenia, these tasks are crucial for addressing severe cognitive deficits. However, evaluating the correctness of these physical actions generally relies on manual observation by clinicians, which introduces subjectivity and limits the scalability of therapeutic interventions. In this paper, we propose an automated framework based on Vision-Language Models for action verification in cognitive remediation tasks tailored for schizophrenia rehabilitation. The proposed system relies on a camera-monitored tabletop environment composed of structured miniature scenes including roads, a roundabout, a park, and toy vehicles. Patients receive audio instructions describing goal-oriented spatial actions to perform by manipulating a toy vehicle. These interactive physical activities are specifically designed to stimulate targeted cognitive functions, such as sustained attention, motor coordination, spatial navigation, and cognitive flexibility. To verify the correctness of the performed actions without requiring continuous clinical oversight, the system analyzes the video feed tracking the patient's hand and toy movements. A fine-tuned Vision-Language Model interprets the recorded video sequences and generates semantic descriptions of the observed activities, enabling high-level verification of the executed actions with respect to the initial textual instructions. A dedicated dataset of 4634 tabletop cognitive remediation video scenarios was collected to evaluate the proposed approach. Experimental results demonstrate that our specialized framework effectively bridges low-level physical telemetry with high-level clinical feedback, presenting a scalable and objective solution for advanced cognitive rehabilitation.

Understanding animal behavior at an algorithmic level -- what animals attend to, how they form internal models and plans, and how this maps to action -- remains a central challenge in neuroscience and ethology. Data-driven generative models offer a path toward this understanding. We introduce a framework for training agent-centric autoregressive models of animal behavior from tracked pose, applicable to single animals and to groups in which each agent senses and responds to its conspecifics. Our models input egocentric sensory observations and output egocentric movements, mirroring the biological constraint that animals observe and act on the world from their own reference frame. Social behavior emerges from agents independently sensing and responding to one another. This agent-centric formulation requires managing many parallel representations of the same data, along with ML-specific transformations like discretization. We release a general-purpose library focused on the composable sequences of operations that translate between these representations. We show that trained models capture the distribution of social behavior in groups of courting Drosophila, and our library includes quantitative tools for measuring fit. We demonstrate how the library supports systematic comparison across input and output representations and that it adapts straightforwardly to a new domain.

Low-rank adaptation introduces a static learned update applied identically to every input. The update provides task-level adaptation but does not explicitly represent token-level or instance-level state variation. A family of adapters is proposed that introduces selective state-space control at two complementary granularities. At the token level, MaLoRA (Mamba-modulated low-rank adaptation) makes the adapter's scaling factor a dynamic input-dependent function with recurrent state across tokens, in contrast to the stateless modulators of prior work. The token-level adapter improves over low-rank adaptation. On the other hand, it differentiates tokens by structural role but not by contextual relevance, which motivates placing evidence selection at the context level. At the context level, MaRA (Mamba Retrieval Adapter) tracks cross-segment reasoning state and selects the segments most relevant to the query. State-space controlled retrieval of approximately three million parameters exceeds an eight-billion-parameter dense retriever on supporting-paragraph recall. Although base models perform poorly on the task without adaptation (14 to 25 F1), MaRA recovers the evidence relevance latent in their representations. Across three frozen backbones and two multi-hop reasoning benchmarks, the end-to-end family improves reasoning accuracy on every cell of the 3-by-2 grid, by +6.4 F1 (+10.0% relative) on average over the LoRA baseline.

Real-world spatial intelligence requires agents to understand scenes from continuous video streams, where objects move, persist, disappear, and reappear over time. While recent spatial foundation models have enabled generalizable feed-forward 3D reconstruction, most streaming methods remain geometry-centric and lack temporally consistent object-level understanding. Meanwhile, existing semantic reconstruction and 3D-aware vision-language methods largely rely on externally extracted 2D semantic cues or loosely coupled geometry inputs, limiting unified geometry-instance learning in long dynamic scenes. In this paper, we propose IGGT4D, a streaming instance-grounded geometry Transformer for online 4D scene understanding. IGGT4D processes video frames sequentially, reuses historical context through causal spatial-temporal modeling, and incrementally updates a unified representation of camera motion, geometry, and object identity. This enables long-sequence feed-forward reconstruction with geometry-instance consistency in dynamic environments. To address the lack of high-quality 4D supervision, we further construct InsScene4D-147K, a large-scale dataset spanning real/synthetic and static/dynamic scenes, with RGB images, depth, poses, and temporally consistent instance masks generated by an automated geometry-guided annotation pipeline. Experiments on 3D reconstruction, pose estimation, instance spatial tracking, and open-vocabulary segmentation demonstrate that IGGT4D outperforms existing streaming baselines while maintaining scalable online inference for long dynamic sequences.

This full paper in the research-to-practice track presents methods for assessing student teams in tabletop exercises (TTXs). TTXs enable learner teams to prepare for workplace tasks and practice crisis responses, such as resolving cybersecurity incidents. While assessment is essential for determining how well teams achieve learning objectives, the complex, open-ended nature of TTXs often leads to delayed or incomplete feedback. TTX learning platforms can record teams' actions and communication; yet, leveraging these data to assess performance is underexplored. To address this gap, we compared two post-TTX team assessment methods -- clustering and large language models (LLMs) -- using an original dataset from 81 participants across two countries. We evaluated these methods against instructor-assigned scores based on standardized rubrics. Clustering grouped teams that approached TTX tasks similarly, enabling instructors to deliver faster, targeted feedback to teams within a cluster. This method was valid and reliable, with low computational requirements. LLMs used the standardized rubrics to assess teams' communication. While GPT-4o frequently disagreed with instructor scores, GPT-5.2 demonstrated considerably lower error. The researched methods have been integrated into INJECT, an open-source TTX learning platform, to support scalability and teaching practice. To encourage community adoption, we publicly share all datasets, software tools, and a full-fledged TTX scenario.

Reconstructing animatable 3D human avatars from monocular video is a fundamental problem in computer vision with broad applications in AR/VR and digital content creation. Existing approaches typically couple parametric body models with neural rendering or 3D Gaussian splatting and optimize all body regions jointly from short videos, which often degrades fidelity in the visible areas. To overcome this limitation, we introduce FlexiAvatar, a unified framework that explicitly optimizes only the visible body regions, effectively eliminating artifacts arising from unobserved limbs. Our method integrates occlusion-robust SMPL-X tracking with part-specific residual refinement to capture high-frequency geometric and appearance details. To complete entirely unseen regions (e.g., back views), we leverage a diffusion-based approach to generate texture consistent with the observed appearance. Experiments on full-body (NeuMan, ZJU-MoCap, WildAvatar), upper/half-body (talk-show clips), and head-only (INSTA) inputs show that FlexiAvatar delivers consistently higher reconstruction quality, outperforming state-of-the-art methods by an average PSNR improvement of approximately 3% across datasets. Finally, by restricting optimization to observed regions, our method reduces the effective number of Gaussians that must be optimized and rendered, leading to reduced runtime and memory overhead in partial-visibility scenarios.

Infrared small target detection (ISTD) remains challenging because tiny, low-contrast targets are easily overwhelmed by clutter, noise, or occlusion. Conventional single-frame and multi-frame detectors rely on bounding-box supervision, which specifies final target locations but offers little explicit guidance for prioritizing candidate regions or preserving weak-target evidence before localization. Task-driven visual search offers such guidance: top-down goals and visual evidence jointly form a spatial priority map that ranks candidate locations. Building on this principle, we propose Gaze-DETR, a bio-inspired detector that learns an internal priority map before localization. First, a priority head predicts a normalized priority map from image features. Second, Residual Priority-Guided Feature Modulation (RPFM) enhances high-priority responses while retaining multi-scale features. Finally, Priority-Guided Anchor Query Injection (PAQI) converts high-priority locations into decoder anchor queries. We train the priority head using three supervision schemes: box-derived Gaussian maps; real-gaze maps constructed from fixation-density maps; and transferred pseudo-gaze maps learned from gaze--box relations in paired annotations and applied to Anti-UAV410 training boxes. To support the latter two schemes, we construct TIR-UAV120-Gaze with paired detection and task-driven eye-tracking annotations. On TIR-UAV120-Gaze, Gaze-DETR achieves 85.76 mAP$_{50}$ and 88.77 F1 with box-derived supervision, and 86.18 mAP$_{50}$ and 89.00 F1 with real-gaze supervision. On Anti-UAV410, it achieves 87.06 mAP$_{50}$ and 90.90 F1 with box-derived supervision, and 87.08 mAP$_{50}$ and 90.43 F1 with transferred pseudo-gaze supervision. These results show that explicit spatial-priority learning provides pre-localization guidance complementary to bounding-box supervision across annotation settings and costs.

Personal AI is moving beyond chat-only interaction toward continuous services that span phones, cars, homes, wearables, cameras, and tools. In this setting, memory cannot remain a cache of prior conversations. It should serve as a continuity and governance substrate: preserving durable user state, grounding answers in multimodal and device evidence, supporting correction and forgetting, bounding policy evolution, and remaining deployable under latency, cost, privacy, and edge-cloud constraints. This technical report presents Mi-Memory, a lifecycle memory framework for Personal AI organized around four roles: Structure, Expansion, Evolution, and Deployment. A shared audit contract links these roles through four recurring artifact families: typed evidence payloads preserve source identity and provenance, diagnostic traces localize evidence loss across the serving pipeline, strategy artifacts make memory-policy changes explicit, and gate/rollback records bound accepted evolution. MiMemory instantiates the roles through MemStack, MemSense/MemFuse, D$^{2}$ACCI/E$^{2}$MEND, and LiteMem. In controlled-reference Structure evaluations, MemStack reaches 93.59%, 57.24%, and 87.47% on LoCoMo, PersonaMem-V2, and LongMemEval, respectively; other tracks report module-level, preliminary/internal, transfer-feasibility, or design-only evidence with explicit boundaries. MiMemory is a step toward auditable, evidence-gated, and deployment-aware memory systems for Personal AI. Project homepage: https://darwin-agent.github.io/Mi-Memory/ .

Forecasting under real-world conditions is inherently non-stationary, as the conditional distribution of future observations evolves over time. Recent test-time adaptive sequence models address this challenge by updating internal states during inference, but tie adaptation to instantaneous prediction errors or surprise. This coupling can conflate persistent distribution shift with stochastic innovations, leading to unnecessary updates and inefficient adaptation. We introduce Black-Mamba, a test-time adaptive forecasting architecture that formulates online adaptation as evidence-gated state tracking under distribution drift. The model augments a base predictor with a dynamic memory updated when temporally accumulated surprisal provides sufficient evidence of a regime change. This turns adaptation into a selective, event-driven process rather than a continuous one. Across multiple forecasting benchmarks with non-stationary dynamics, Black-Mamba achieves competitive or improved predictive performance compared to existing test-time adaptation methods while significantly reducing the number of memory updates during inference. Together with mathematical analysis and biological evidence, these results suggest that accumulated surprisal provides a principled signal for distinguishing persistent drift from transient noise, yielding more efficient and robust adaptation.

Kernel-based alignment of CLIP toward a vision centric teacher such as DINOv2 (KUEA) improves CLIP's visual representations while preserving text-encoder compatibility, using a fixed trade-off weight tuned on curated ImageNet-1K. We ask whether this transfers to noisy, web-scale data (CC12M) and find that it does not: the alignment term's weighted contribution falls to about 0.2% of the clean term, so under any fixed weight its gradient is effectively inert. We introduce KALE, a loss-equilibration controller that tracks both losses and adaptively rescales the alignment weight toward a target ratio, restoring the signal with no per-dataset tuning; reaching balance requires increasing the weight by roughly four orders of magnitude, and the required value is configuration-dependent, so no fixed scalar suffices. We characterize the resulting regime: a bounded high learning rate and a decaying schedule with a moderate floor are needed for stability, and the controller equilibrates rather than diverging. On a 3.3M-image CC12M subset, the aligned model preserves image-text retrieval and reproducibly improves SVHN linear probing; zero-shot improves by +2.00 over CLIP on the standard 11-dataset average, exceeding KUEA's +1.29. We report all results with explicit run-to-run variance and base our conclusions on the metrics that are stable across runs.

Large language models leak parametric knowledge of what followed a historical date into decision tasks indexed by that date -- not necessarily a lookup of the realized outcome, but knowledge of the period all the same. Existence is settled; what users lack is a cheap way to audit a given model. We present HindsightBench, a black-box audit protocol that profiles parametric hindsight in any time-indexed LLM decision task at probe-level cost (no backtests, no logprobs, no corpus access). It chains a four-arm date-manipulation matrix (revealed/date-only/masked/transplanted), dual memory probes (date recovery; outcome recall), and six metrics -- trigger strength, transplant effect, post-cutoff placebo, recoverability, behaviorally effective cutoff, and recall-accuracy dissociation -- with explicit gates where identifiability is data-dependent. Applied to 15 models from seven vendors on a 258-node vintage-correct macro panel, it yields three patterns: (i) the date-trigger reflex is not a scale phenomenon -- it tracks training recency, though what installs it is not identified here: absent across every 2024 open-weight row where it is measurable, including a 70B tier with cutoff-aligned recall propensity, present in every tested 2026-generation model, and switching on within one vendor lineage (Qwen3 -> Qwen3.6) in the same MoE family at ~3B active; (ii) effective cutoffs span 22 months across vendors and precede vendor-reported dates by up to eight months, invalidating calendar-window placebos; (iii) results are not invariant to serving -- BF16 serving of an FP8-referenced model breaks the trigger estimate's stability while AWQ-INT4 preserves it, and a provider-locked reasoning regime makes one probe non-convergent -- so the protocol pins quantization and thinking regime as part of its contract. We release the panel, preregistrations, audit rows, transcripts, and one-command regeneration.

World Action Models (WAMs) offer a promising paradigm for robotic manipulation by jointly modeling visual state transitions and robot actions. However, existing WAMs are constrained by limited temporal context, coarse episode-level language supervision, and predominantly text-only conditioning, which hinder task-progress tracking and fine-grained language-video-action grounding while limiting visual-context reasoning and cross-embodiment transfer. In this paper, we introduce WorldScape Policy 2.0, a controllable WAM with reasoning-augmented long short-term memory. Its causal short-term visual memory supplies recent observations as DiT prefill to preserve local interaction dynamics, while its long short-term event memory organizes historical VLM outputs into global-history, local-active, and event-boundary representations for progress-aware retrieval. The retrieved history augments perception and autoregressively generated planning tokens, yielding an implicit subgoal condition for autonomous planning; semantic forcing further transfers event-level instruction semantics into this latent planning pathway. To establish fine-grained multimodal controllability, we construct ManipEvent-5M, an event-grounded embodied pretraining dataset containing nearly 5 million event segments with aligned action trajectories, episode-level task instructions, segment-level subtask captions, goal images, and video demonstrations. These designs provide a unified interface for autonomous planning from high-level instructions and controllable execution from fine-grained text, goal-image, or video-context prompts. Experiments in both simulation and real-world platforms demonstrate superior capabilities in long-horizon autonomous planning, fine-grained instruction following and in-context adaptation.

In legged locomotion, divergent components of motion (DCMs) have emerged as characteristic states for balance control. They isolate the unstable mode of the dynamics but, in existing formulations, apply only to reduced models such as the linear inverted pendulum. In this study, we show how DCMs can be more generally formulated as Koopman eigenfunctions. Whereas Koopman analysis typically targets eigenvalues near zero, which capture conserved or slowly varying quantities, our investigation leads us to deliberately search for unstable eigenpairs with large eigenvalues. The resulting Koopman DCMs are data-driven observables trained using only real-robot data. On a real biped, DCMs learned from one hour of robot data improve tracking of reference walking patterns. We further show how learned DCMs provide state-based viability constraints when combined with model predictive control.

Behavior Trees (BTs) are widely adopted for complex task execution in robotics, providing modular, reactive control but lacking formal guarantees. However, existing correct-by-construction synthesis from Linear Temporal Logic (LTL) cannot express quantitative timing constraints. This letter synthesizes correct-by-construction BTs from Signal Temporal Logic (STL) specifications. The workspace is modeled as a timed transition system and abstracted into a zone graph, and an augmented state space tracking both logical progress and timing constraints is introduced. A hierarchical fixed-point algorithm computes winning sets for an STL fragment encompassing safety, reachability, response, recurrence, and persistence, yielding BT subtrees with a runtime constraint function. Correctness guarantees are proven and complexity bounds are derived. Simulations demonstrate specification satisfaction with strictly positive robustness, and a physical quadrotor experiment with six STL specifications validates practical deployability.

A graph foundation model generalizes across graph domains by mapping every input into one shared representation before any task reasoning. We call this map the alignment layer, the component that separates a graph foundation model from a graph neural network, and we show it is a distinct attack surface that prior work has not studied. We attack it at inference time, with no access to training, on six public models spanning spectral tokenizers, text embedding spaces, and a discrete codebook. A directed representation-space perturbation collapses every model, but at a budget comparable to the representation norm a plain graph network also needs, with one exception: OpenGraph, whose spectral tokenizer collapses at a fifth of that budget, an alignment-specific fragility a plain network does not share and which a same-representation control traces to the tokenizer rather than the decoder. A realizable input-space attack that edits edges, features, or text removes at least half the correct predictions on three of the six models at peak. How much of this fragility an input-access attacker realizes tracks how directly the decoder reads the representation, and not the clean accuracy a task leaves; we measure this carrier gain structurally from the decoder's local Lipschitz sensitivity, and report clean-accuracy headroom as a within-model ordering heuristic that does not survive on realizable attacks.

Preference over model-generated emotion descriptions is emerging as a standard evaluation metric for multimodal emotion understanding, exemplified by the MER2026 MER-Prefer track on EmoPrefer. Such benchmarks assume that predicting the preferred description requires grounded cross-modal understanding of the video. We conduct a systematic shortcut audit of EmoPrefer using content-blind probes. A simple logistic regression using only description length and generator identity, without processing the text, video, or audio, performs comparably to LoRA-finetuned 7B text and audio-visual judges (65.8 versus 66.8 WAF on EmoPrefer-V2). Generator identity is recoverable from description text with 99.5 percent accuracy, every candidate pair contrasts two distinct generators, and the human preference labels agree with a fold-exclusive per-generator win-rate prior on 66 percent of the evaluated pairs. When the human label conflicts with this prior, trained judges still follow the style prior on 63 to 80 percent of the pairs. On a length-matched subset that neutralizes verbosity bias, the tested media configurations yield no statistically significant improvement, while an ODIN-inspired diagnostic that decouples the style shortcut leaves its content head near chance. These results do not imply that human preferences are inherently stylistic or that the descriptions contain no emotional information. Instead, they show that the current scores can be reached without verifying either description against the video. We recommend source-balanced pairing, strict length control, counter-stereotypical sliced reporting, and multi-annotator consensus for future cross-generator evaluations. Code is available at https://github.com/jiabingyang01/EmoPrefer-Audit.

Robotic grasping requires accurate coordination between visual perception, object localization, inverse kinematics, and hand control. However, when movements planned in simulation are executed on a physical robot, the sim-to-real gap can cause small positioning errors that prevent successful grasping. In our previous work, we introduced a low-cost haptic calibration method that improved 2D reaching accuracy of the humanoid robot NICO. In this paper, we extend this approach from reaching to tabletop object grasping by adding YOLO-based object and hand detection, stereo vision-based localization using the robot's built-in low-resolution fisheye cameras, and task-specific corrections for grasp execution. Together, these components form a novel calibration-based grasping pipeline that does not require RGB-D cameras, motion capture, or external tracking systems. We also implemented a visual feedback model that aligns the robot hand with the detected object before grasping. Our results show that the fully nonlinear calibration model achieved the best performance inside the calibrated area, while the visual feedback model achieved the highest overall grasping success across the full tabletop workspace.

Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution. While single-turn safety mechanisms are relatively mature, extended interactions reveal structural vulnerabilities where initial alignment degrades over time. This paper empirically characterizes two observed failure modes across multiple state-of-the-art LLMs: Safety Drift, the gradual erosion of declared safety intent leading to constraint-violating actions (e.g., textual refusal followed by reconnaissance and unsafe execution), and Operational Hallucination, persistent repetitive tool calls indicative of flawed state perception (e.g., livelocks even in legitimate tasks). Through controlled multi-turn evaluation on high-stakes ethical dilemmas, malicious requests, and benign controls, we quantify these phenomena using declaration-action gap and livelock metrics, demonstrating their cross-model prevalence under direct execution protocols. Root-cause analysis attributes the instabilities to the decoupling of reasoning context from execution state in current agent loops. We propose an Action-Aware Supervision Layer - a lightweight, plug-and-play architectural blueprint incorporating intent-action consistency checks, runtime state tracking, and forced termination primitives. Post-hoc simulation on captured failure trajectories shows the layer can intercept observed violations without false positives on benign cases. This work advances agent reliability by shifting focus from linguistic safeguards to enforceable architectural mechanisms for responsible agentic AI.

Dynamic object segmentation plays a critical role in many visual applications such as static scene reconstruction from dynamic videos. However, existing optical flow-based methods fail to ensure consistent static/dynamic segmentation along object boundaries, while 3D reconstruction-based approaches are highly sensitive to reconstruction errors. To address these limitations, we present a dynamic object segmentation framework that can generate both precise and complete dynamic masks by integrating multimodal cues including 2D point tracks, 3D reconstruction, and semantic information. We design a network combining Transformer architectures with feature clustering aggregation modules to perform static/dynamic classification of multimodal feature trajectories. It enables the model to adaptively determine which type of feature should dominate based on the characteristics of each scene, while also mitigating the impact of feature degradation. Additionally, we introduce a novel point-query-based SAM post-processing method capable of handling multiple objects within a single mask. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in both dynamic object segmentation and static scene reconstruction tasks.