Papers

Falling detection is vital for elderly care and intelligent surveillance; however, prevailing vision-based approaches predominantly frame it as static pose classification or discrete temporal pattern matching, fundamentally overlooking the instability dynamics of the human support system. This paper proposes a physics-informed falling detection framework that recasts falling as a stability-loss event in a coupled dynamical system. We introduce a novel dual-LTC architecture comprising a Center-of-Mass (CoM) subsystem and a Base-of-Support (BoS) subsystem, both instantiated as Liquid Time-Constant (LTC) neural networks to continuously model inertial trajectory evolution and ground-contact adjustment through adaptive time constants, Physical interpretability of falling motion. A learnable coupling module emulates physical interaction between the two subsystems, while a Stability Manifold classifier operates in the joint latent space to detect boundary crossing via Lyapunov-inspired stability metrics. Complementary counterfactual trajectory projection and Time-to-Collision (TTC) estimation further enable irreversibility assessment and early warning. The architecture is designed to support a three-state prediction paradigm (Normal, Falling, Fallen); in this preliminary study, we validate the core stability discrimination capability on a two-class dataset (Normal vs. Falling), leaving the full three-state temporal transition to future work. Unlike conventional CNN–RNN pipelines, the proposed formulation encodes continuous-time mechanical inertia, yielding a sub-50K-parameter network capable of real-time inference on resource-constrained edge devices. Extensive experiments demonstrate competitive accuracy with superior physical interpretability, validating its efficacy for low-compute visual fall detection.

Long-term memory has become a foundational capability for LLM-based agents that accompany users across extended, multi-session interactions. Existing benchmarks, however, evaluate such memory almost exclusively through downstream question answering, scoring only the correctness of a final answer. This black-box formulation conflates the heterogeneous causes of memory failure, such as missing the introduction of a relevant fact, binding an operation to the wrong target, or relying on stale values after a correction. As a result, it can credit correct answers despite their reliance on inconsistent or unsafe memory states. In this paper, we argue that, in dynamic long-horizon interactions, memory is not a static collection of facts but a lifecycle of explicit operations, including remembering, forgetting, updating, reflecting, and their compositions. We introduce MemOps, a benchmark that reformulates conversational memory as a sequence of lifecycle operations and represents each memory event with a structured trace specifying its trigger, target, scope, state transition, and supporting evidence. A controllable generation pipeline embeds these operations into long, task-oriented conversations and produces gold operation traces together with six categories of operation-level probes, evaluated under both adjacent-evidence and long-context settings. Across long-context, retrieval-based, parametric and managed-memory systems, MemOps disentangles failure modes that final-answer accuracy alone conceals, revealing that current systems remain far from uniformly reliable. For instance, session-level retrieval outperforms turn-level retrieval, and long-context models remain notably weak at reconstructing ordered memory-state trajectories. These results move long-term memory evaluation from final-answer scoring toward interpretable, operation-level diagnosis.

Modern robot learning systems increasingly rely on dense progress or value signals to evaluate intermediate states, guide policy learning, and detect task completion, making the quality of these signals critical. Since such dense labels are rarely available at scale, normalized time within a demonstration is often used as a scalable substitute: later frames are treated as higher progress. However, this time-derived label is only a noisy proxy for physical task progress. In contact-rich manipulation, a robot may make progress and then lose it through slips, failed grasps, or partial undoing, while the time-derived label continues to increase monotonically. We introduce Unsupervised Robotic Value Correction (UR-VC), an offline, training-free method for correcting time-derived progress labels. UR-VC exploits a simple regularity in demonstration data: similar states often recur across different episodes, but at different timestamps. Instead of trusting the timestamp from a single trajectory, UR-VC retrieves similar states from other episodes and aggregates their time-derived labels to obtain a corrected progress estimate. UR-VC requires no manual progress labels, reward annotations, or additional value model. We evaluate UR-VC on real bimanual cloth flatten-and-fold data, a long-horizon deformable-object manipulation task with visible intermediate progress. The corrected labels capture local regressions and non-uniform progress that normalized time cannot represent, while preserving the overall task trend. We further use the corrected signal to construct advantage labels for VLA training, following recent advantage-conditioned policy learning. UR-VC shows a positive trend in real-robot task success under matched data, model, and training settings.

Clinical notes contain many of the signs and symptoms that bring patients to care, yet this information rarely reaches structured fields. Existing extraction approaches either rely on context-insensitive rules that generate false positives or on supervised models that require substantial fine-tuning. We present Pythia, a multi-agent system that autonomously writes and optimizes extraction prompts for clinical concepts without manual prompt engineering or fine-tuning. Running on a locally hosted open-weights model, Pythia keeps clinical notes on local infrastructure and selects prompts using development-set sensitivity and specificity. We compared Pythia with a curated lexicon across 72 signs and symptoms from 400 clinical notes representing 387 patients. Development (n=300) and validation (n=100) sets were partitioned independently for each concept. Pythia achieved mean sensitivity of 0.76 and specificity of 0.95, compared with 0.82 and 0.76 for the lexicon, and matched or exceeded the lexicon on both metrics for 20 of 62 directly comparable concepts. For 14 concepts where the lexicon labeled every note positive, Pythia recovered mean specificity of 0.97 by requiring a present-tense, patient-attributed finding rather than any textual mention of a term. Specificity transferred from development to validation with minimal degradation across prevalences, whereas sensitivity transfer weakened below 5% prevalence, reaching a mean gap of 0.25 below 2% prevalence. A BERT classifier fine-tuned per concept on the same development set achieved mean sensitivity of 0.23 and collapsed to zero sensitivity for concepts below roughly 5% prevalence. These findings suggest that autonomous, fine-tuning-free prompt optimization can produce symptom extraction prompts that generalize effectively from development to validation while remaining deployable on local infrastructure.

Multi-agent Reinforcement Learning (MARL) holds great potential for robot swarms, but the black-box nature of neural policies complicates strategic analysis, limiting multi-robot applications. Furthermore, complex swarm behaviors can surprisingly emerge from simple rewards without explicit aggregation incentives. Unveiling the mechanisms behind this emergence is critical, but the disconnection between simple rewards and collective behaviors exacerbates interpretability challenges. This paper aims to reveal the hidden mechanisms in this process. We propose a two-stage EEC (\LinkIII) explanatory framework. This includes a novel analytical tool called the Agent Response Map (ARM), which reveals agents' decision-making patterns across space and identifies regions of aggregation and avoidance. ARM reveals that the robots implicitly learn the geometric fields of the environment and utilize these structures as desired targets for coordinated movement. We validate this finding across two distinct tasks: a cooperative multi-robot shape assembly and a competitive predator-prey pursuit-evasion. 1) In the cooperative task, ARM identifies the unoccupied target interior as the desired destination for robot navigation. As the center becomes occupied, this target region automatically shifts toward the boundary, demonstrating the robots' capacity to autonomously explore unoccupied areas. 2) In the competitive task, ARM surprisingly identifies the boundary of the predators' Voronoi diagram as the convergence destination for prey agents. Together, these two tasks demonstrate the capability of ARM to discover the hidden geometric structures underlying MARL policies in robot swarms.

A generated rhythm-game chart need not reproduce one official note sequence: many note choices can fit the same song and difficulty. Reference-note agreement therefore measures reconstruction, not the full design problem. We introduce ChartGenEval, a six-question evaluation framework with an automatic, corruption-tested core. It leaves note choice open while anchoring timing to the song: the matched official chart supplies only its authored timing map, never target notes. We test each core output with dose-controlled failures rather than assume that a familiar statistic measures chart quality. Across 80 held-out song groups, seven output axes satisfy prespecified sensitivity and invariance criteria in nine nonredundant tests. Complementary stress tests on the 40-song development panel expose two broader lessons. A chart-wide phase estimate recovers injected shifts of 15, 30, and 60 ms while chart-only outputs remain essentially unchanged. Common-pattern rewriting lowers mean language-model perplexity by 37%, and loop collapse raises mean self-similarity by 62%. ChartGenEval therefore reports separate, role-specific signals instead of one proxy or total score. This profile provides automatic feedback for comparing and iterating generators; selected outputs are candidate optimization targets or constraints after task-specific stress testing.

Unconventional computing systems must demonstrate robust performance under real-world environmental conditions to enable practical deployments. We have recently proposed superparamagnetic nanodot ensembles driven by strain-induced magnetoelectric coupling as exciting candidates for use as ultra-low energy consumption reservoir computing substrates. However, because their dynamics are governed by thermal activation effects, these systems are intrinsically sensitive to ambient temperature fluctuations, leading to degraded task performance when operated outside the temperature range used during training. In this paper we simulate how temperature variations affect the magnetization dynamics of such superparamagnetic ensembles, and quantify how this affects task performance. We then show how heterogeneous nanodot patterns that incorporate different sizes of nanodots with different characteristic timescales for thermal activation mitigate this problem. Benchmark results on the NARMA-10 task show that introducing optimized heterogeneity stabilizes performance of the reservoirs across a wide range of ambient temperatures (5-35{\deg}C), with little loss of ultimate performance. We also characterize the trade-off between performance and temperature stability and show that it can be tuned via reservoir hyperparameters. Our study demonstrates a key step in making these novel devices suitable for real-world deployment.

Diffusion large language models (dLLMs) offer a theoretical advantage in parallel generation over standard autoregressive models. However, parallel generation alone does not guarantee practical speedups. Realizing this efficiency requires specialized inference mechanisms, such as diffusion-aware caching and reuse. Consequently, as inference efficiency becomes a prerequisite for practical deployment, recent research has actively explored acceleration techniques across algorithms, architectures, and systems. However, rigorous comparisons remain difficult, as end-to-end latency stems from intricate trade-offs between algorithmic, architectural, and system-level factors that are often conflated in existing benchmarks. In this survey, we introduce a unified latency decomposition framework for dLLMs to disentangle these factors and analyze their impact on inference speed in real deployments. Guided by this framework, we categorize acceleration techniques along three axes covering algorithmic innovations, architectural and system optimizations, and inference-time scaling. Finally, we provide guidelines for reproducible benchmarking and highlight open challenges for realizing the full potential of parallel generation.

This paper addresses Carl Hempel's longstanding problem of statistical ambiguity in inductive-statistical inference, in which contradictory predictions are derived from statistical laws. To avoid such predictions, Carl Hempel proposed the Requirement of Maximal Specificity (RMS) for the statistical laws used in the inference. An analysis of the RMS refinements made by Wesley Salmon, Alberto Coffa, and James Fetzer led to the following definition of maximally specific statistical laws: "the lawlike premises of an adequate explanation must specify all and only those properties whose presence or absence made a difference to the occurrence of its explanandum-phenomenon." However, there was no proof of a solution to the statistical ambiguity problem based on this definition. We use Nancy Cartwright's definition of causes that raise probabilities across background contexts, and then introduce the concept of Causal Rules. Then we define a special semantic probabilistic inference procedure that incrementally refines these causal rules by incorporating all statistically relevant information. This procedure yields Maximally Specific Causal Relationships (MSCRs), for which we prove (Theorem 1) that predictions derived from them are consistent. This resolves the statistical ambiguity problem. The semantic probabilistic inference procedure provides a probabilistic causal learning system, which may be used in such new areas as Causal AI and Causal Machine Learning. They fundamentally explore causal inference as a tool for understanding cause-and-effect relationships within complex systems. Properties similar to RMS remain under discussion. Several notions related to RMS are considered: invariant feature learning, invariant causal prediction, and spurious association.

Interaction with AI agents has become one of the most frequent activities of everyday digital life. Whether conversing with an assistant, working with a coding copilot, or generating images, the interaction follows a common iterative loop: a request is issued, a result returned, appraised, and the request revised. We observe that this loop is a high-frequency stream of contact events – moments at which a result meets a person and a conditioned response may fire before deliberate appraisal – making everyday agent interaction an unrecognised neuroplastic training environment. When a result disappoints, reactive patterns of impatience, perfectionism, frustration, and self-criticism are repeatedly evoked, and under activity-dependent synaptic plasticity each uninterrupted cycle deepens the underlying pathway through long-term potentiation. Ordinary agent use may thus quietly strengthen the very patterns it provokes. We propose that the same training environment can be engaged to the opposite effect. Treating conditioned reactive patterns as physical neurone paths – activated through a pre-cognitive feeling tone that opens a brief regulatory gap – we develop a framework in which, at that gap, in place of the reactive re-prompt, a person performs behind-the-scenes observation: watching the neural process operate so the cascade does not complete and long-term depression weakens the path rather than potentiation strengthening it. We characterise this practice through three layers of observation and two modes of application: a user-guided mode requiring no change to existing tools, and an agent-assisted mode in which an ordinary agent is lightly configured to support observation at the gap. We illustrate the framework through generative image prompting, showing how a single frustrating session is behaviourally nearly identical whether or not it is observed, yet neurologically opposite.

When do vision-language models need direct access to the image while generating an answer? We study image dependence during answer generation by examining how the visual information needed for the current question becomes available in context. We intervene on direct image access while retaining previously computed states. Across real-image and synthetic tasks, we show that, depending on the generation process, direct access can continue to support accuracy after question processing. Supplying the required attributes as text in the context weakens this dependence. On synthetic tasks, we also examine how dependence changes as the model itself states the required attributes. Before attribute expression, severing access reduces accuracy, and replacing image-side states shifts answers toward the counterfactual content. After sufficient expression, both interventions have smaller effects. Even with an identical generated prefix, dependence differs according to whether image access was available during question processing. Thus, both the visible text and the preceding image access matter. Several of these patterns hold across model families, including Qwen2.5-VL-32B and InternVL3-14B. These findings offer a view of image dependence in terms of the information needed for the current question and the history of image access, beyond generation position alone. This perspective provides a basis for deciding when to reduce visual access during an answer and which visual information to retain for subsequent questions.

Although topological mapping and navigation have been studied extensively, the specific role and downstream effect of loop closures in purely topological representations has received relatively little attention. Importantly, loop closure over topological maps is distinct from loop closure over globally referenced trajectories and metric maps. Building on recent denser topologies grounded in pixel-level, relative 3D geometry, we propose PixelLoop which introduces loop closures directly in pixel space. Unlike sparse image-level edges or pose-graph corrections in SLAM, our pixel-level closures act as dense topological shortcuts that alter planning connectivity and cost propagation rather than merely aligning coordinates. This dense connectivity enables stable any-point-to-any-point navigation and produces costmaps that align accurately with geometric shortest paths. In particular, we showcase the distinct advantage of applying loop closures to fine-grained pixel topologies rather than image-level topologies. Across extensive simulated experiments, PixelLoop achieves over 35% absolute improvement in both Success Rate and SPL compared to image-relative baselines, with the largest gains in scenarios requiring shortcut exploitation. Results are further validated through real-world mobile robot deployments, demonstrating that dense pixel-level loop closures provide a practical and robust foundation for topological visual navigation. Project Page: https://pixelloop-nav.github.io/

This study introduces a unified control framework for fixed-wing unmanned aerial vehicles (UAVs) fitted with a pan-tilt (PT) camera, intended to perform an end-to-end mission spanning from initial target detection to accurate terminal engagement. The proposed system employs a three-phase strategy: a vision-based target acquisition phase, an NMPC-based tracking phase, and a terminal guidance phase. During tracking, the framework uses an Unscented Kalman Filter (UKF) to fuse YOLO-based visual detections with inertial measurements, enabling robust target state estimation under unknown dynamics. To ensure reliable visual contact, we introduce a constraint-aware Nonlinear Model Predictive Control (NMPC) strategy that incorporates Control Barrier Functions (CBFs) to explicitly prevent UAV self-occlusion – a common limitation in fixed-wing tracking. Upon satisfying terminal engagement conditions, the system seamlessly transitions control to a quaternion-based Biased Proportional Navigation Guidance (BPNG) law, enforcing precise impact angle constraints. High-fidelity simulations demonstrate that the framework achieves stable, robust tracking and accurate terminal interception while strictly respecting the vehicle's dynamic limits and camera field-of-view constraints.

When a language model must choose one answer from a large space of equally valid options, which answer does it choose, and how often is it the answer every other model chooses? Asked to "pick a word," 105 language models from more than twenty labs chose serendipity 46% of the time. We measure this convergence, and each model's share in it, with 96 single-turn prompts that each name a category with many valid one-word answers ("Name a tree."), asked eight times per model and scored by exact match, with no embeddings and no judge. A model's answer-choice surprisal is the average -log2 probability of its answers under the pooled answers of all other models. In 28 of 96 categories a single answer takes at least 80% of all answers. The concentration does not depend on small or persona-tuned models: the 87 major-lab models are at least as concentrated as the full field. Lightly post-trained and persona-tuned models are the most divergent; heavily post-trained assistants from the major labs are the most conformist. Models that avoid the modal answer mostly land on the same runner-up. Within the major providers' lineages, release order shows no panel-wide trend once model tier is controlled; GPT, Gemini, Grok and Qwen become more conformist across releases, and Claude's generation-5 releases reverse. On open checkpoints of three post-training pipelines, supervised fine-tuning is the largest step toward the field's answers. Against human category-production norms, the field is more concentrated than people in 18 of 20 shared categories. All prompts, transcripts, and code are public.

Jailbreak-robustness research typically evaluates safety through generated responses using an LLM-as-judge approach. Such evaluations, however, are sensitive to the benchmark's grading procedure and capture only observed behavior on a given set of attacks, without directly revealing the hidden fragility of the underlying safety mechanisms. This work proposes JADR (Jacobian Assessment of Danger Recognition), a protocol that measures a model's internal representation through Jacobian space (J-space, a recently proposed workspace of verbalizable concepts) before the first response token is generated. For every prompt and layer we record the top-k J-space tokens; these are grouped into six behavioral scenario axes and compared between a danger sample based on StrongREJECT and a safe control drawn from XSTest and OKTest. The method does not call on an external judge model: the computation runs entirely locally, on the activations of the model under evaluation, which lets us compare both different models against each other and modifications of a single model - quantization and fine-tuning in particular - on the same terms. The final comparison rests on the proposed SafetyAUC metric, complemented with bootstrap confidence intervals. The protocol is applied to six models (Qwen3-1.7B, Qwen3-4B, Qwen3-8B, Qwen3-Uncensored-4B, Qwen3-SafeRL-4B, Gemma 2 9B) across three weight-representation regimes - BF16, INT8, and INT4 - and checked against an independent behavioral evaluation with the StrongREJECT grader. The metric separates models with a strong versus a weak internal safety mechanism with statistical significance and captures substantively different effects across quantization regimes.

Self-evolving agent systems create, revise, and retire their own skills, but every such loop assumes a reliable evaluation metric already exists. In many real applications none does. We show the metric itself can be the evolving object: our loop searches compositions of small typed drawback detectors under a full evolutionary lifecycle, selecting for agreement with a ten-item anchored reference set and regularizing by consensus over unlabeled outputs. What evolves is the function that grades one output, never the fixed task sets it is scored on, and what comes out is an inspectable expression rather than an opaque judge. It is also valid: on code generation it gains 0.21 agreement with hidden ground truth on a locked set that metric selection never reads (paired $p=0.014$), beating the bare LLM judge it contains. Validity is where safety lives: removing the anchor guards collapses the metric into a vacuous always-pass detector while removing the detector lifecycle does not, inverting the lesson from skill evolution. That collapse warns this line of work that downstream task score cannot validate a self-evolved evaluator, since the collapsed metric trains skills just as well. Task score answers only sufficiency, and an evolved metric suffices: Double Ratchet, co-evolving the metric with a lifecycle-managed skill loop, retains 88–110% of the lift ground truth or a hand-written rubric buys, across MBPP+, Spider~2.0-Snow, and report generation. When evolved skills gamed the report rubric, an independent judge caught it and one added detector repaired it.

Recent advances in multimodal large language models (MLLMs) have significantly improved the performance of multimodal emotion recognition (MER) and enabled interpretable description generation by jointly modeling video, audio, and language, etc. However, these performance improvements are often accompanied by an increase in model parameter size (e.g, at least 7B), which simultaneously incurs high computational costs and reduces inference efficiency, thereby hindering real-time deployment on resource-constrained platforms such as robots and mobile devices. This raises a fundamental question: do we really need the multimodal MER model larger than 1B parameters for high-quality MER? In this paper, we challenge the assumption that larger models are inherently necessary and proposes a lightweight MER framework (called Light-MER), which achieves better and faster multimodal sentiment understanding and recognition through knowledge distillation. It can transfer knowledge from a strong, large-scale teacher model to a lightweight sub-billion-parameter student model, aiming to preserve rich multimodal emotion reasoning and recognition while substantially improving deployment efficiency. Specifically, we introduce two new optimization strategies to enhance knowledge transfer: (1) a new optimal transport loss that combines Sliced Wasserstein Distance with hidden-state alignment, and (2) a new multi-reward optimization strategy based on GRPO that balances MER performance and efficiency, aimed at further enhancing the learning capabilities of student models. Extensive experiments on nine benchmark datasets demonstrate that Light-MER achieves state-of-the-art performance while significantly improving inference efficiency. This highlights the strong potential of small multimodal emotion language models for future research. Code is available at https://github.com/GAIR-Lab/Light-MER.

Quantum circuit optimization for fault-tolerant computing requires exact functional equivalence while minimizing expensive non-Clifford resources such as T gates. We study this problem using a compact 44.8M-parameter encoder-decoder transformer with structured circuit tokenization, evaluating on parameterized circuits (2-6 qubits) and Clifford+T circuits (3-6 qubits). On parameterized circuits, a hybrid approach – structure from the transformer, angles from classical optimization – achieves median fidelity 1.000 on 3-6 qubit circuits. On Clifford+T circuits, where all gates are discrete and no post-processing is possible, the model learns valid syntax and accurate T-Count statistics, yet exact equivalence degrades sharply with target length – from 88% on circuits with <=9 gates to near zero beyond 26 gates. We trace this failure to autoregressive drift: early-token divergence cascading irrecoverably through left-to-right decoding. Two levers partially mitigate the drift: inference-time strategies that generate multiple candidates and select via equivalence verification raise exact-match rates from 7% to 22.5%, while scaling training data by 2.5x pushes them to 39.5%. Yet the degradation with target length persists – even with more data, exact equivalence drops from 94% on short circuits to under 4% beyond 26 gates. The contrast between settings is our central finding: when approximate outputs can be rescued by post-processing, the transformer succeeds; when exact discrete correctness is required, autoregressive drift limits reliability, with both inference-time search and data scaling as effective levers while training-side fine-tuning and model-level diversification are not.

This article presents our results for the 11th Affective Behavior Analysis in-the-Wild (ABAW) competition. For multi-task learning with simultaneous prediction of valence, arousal, facial expressions, and action units on s-Aff-Wild2 dataset, we use frozen lightweight facial extractors, MT-EmotiDDAMFN and MT-EmotiEffNet-B0, with separate heads and systematic post-processing: temporal Gaussian smoothing, per-class expression bias, AffectNet blending, per-AU threshold tuning, and weighted backbone fusion. On the official validation set, our ensemble significantly exceeds the performance of the ConvNeXt baseline. For ambivalence/hesitancy video recognition on the expanded BAH dataset, we extend the audiovisual pipeline to video-level Macro F1 by late fusion of face, HuBERT audio, and RoBERTa text classifiers, temporal aggregation, and a global-text gate. Frame-level Weighted F1 on validation set rises from 0.74 in ABAW-8 to 0.79, while the best public-test video-level Macro F1 reaches 0.73. In both tasks, competitive performance is achieved without fine-tuning heavy backbones. These results indicate that systematic prediction calibration and lightweight multimodal fusion can rival substantially heavier end-to-end approaches while offering improved efficiency and deployment flexibility.

Multiple-choice benchmarks that rank candidate completions by conditional log-probability suffer from a length bias: because log-probabilities sum over tokens, longer answers tend to be penalized relative to shorter ones in practice. A common mitigation is to normalize scores by completion length, but we show empirically that this heuristic frequently over-corrects, introducing a bias toward longer answers instead. We first analyze these scoring rules, characterizing when standard and length-normalized accuracy are appropriate and how their length biases depend on the distribution of completion lengths. Motivated by this analysis, we introduce Bayesian accuracy, a scoring rule that computes the posterior probability of each candidate under an explicit prior over answer length, thereby removing linear length effects. Bayesian accuracy is a drop-in replacement for likelihood-based multiple-choice evaluation, requires no additional forward passes, and consistently exhibits lower empirical length bias than both standard and length-normalized accuracy across benchmarks and few-shot settings.

Federated Reinforcement Learning (FedRL) enables coordination of distributed energy resources without sharing raw local data, but standard aggregation methods such as FedAvg do not account for system-level constraints, often leading to unsafe global behavior. In this work, we study constraint-aware aggregation for federated reinforcement learning in distributed energy coordination. We propose aggregation rules that incorporate both local performance and estimated constraint violation into the server-side update. Among these, a simple penalty-based rule, $w_i \propto R_i - \alpha V_i$, consistently provides the most reliable trade-off between reward and safety, without requiring dual optimization or modifications to local training. \textcolor{black}{We evaluate our approach on DairyGridEnv, a benchmark modeling multiple farms coordinating battery storage under stochastic demand and a shared grid capacity constraint, and further assess robustness using real load-driven demand profiles from Finland and the German FIELD dataset. Across multiple seeds, penalty-based aggregation substantially reduces violations while improving reward relative to FedAvg in both synthetic and real load-driven settings.} A combined reward-violation scheme exposes a tunable trade-off via $\lambda$, but is less stable. These results demonstrate that lightweight aggregation strategies can substantially improve empirical safety in federated reinforcement learning while preserving standard communication protocols.

AI-enabled systems are seeing increasing deployment across numerous domains, with many being "black boxes" with respect to core functions and capabilities. I.e., many systems take inputs and give outputs, but without users having any ability to see how the former lead to the latter. AI-enabled systems are also being used to augment autonomy in systems, and autonomy coupled with opacity raises numerous concerns surrounding, e.g., the reliability of systems, their regularity in functioning, human ability to control them, or whether deploying opaque and potentially autonomous systems is in compliance with ethical and legal norms. In this article, we argue that many of these worries can be mitigated by leveraging practical judgment, virtue, and intuition in the deployment and use of opaque AI-enabled systems. We show that focusing on these distinctly human capabilities provides a means for bridging between the practical challenges created by opacity and the ethical, legal, and social norms underpinning particular domains. We argue that a core element in doing this is a recognition that many positive human traits are not quantifiable and we therefore must develop training regimen and guidelines on AI deployment anchored in humanistic but non-quantifiable values. Throughout the article, we focus on the military domain as an exemplar of the importance of practical judgment, virtue, and intuition as drivers for ethical and effective human decision-making surrounding AI deployments, but the underlying arguments apply to all domains where opaque and potentially autonomous systems are being deployed (subject to domain-specific alterations).

While recent advances in 3D generation have enabled impressive visual synthesis, existing methods often rely on 2D diffusion supervision without explicit mechanisms for geometric consistency, leading to spatial hallucinations such as duplicated structures and misaligned geometry. These issues become more severe in 4D generation, where maintaining consistency across viewpoints and temporal evolution introduces additional challenges, including jitter, identity flicker, and structural drift. We present Hallo4D, a unified and model-agnostic framework for mitigating spatiotemporal hallucinations in 3D and 4D content generation. Hallo4D introduces a generation-detection-correction paradigm that leverages large multimodal language models (LMMs) to identify and summarize spatial and temporal inconsistencies from multi-view and multi-frame renderings. These insights guide a consensus-driven image-space consistency optimization, where an LMM-based selector evaluates candidate corrections through multi-model voting, without requiring retraining or architectural modifications. To further improve temporal consistency and optimization efficiency, Hallo4D incorporates motion-aware keyframe sampling, LMM-guided initialization, and appearance alignment. We additionally introduce exposure-aware optimization and visibility pruning to enhance robustness under challenging viewpoints. Extensive experiments demonstrate that Hallo4D consistently outperforms strong baselines across diverse 3D and 4D generation settings, providing a scalable and generalizable solution for consistency-aware content generation.

Farm site discovery from satellite imagery is a spatiotemporal candidate ranking problem because farm evidence is distributed across pasture, field boundaries, roads, buildings, and seasonal vegetation patterns. Direct farm labels are often incomplete, which makes fully supervised detection difficult. This paper proposes a weakly supervised pipeline for ranking dairy farm candidate clusters from seasonal Sentinel imagery and open map priors. The method uses aligned spring, summer, and autumn image tiles from County Cork, Ireland, with spectral bands, vegetation indices, built area indices, and a pasture channel. A Barlow Twins encoder learns multi-season tile embeddings without farm labels. In parallel, weak OpenStreetMap farm priors are split into a prior and a held-out set. Prior features support a rule-based tile score that combines farm proximity, seasonal pasture evidence, and summer greenness, while held-out features are reserved only for proxy evaluation. The rule score is smoothed over a spatial representation graph using geographic proximity and embedding similarity, and high-scoring tiles are grouped into ranked candidate clusters. From 26,722 valid tiles, the main run selects 535 high-confidence tiles and forms 71 candidate clusters. The top 5 clusters achieve 0.60 precision within 500 m and 0.80 precision within 1000 m of held-out OpenStreetMap farm features. The top 10 clusters achieve 0.40 precision within 500 m and 0.80 precision within 1000 m. The results show that seasonal representation learning and weak geographic priors can reduce large satellite image collections into compact candidate sets for human review.

Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajectory caused the task to fail, is critical for debugging and improving these systems. Existing approaches either rely on prompting-based pipelines, which are computationally expensive, or require post-training on failure trajectories with step-level error annotations, which are costly to collect and difficult to scale. We argue that a practical failure attribution model should be lightweight and trainable without step-level supervision on failure data. To this end, we address unsupervised failure attribution, i.e., training exclusively on successful trajectories and identifying error steps at inference time given a failure trajectory. We propose OAT, which casts this problem as one-class learning with neural controlled differential equations, modeling the dynamical pattern of successful trajectories in latent space. At inference time, each step in a failure trajectory is assigned an anomaly score based on its deviation from the dynamics learned on successful trajectories, which is then used to form a set of error steps. With training on only 100 successful trajectories, experiments show that OAT is 200–5000 $\times$ faster than prompting-based baselines, and, at the same time, consistently outperforms them in both in-domain and out-of-distribution datasets with +20% and +7% F1 scores, respectively, demonstrating that OAT is a promising and efficient direction for diagnosing agentic system failures.

Large language models (LLMs) excel at pattern recognition and text generation, but their capacity for abductive inference - inferring latent hypotheses that explain observed behavior - remains poorly understood. Here, we introduce Elenchos (named after the Socratic method of cross-examination), a generative evaluation framework that measures abductive reasoning as a structural inverse problem. Given a reference formal system, such as the lambda-calculus, and a potentially mutated counterpart, agents must determine whether a mutation has occurred and infer the rule modifications responsible for the resulting behavioral differences. Evaluating frontier and mid-tier LLMs reveals a consistent detection-attribution dissociation: models often recognize that a system has been altered but struggle to identify the latent mutations causing the observed discrepancies. Performance degrades substantially under interacting mutations, where models frequently recover only a subset of the underlying mutations. Preliminary evidence also suggests diminishing returns from increased inference-time reasoning, with only modest improvements under larger reasoning budgets, though this finding requires further validation.

Smart-building load forecasters are often trained offline on dense, multivariate, high-frequency data, but deployment may provide only hourly, feature-limited inputs. Missing features must then be reconstructed, and their errors can propagate through the model. If this input uncertainty is not reflected, prediction intervals may become miscalibrated, affecting demand-response scheduling. Our work examines where uncertainty should be placed once inference inputs are reconstructed. We develop a unified one-day-ahead probabilistic forecasting framework that aligns temporal resolution, reconstructs the unavailable inputs, and derives causal features, and we compare a modular post-hoc residual-quantile scheme with an integrated in-model quantile-learning scheme. The comparison uses three mid-scale Deep Learning (DL) backbones: recurrent, hybrid recurrent, and attention-based Temporal Fusion Transformer (TFT) models, under identical inputs, forecasting horizon, preprocessing rules, and training budgets. Results show that uncertainty placement is backbone-dependent. Integrated quantile learning is most reliable with the TFT, yielding 2.2-3.6% MAPE and 28-83W RMSE on the labeled test window, while producing intervals about 5x narrower than the modular intervals at the closest-to-nominal coverage level. Diebold-Mariano tests support the TFT ranking and the mixed behavior of the recurrent backbones. A reconstruction-sensitivity test shows that reconstructed inputs increase the Quantile Score (QS) by 106% while interval width remains nearly unchanged, indicating that the model does not automatically absorb reconstruction-induced uncertainty. Robustness checks against non-DL baselines and seasonal hold-out weeks support this ranking. Our results expose the limits of post-hoc residual quantiles when inference depends on reconstructed inputs.

Container filesystem isolation depends on safely resolving container-controlled paths during privileged host-container interactions. As third-party plugins and agent sandboxes introduce more interactions, unsafe path resolution can redirect host operations across isolation boundaries, expanding the attack surface for path traversal vulnerabilities. These logic flaws are difficult to mitigate: kernel defenses require intrusive redesign, static rules miss cross-boundary semantics, and manual auditing cannot scale. Large Language Model (LLM) based methods can detect syntax flaws through stable code patterns and identify logic flaws in domains such as smart contracts by comparing equivalent implementations. Container components, however, provide neither form of regularity: their heterogeneous interfaces operate under trust boundaries, filesystem views and interaction orders, making the security invariant difficult to find. We present Bulkhead, an automated framework for detection and remediation. Bulkhead summarizes historical CVEs into structured semantic patterns, correlates documentation with entry and effect side code evidence, and recovers source-to-sink execution contexts. Grounded patterns guide LLM reasoning, while isolated Proof-of-Concept (PoC) execution validates findings. For remediation, Bulkhead generates repository-specific patches, checks that they build, and iteratively verifies path safety and functionality using pattern derived model checking templates and counterexamples before runtime validation. Across container repositories, Bulkhead discovered 20 zero-day vulnerabilities, accounting for 43% of the total number discovered over the past decade. Among them, 3 have been assigned CVEs and the verified patch suggestions have been submitted to the upstream.

Generated tokens are a direct driver of the cost, latency, and energy of generative AI (GAI) code editing. We show the format of feedback is a lever on all three. We compare two deliveries of the same requested changes: a holistic prompt (control) versus the structured, line-anchored export of FileMark (treatment). FileMark is a VSCodium extension for inline comments on any file. In a paired experiment line anchoring cut generated tokens by 22% (Claude Opus) and 58% (Claude Sonnet), reaching 24%-80% on files of 100 lines or more, with four of seven models generating significantly fewer tokens after multiple-testing correction. Correctness rose where models had headroom: +2.0 points pooled and +5 to +7 points for three of five local models. An exploratory experiment in which the harness, not the GAI model, applies function-level patches shows the correctness benefit grows further when the edit-application burden is lifted: local-model correctness on 100+ line files roughly triples under anchoring. Line-anchored feedback reduces what stronger models spend and improves what weaker models get right.

Vision–Language Models (VLMs) have recently demonstrated promising performance on structured visual reasoning tasks, including grid-based puzzles. However, despite strong perceptual capabilities, these models lack explicit mechanisms for enforcing logical consistency and frequently generate assignments that violate underlying constraints. In this paper, we propose a neuro-symbolic approach that integrates formal constraint reasoning into the VLM solving process via a Maximum Satisfiability (MaxSAT) oracle. Rather than computing solutions directly, the symbolic component acts as a consistency validator and refinement engine. Candidate placements generated by the VLM are encoded as soft clauses in a partial MaxSAT formulation, while Sudoku constraints remain hard clauses. When inconsistencies arise, the MaxSAT solver identifies a largest mutually consistent subset of assignments, which is then translated into structured textual and visual feedback to guide subsequent refinements. We evaluate our approach on a Sudoku dataset across multiple open-source and closed-access VLMs. Results show that MaxSAT-based feedback improves logical consistency and increases the number of solved instances, particularly in full-board refinement mode. These findings demonstrate that symbolic optimisation can enhance the reliability of vision-language reasoning.