探索全球前沿学术脉络

01.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12834

Fantastic Scientific Agents and How to Build Them: AgentBuild for Rietveld Refinement

作者:

Woong Shin↗Craig A. Bridges↗Marshall T. McDonnell↗Rafael Ferreira da Silva↗

arXiv:2606.12834v1 Announce Type: new Abstract: As scientific workflows shift from deterministic executables to LLM-based agents, the development practices on offer, such as fine-tuning, reinforcement learning, and prompt-and-go, bury the scientist's judgment. We propose treating agent construction as a workflow stage and introduce AgentBuild, which builds a scientific agent from a contract the scientist authors. The contract is a version-controlled rubric, a difficulty-graded curriculum, and a curated external knowledge base. A rubric-driven judge gates a meta-optimizer coding agent that edits the agent within a declared boundary, so the build compiles the agent, not the scientist's judgment. We instantiate this for Rietveld refinement of X-ray diffraction data through GSAS-II behind MCP and A2A, where a blank-harness construction run progresses through a lithium lanthanum zirconium oxide (LLZO) signal-to-noise ladder, reaches the 4 hour scan as a frontier case, and exposes the workflow-scope limits that remain. The same rubric that rewards credible fits also scores trajectory scope, making the frontier a contract failure rather than a pattern-fitting failure. As base models evolve, re-running AgentBuild is a re-tune, not a rebuild, and the scientist's authored contract remains the durable asset.

阅读与讨论 → 访问原文 →

02.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2606.15899

SkillVetBench: LLM-as-Judge for Multi-Dimensional Security Risk Evaluation in Open-Source LLM Agent Skills

作者:

Ismail Hossain↗Sai Puppala↗Md Jahangir Alam↗Tanzim Ahad↗Sajedul Talukder↗

arXiv:2606.15899v1 Announce Type: cross Abstract: Open-source LLM agent ecosystems are growing rapidly, yet the security of community-contributed skills - modular tool definitions that extend agent capabilities - remains largely unvetted. The gap we fill: existing scanners operate at the code layer and are structurally blind to instruction-layer and multi-agent risk - natural-language directives that hijack an agent, exfiltrate data through encoded side channels, or chain harm across pipelines - so what is needed is a semantic, multi-dimensional vetting system rather than another signature matcher. We present SKILLVETBENCH, a live public leaderboard on Hugging Face that uses an LLM-as-Judge to vet agent skills. What is new: SARS (Skill Agentic Risk Score), a five-dimensional agentic-risk metric with a principled weighted formula for instruction-following systems. What is integrated: full CVSS v4.0 vector decomposition and a ClawHub dual-view that places our LLM-generated review beside the official marketplace verdict. What is demonstrated: drawing on our companion benchmark paper [ 1], the LLM-as-Judge stage achieves zero false negatives across 78 confirmed-malicious skills and zero false positives across 22 benign controls, while the best static baseline (SKILLSIEVE) still misses 15%; for instruction-layer categories such as Prompt Injection and Memory Poisoning, conventional tools miss between 89% and 100% of threats (e.g., CODEBERT detects none of nine memory-poisoning skills). Detection rates vary from 35% to 95% across four LLM evaluators, motivating ensemble scoring in production deployments.

阅读与讨论 → 访问原文 →

03.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.14604

A Comparative Study of Deep Learning Architectures for Multi-Horizon Behavioural Forecasting for Mobile Health

作者:

Pavlos Nicolaou↗Kleanthis Malialis↗Artemis Kontou↗Panayiotis Kolios↗

arXiv:2606.14604v1 Announce Type: cross Abstract: Wearable devices and smartphones generate rich behavioural time series that can support proactive health interventions, yet systematic comparisons of modern forecasting architectures for these data are lacking. In particular, it remains unclear how models generalise across populations, how different architectures respond to participant-level fine-tuning and how forecasting accuracy degrades across multi-day horizons. We benchmark six deep learning architectures, two zero-shot Foundation Models (FM) and statistical baselines on three public datasets encompassing over 800 participants, reporting per-feature metrics for step counts, screen time and sleep duration across 1-8 day horizons. We further conduct a per-feature personalisation study across all six architectures and assess FM transferability across dataset sizes and temporal granularities. Our key findings are: (i) no single architecture dominates, PatchTST leads among trained models while the three runners-up (TCN, MLP, Transformer) show no meaningful performance difference; (ii) the FM TimesFM matches or exceeds trained models zero-shot, especially in low-data regimes and (iii) participant-level fine-tuning reduces per-feature RMSE by 16-60\%, with sleep benefiting most and step counts least. These results provide practical guidance on architecture selection, FM applicability and personalisation strategies for mobile health forecasting. To the best of our knowledge, this is the first study to jointly evaluate modern deep learning, FMs and personalisation for multi-horizon behavioural forecasting from wearables.

阅读与讨论 → 访问原文 →

04.

arXiv (CS.LG) 2026-06-11 DOI: arXiv:2602.22962

Scaling Laws of Global Weather Models

作者:

Yuejiang Yu↗Langwen Huang↗Alexandru Calotoiu↗Torsten Hoefler↗

arXiv:2602.22962v2 Announce Type: replace Abstract: Data-driven models are revolutionizing weather forecasting. To optimize training efficiency and model performance, this paper analyzes empirical scaling laws within this domain. We investigate the relationship between model performance (validation loss) and three key factors: model size ($N$), dataset size ($D$), and compute budget ($C$). Across a range of models, we find that Aurora exhibits the strongest data-scaling behavior: increasing the training dataset by 10x reduces validation loss by up to 3.2x. GraphCast demonstrates the highest parameter efficiency, yet suffers from limited hardware utilization. Our compute-optimal analysis indicates that, under fixed compute budgets, allocating resources to more total training data yields greater performance gains than increasing model size. Furthermore, we analyze model shape and uncover scaling behaviors that differ fundamentally from those observed in language models: weather forecasting models consistently favor increased width over depth. These findings suggest that future weather models should prioritize wider architectures and larger effective training datasets to maximize predictive performance.

阅读与讨论 → 访问原文 →

05.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2602.06470

Improve Large Language Model Systems with User Logs

作者:

Changyue Wang↗Weihang Su↗Qingyao Ai↗Xingzhao Yue↗Rui Zhang↗Xiaojia Chang↗Yiqun Liu↗

Scaling training data and model parameters has long driven progress in large language models (LLMs), but this paradigm is increasingly constrained by the scarcity of high-quality data and diminishing returns from rising computational costs. As a result, recent work is increasing the focus on continual learning from real-world deployment, where user interaction logs provide a rich source of authentic human feedback and procedural knowledge. However, learning from user logs is challenging due to their unstructured and noisy nature. Vanilla LLM systems often struggle to distinguish useful feedback signals from noisy user behavior, and the disparity between user log collection and model optimization (e.g., the off-policy optimization problem) further strengthens the problem. To this end, we propose UNO (User log-driveN Optimization), a unified framework for improving LLM systems (LLMsys) with user logs. UNO first distills logs into semi-structured rules and preference pairs, then employs query-and-feedback-driven clustering to manage data heterogeneity, and finally quantifies the cognitive gap between the model's prior knowledge and the log data. This assessment guides the LLMsys to adaptively filter out noisy feedback and construct different modules for primary and reflective experiences extracted from user logs, thereby improving future responses. Extensive experiments show that UNO achieves state-of-the-art effectiveness and efficiency, significantly outperforming Retrieval Augmented Generation (RAG) and memory-based baselines. We have open-sourced our code at https://github.com/bebr2/UNO .

阅读与讨论 → 访问原文 →

06.

arXiv (CS.AI) 2026-06-12 DOI: arXiv:2606.12439

Position: Generative Engine Optimization Creates Underexamined Risks, Governance Must Target Concentration, Disclosure, and Academic Blind Spots

作者:

Yizhu Wen↗Nan Zhang↗Haohan Yuan↗Xun Chen↗Haopeng Zhang↗Hanqing Guo↗

arXiv:2606.12439v1 Announce Type: cross Abstract: Large language model (LLM) answer engines are increasingly used for information seeking, shifting visibility from ranked lists to synthesized answers. This enables Generative Engine Optimization (GEO), which targets LLM answer engines' evidence pool and generation. We analyze the search engine optimization (SEO) to GEO transition to identify two risks: (i) concentrated influence from low contestability and system sensitivity, and (ii) undisclosed commercial influence embedded in evidence and reasoning. We then formalize a general GEO pipeline to locate where optimization acts and compare academic and industry practices, revealing a third risk: (iii) academic-industry blind spots driven by visibility and evaluation asymmetries between offline setups and deployed systems. This position argues the need for answer-level governance and measurement: stronger contestability, high-precision disclosure, black-box auditing of material influence, and deployment-aligned metrics for exposure persistence.

阅读与讨论 → 访问原文 →

07.

arXiv (CS.CV) 2026-06-17 DOI: arXiv:2604.03120

SCC-Loc: A Unified Semantic Cascade Consensus Framework for UAV Thermal Geo-Localization

作者:

Xiaoran Zhang↗Yu Liu↗Jinyu Liang↗Kangqiushi Li↗Zhiwei Huang↗Huaxin Xiao↗

Cross-modal Thermal Geo-localization (TG) provides a robust, all-weather solution for Unmanned Aerial Vehicles (UAVs) in Global Navigation Satellite System (GNSS)-denied environments. However, profound thermal-visible modality gaps introduce severe feature ambiguity, systematically corrupting conventional coarse-to-fine registration. To dismantle this bottleneck, we propose SCC-Loc, a unified Semantic-Cascade-Consensus localization framework. By sharing a single DINOv2 backbone across global retrieval and MINIMA$_{RoMa}$ matching, it minimizes memory footprint and achieves zero-shot, highly accurate absolute position estimation. Specifically, we tackle modality ambiguity by introducing three cohesive components. First, we design the Semantic-Guided Viewport Alignment (SGVA) module to adaptively optimize satellite crop regions, effectively correcting initial spatial deviations. Second, we develop the Cascaded Spatial-Adaptive Texture-Structure Filtering (C-SATSF) mechanism to explicitly enforce geometric consistency, thereby eradicating dense cross-modal outliers. Finally, we propose the Consensus-Driven Reliability-Aware Position Selection (CD-RAPS) strategy to derive the optimal solution through a synergy of physically constrained pose optimization. To address data scarcity, we construct Thermal-UAV, a comprehensive dataset providing 11,890 diverse thermal queries referenced against a large-scale satellite ortho-photo and corresponding spatially aligned Digital Surface Model (DSM). Extensive experiments demonstrate that SCC-Loc establishes a new state-of-the-art, suppressing the mean localization error to 9.37 m and providing a 7.6-fold accuracy improvement within a strict 5-m threshold over the strongest baseline. Code and dataset are available at https://github.com/FloralHercules/SCC-Loc.

阅读与讨论 → 访问原文 →

08.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18389

Want Better Synthetic Data? Steer It: Activation Steering for Low-Resource Language Generation

作者:

Jan Cegin↗Daniil Gurgurov↗Yusser Al Ghussin↗Simon Ostermann↗

Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated data can improve downstream task performance. Current best-performing approaches typically rely on few-shot prompting with target-language examples, which increases inference costs and may reduce diversity through lexical anchoring. In this work, we investigate activation steering as an alternative for low-resource synthetic data generation. We study two steering strategies: Language Steering, which targets the linguistic identity of a language, and Quality Steering, which captures well-formedness by contrasting human-written and backtranslated text representations. We evaluate these methods across four open-source LLMs, multiple layers, and 11 typologically diverse languages by generating sentiment and topic classification data and finetuning smaller classifiers. Steering is applied in both zero-shot and few-shot prompting settings and compared against non-steered counterparts. Our results show that steering on early layers consistently improves the diversity of generated data while often yielding stronger downstream model performance, particularly for low-resource languages.

阅读与讨论 → 访问原文 →

09.

arXiv (CS.CL) 2026-06-15 DOI: arXiv:2606.13683

UP-NRPA: User Portrait based Nested Rollout Policy Adaptation for Planning with Large Language Models in Goal-oriented Dialogue Systems

作者:

Hui Wang↗Fafa Zhang↗Meng Liu↗Xiangyu Chen↗Chaoxu Mu↗

To address the challenge that current dialogue policy planning methods struggle to dynamically adapt to diverse user characteristics, this paper proposes a User Portrait based Nested Rollout Policy Adaptation (UP-NRPA) online framework with Large Language Models. In contrast to conventional approaches dependent on model training and require offline reinforcement learning policy models for user groups, UP-NRPA enables dynamic customization of dialogue strategies through an adaptive mechanism. This is achieved by leveraging real-time user feedback alongside personality, preferences, and objectives mapped from the current user portrait, thereby adapting to user characteristics without offline reinforcement learning. In collaborative and non-collaborative dialogue benchmarks, UP-NRPA demonstrated considerable benefits, achieving an impressive 100% success rate in multiple dialogue tasks. Particularly in negotiation tasks, the sale-to-list ratio (SL) increased by 56.41%. This demonstrates that UP-NRPA can adapt to diverse user needs without requiring a training mechanism, enabling the dialogue system to adapt to user characteristics.

阅读与讨论 → 访问原文 →

10.

arXiv (quant-ph) 2026-06-11 DOI: arXiv:2507.15453

Entanglement preservation and Clauser-Horne nonlocality in electromagnetically induced transparency quantum memories

作者:

Po-Han Tseng↗Yong-Fan Chen↗

arXiv:2507.15453v4 Announce Type: replace Abstract: Entanglement preservation in noisy quantum memories represents a central challenge in quantum information science. While experiments have shown that electromagnetically induced transparency (EIT) memories can store entangled photons, a quantitative theoretical analysis of whether nonlocal quantum correlations can survive storage loss induced by ground-state decoherence remains limited. Here we combine the dark-state polariton formalism with a reduced density-operator treatment to derive an EIT-specific effective pure-loss description for the retrieved photonic state in the ground-state-decoherence-limited regime. The analysis reveals that decoherence transforms an initially pure Bell state into a mixed state with a vacuum component and predicts a protocol-dependent storage-efficiency benchmark of 89.7% for violating the chosen unconditional Clauser-Horne (CH) inequality. Above this benchmark, the retrieved photonic state violates the CH inequality without post-selection, whereas below it, this unconditional CH violation is no longer obtained. This framework provides a quantitative theoretical description of entanglement retention, retrieved photonic density operators, and protocol-dependent Bell-test benchmarks in EIT quantum memories.

阅读与讨论 → 访问原文 →

11.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13120

EvoBrowseComp: Benchmarking Search Agents on Evolving Knowledge

作者:

Yunhan Wang↗Jiaan Wang↗Lianzhe Huang↗Xianfeng Zeng↗Fandong Meng↗

Search Agents – large language models augmented with search tools – have intensified the need for future-proof evaluation benchmarks. Existing benchmarks such as BrowseComp rely on static knowledge, making them vulnerable to test-set contamination and parametric memorization. Consequently, models can achieve high scores through fact recall rather than genuine retrieval, obscuring true browsing competence via reasoning shortcuts. In this paper, we introduce EvoBrowseComp, an evolving benchmark of 400 English and 400 Chinese contamination-free complex questions synthesized via live-web traversal. To collect these questions, we design a three-agent collaborative framework: (1) a QA synthesis agent that retrieves fresh knowledge from the live web to synthesize QA pairs; (2) an information filtering agent that filters retrieved knowledge in terms of credibility and popularity to block parametric shortcuts; and (3) a high-level guidance agent that formalizes questions into reasoning graphs to reduce logical redundancy and shortcuts in synthesized QA pairs. Because the framework supports fully automated synthesis, EvoBrowseComp can be regularly updated to prevent data contamination and maintain temporal freshness. Extensive experiments confirm its great difficulty, requiring broad horizontal search. It establishes a scalable paradigm for auto-updatable, high-difficulty benchmarking that keeps pace with both evolving world knowledge and advancing agent capabilities.

阅读与讨论 → 访问原文 →

12.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16951

Simulation-Based Multi-Fillet Evaluation of Woody Breast Poultry Fillets

作者:

Chirantan Sen Mukherjee↗Seung-Chul Yoon↗William J. Beksi↗

Woody breast (WB) is a myopathy in modern broiler chickens that causes the breast muscle to become unusually stiff and fibrous, leading to decreased meat quality and significant economic losses. State-of-the-art automated WB detection relies on a side-view imaging system to analyze the bending behavior of a single fillet as it falls off a conveyor belt. While highly accurate, this approach is constrained by its single-fillet field of view, creating throughput bottlenecks on commercial processing lines. In this paper, we address this limitation via a novel multi-fillet detection architecture utilizing a top-down camera configuration. To validate our approach, we first develop a high-fidelity digital twin of an industrial conveyor system. Next, we synthesize a diverse dataset of 3D fillet meshes and model their viscoelastic bending dynamics using a physics-based simulation engine. Lastly, a continuous 2D shape deformation score is extracted from the top-down perspective as the simulated fillets traverse the roller precipice. Experimental results demonstrate that the top-down shape score effectively captures the contour changes of the fillets as it bends, providing a robust and scalable alternative to a side-view imaging system for simultaneous multi-fillet WB evaluation.

阅读与讨论 → 访问原文 →

13.

arXiv (CS.AI) 2026-06-16 DOI: arXiv:2603.10384

Beyond Scalars: Evaluating and Understanding LLM Reasoning via Geometric Progress and Stability

作者:

Xinyan Jiang↗Ninghao Liu↗Di Wang↗Lijie Hu↗

arXiv:2603.10384v3 Announce Type: replace Abstract: Evaluating LLM reliability via scalar probabilities often fails to capture the structural dynamics of reasoning. We introduce TRACED, a framework that assesses reasoning quality through theoretically grounded geometric kinematics. By decomposing reasoning traces into Progress (displacement) and Stability (curvature), we reveal a distinct topological divergence: correct reasoning manifests as high-progress, stable trajectories, whereas hallucinations are characterized by low-progress, unstable patterns (stalled displacement with high curvature fluctuations). Leveraging these signatures, our probabilistic framework achieves competitive performance and superior robustness across diverse benchmarks. Crucially, TRACED bridges geometry and cognition by mapping high curvature to ''Hesitation Loops'' and displacement to ''Certainty Accumulation'', offering a physical lens to decode the internal dynamics of machine thought.

阅读与讨论 → 访问原文 →

14.

arXiv (CS.CL) 2026-06-19 DOI: arXiv:2606.07822

The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust

作者:

Nishant Subramani↗Palash Goyal↗Yiwen Song↗Mani Malek↗Yuan Xue↗Tomas Pfister↗Hamid Palangi↗

As language models improve and become increasingly deployed to solve a variety of tasks, trustworthiness becomes essential. Calibration is a good proxy for trust: well-calibrated confidence estimates help inform the risk versus reward tradeoff when trusting a specific model output. Unfortunately, even as models improve, they remain poorly calibrated, often biasing towards overconfidence. Additionally, calibration can be gamed: a policy that always predicts the base rate is perfectly calibrated, but completely uninformative. To resolve this, we develop a new metric, expected utility renormalized by the oracle (EURO), that balances calibration and informativeness. We also propose a general-purpose activation-based confidence, utility, and trust estimation protocol (ACUTE) to appropriately adjudicate uncertainty. The ACUTE protocol provides flexible, sample-efficient, and compute-efficient confidence estimators for 3 tasks including multiple choice question answering, tool-calling, and scientific document summarization across 6 models from 4 model families. ACUTE outperforms strong baselines on EURO, while maintaining low calibration error. Taken together, our work shows that equipping LLMs with the ACUTE protocol can improve calibration, utility, and trustworthiness in numerous settings.

阅读与讨论 → 访问原文 →

15.

arXiv (CS.CL) 2026-06-12 DOI: arXiv:2606.13218

When Similar Means Different: Evaluating LLMs on Arabic–Hebrew Cognates

作者:

Junhong Liang↗Noor Abo Mokh↗Bashar Alhafni↗

Arabic and Hebrew, as closely related Semitic languages, share a substantial lexicon of true cognates, misleading false friends, and modern loanwords. This overlap poses a challenge for cross-lingual semantic understanding in large language models (LLMs). To evaluate this capability, we introduce SemCog Bench, a curated benchmark of 1,858 Arabic–Hebrew word pairs with sentence-level annotations for cognate identification and semantic disambiguation. We evaluate open-source and commercial LLMs across multiple input representations (raw, diacritized, Romanized, and phonetic) and reveal a critical gap in cross-lingual reasoning. While models achieve high accuracy on true cognates, performance drops sharply on false friends and loanwords, reflecting a strong reliance on surface-form similarity. Furthermore, sentence-level context yields only modest improvements, suggesting that contextual cues alone are insufficient to overcome misleading form-based signals. These findings reveal a fundamental limitation of current LLMs in resolving cross-lingual form–meaning conflicts and establish SemCog Bench as a rigorous benchmark for multilingual semantic reasoning. Our code and data are publicly available.

阅读与讨论 → 访问原文 →

16.

arXiv (CS.CL) 2026-06-17 DOI: arXiv:2604.03444

Olmo Hybrid: From Theory to Practice and Back

作者:

William Merrill↗Yanhong Li↗Tyler Romero↗Anej Svete↗Caia Costello↗Pradeep Dasigi↗Dirk Groeneveld↗David Heineman↗Bailey Kuehl↗Nathan Lambert↗Chuan Li↗Kyle Lo↗…

Recent work has demonstrated the potential of non-transformer language models, especially linear recurrent neural networks (RNNs) and hybrid models that mix recurrence and attention. Yet there is no consensus on whether the potential benefits of these new architectures justify the risk and effort of scaling them up. To address this, we provide evidence for the advantages of hybrid models over pure transformers on several fronts. First, theoretically, we show that hybrid models do not merely inherit the expressivity of transformers and linear RNNs, but can express tasks beyond both, such as code execution. Putting this theory to practice, we train Olmo Hybrid, a 7B-parameter model largely comparable to Olmo 3 7B but with the sliding window layers replaced by Gated DeltaNet layers. We show that Olmo Hybrid outperforms Olmo 3 across standard pretraining and mid-training evaluations, demonstrating the benefit of hybrid models in a controlled, large-scale setting. We find that the hybrid model scales significantly more efficiently than the transformer, explaining its higher performance. However, its unclear why greater expressivity on specific formal problems should result in better scaling or superior performance on downstream tasks unrelated to those problems. To explain this apparent gap, we return to theory and argue why increased expressivity should translate to better scaling efficiency, completing the loop. Overall, our results suggest that hybrid models mixing attention and recurrent layers are a powerful extension to the language modeling paradigm: not merely to reduce memory during inference, but as a fundamental way to obtain more expressive models that scale better during pretraining.

阅读与讨论 → 访问原文 →

17.

arXiv (CS.AI) 2026-06-17 DOI: arXiv:2606.17312

Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty

作者:

Baishali Chaudhury↗Mengdie Flora Wang↗Hyunji Hayley Park↗Rahul Ghosh↗Sungmin Hong↗Jae Oh Woo↗

arXiv:2606.17312v1 Announce Type: new Abstract: Large language models can arrive at the same answer through reasoning paths that are unstable, contradictory, or difficult to rank consistently – a failure mode especially prevalent in multi-step deductive reasoning. Existing methods assess reliability primarily through output dispersion – measuring how much sampled answers differ – but this discards a complementary signal: whether the model can consistently rank competing reasoning candidates. We propose structural uncertainty, a consistency-aware framework derived from the stability of self-preference-induced rankings over sampled reasoning solutions. Given a query, we generate multiple candidate solutions and ask the model to judge pairwise preferences among its own outputs. We aggregate self-preferences into ranking distributions via Bradley-Terry modeling with PageRank, and decompose the signal into two entropy-based components: across-trial ranking instability and within-trial candidate ambiguity. Across five LLMs and eight benchmarks, structural signals provide information complementary to answer dispersion: on logical and mathematical reasoning tasks, the combination improves identification of unreliable instances, while on factual retrieval the structural signal collapses toward uniformity, diagnosing a regime boundary where reasoning-level consistency evaluation is uninformative. The two components relate differently to accuracy: within-trial ambiguity correlates positively with correctness – consistent with settings where multiple plausible solution paths remain competitive – while across-trial instability correlates negatively, signaling unreliable reasoning. Structural uncertainty is best understood not as a universal confidence estimator, but as a regime-sensitive evaluator of logical reasoning consistency.

阅读与讨论 → 访问原文 →

18.

arXiv (CS.AI) 2026-06-15 DOI: arXiv:2606.13705

Can Editing 1 Neuron Fix Repetition Loops in LLMs?

作者:

Aristotelis Lazaridis↗Aman Sharma↗Dylan Bates↗Brian King↗Vincent Lu↗Jack FitzGerald↗

arXiv:2606.13705v1 Announce Type: cross Abstract: Yes. Can it cure doom loops? Probably not. The Gemma 4 instruction-tuned models share a reproducible failure: on long factual enumeration prompts, such as listing every episode of a TV series, the 88 IAU constellations, or the 151 original Pokemon, they collapse into repetition, either a tight verbatim loop or a list whose entries decay onto a single answer. These loops occur at rates as high as 95% and survive prompt rewording, inference-engine changes, and most sampling adjustments. In this paper we explore whether this behavior is localized enough to remove by weight edits. To localize the cause, we use per-layer ablation and per-neuron attribution, then confirm the strongest candidates with full-generation sweeps. The loops trace to a small set of MLP neurons (or, in the 26B-A4B Mixture-of-Experts model, a few routed experts) which we suppress with static weight edits. These "surgeries" can be as small as a single sign-inverted neuron (in the E2B model). The size of the effective edits grows with model scale, but in all cases, the loop patterns can be addressed at normal generation budgets while preserving general-purpose benchmark scores. However, the edits do not solve everything: we also study longer thinking budgets, where the two larger models most visibly enter doom looping, i.e. a non-convergent regime in which the model self-corrects in circles over a fact it cannot recall, exhausting the budget without committing to a final answer. We show this residual failure is reduced but not eliminated by the same edits, and argue it is fundamentally a knowledge-precision problem rather than a removable circuit; weight surgery can delete a loop, but it cannot supply a missing fact. Our results are both a feasibility demonstration, that is, evidence that a concrete generation pathology can be localized to a few parameters and edited out, and a delineation of where that approach stops.

阅读与讨论 → 访问原文 →

19.

arXiv (CS.CV) 2026-06-11 DOI: arXiv:2605.16651

Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations

作者:

Narges Babadi↗Hadis Karimipour↗

Explanation mechanisms are increasingly used to support transparency and trust in vision-language models (VLMs), particularly in settings where model decisions require human oversight. However, the robustness of these explanations remains insufficiently understood. In this work, we investigate whether explanation heatmaps in VLMs, particularly CLIP-based models, faithfully reflect model reasoning under adversarial conditions. We show that explanation maps can be systematically manipulated while preserving the model's original prediction, revealing a disconnect between predictive behavior and explanation faithfulness. To study this vulnerability, we introduce X-Shift, a novel grey-box attack that perturbs patch-level visual representations to redirect explanation heatmaps toward semantically irrelevant regions without altering the predicted output. Unlike conventional adversarial attacks that aim to induce misclassification, X-Shift specifically targets the integrity of the explanation process itself. The attack operates without modifying model parameters and generalizes across multiple CLIP architectures and explanation methods. We evaluate the proposed approach on ImageNet-1k, MS-COCO, and Flickr30K, demonstrating consistent degradation in explanation alignment under imperceptible perturbations while maintaining prediction stability. Furthermore, standard prediction-oriented adversarial attacks fail to reproduce the same explanation-shifting behavior even under substantially larger perturbation budgets. Our findings highlight a fundamental limitation of current explanation mechanisms in VLMs and raise concerns about their use as reliable indicators of model trustworthiness in high-impact applications.

阅读与讨论 → 访问原文 →

20.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.16298

DDTNet: Degradation Disentanglement and Transfer Network for Test-Time All-in-One De-weathering Adaptation

作者:

Kuan-Hung Lin↗Fu-Jen Tsai↗Yan-Tsung Peng↗Min-Hung Chen↗Chia-Wen Lin↗Yen-Yu Lin↗

All-in-one adverse weather image restoration aims to remove multiple degradations, such as rain, haze, and snow, using a single unified model. Despite their broad applicability, existing methods typically compromise performance, delivering balanced but suboptimal results for individual degradation types. This issue becomes more pronounced when a domain gap exists between training and testing data. Motivated by the observation that modeling degradation patterns is more feasible than recovering clean content, we propose the Degradation Disentanglement and Transfer Network (DDTNet), which focuses specifically on degradation transfer. By disentangling degradation patterns from target-domain degraded images and transferring them to source domain clean images, DDTNet generates domain-adaptive paired training data. These pairs are then used to fine-tune restoration models, significantly enhancing their adaptability across diverse weather conditions and domains. The core of DDTNet is the Degradation Disentanglement Module (DDM), which comprises Degradation Coupled Attention (DCA) to capture both general and weather-specific features, thereby enabling effective disentanglement and transfer of degradation patterns. Experimental results demonstrate that DDTNet significantly and consistently improves existing all-in-one models across real-world deraining, desnowing, and dehazing datasets.

阅读与讨论 → 访问原文 →

21.

arXiv (CS.CL) 2026-06-18 DOI: arXiv:2606.18889

Improving Medical Communication using Rubric-Guided Counterfactual Recommendations

作者:

Adrian Cosma↗Nicoleta-Nina Basoc↗Andrei Niculae↗Cosmin Dumitrache↗Emilian Radoi↗

Text-based telemedicine increasingly relies on lightweight patient feedback, however, such feedback primarily reflects perceived communication quality rather than medical accuracy. We introduce an LM-guided counterfactual recommendation pipeline that discovers and refines interpretable communication features such as tone, personalization, actionability and completeness in addressing patient concerns, without interfering with the medical content. These features are used together with patient-doctor interaction metadata to estimate positive feedback. At inference time, the system searches over low-cost ordinal feature changes and recommends minimal communication changes predicted to increase the probability of positive feedback, while independent auditor models test whether these gains generalize beyond the selection model. Across interactions, recommendations yield a mean +6.41% gain in predicted positive feedback probability under independent auditors, and are non-negative for 93.31% of recommendations. These results suggest that small, interpretable communication changes can capture most predicted gains while preserving the doctor's control over medical reasoning and final wording.

阅读与讨论 → 访问原文 →

22.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2512.18725

ML Inference Scheduling with Predictable Latency

作者:

Haidong Zhao↗Nikolaos Georgantas↗

arXiv:2512.18725v3 Announce Type: replace Abstract: Machine learning (ML) inference serving systems can schedule requests to improve GPU utilization and to meet service level objectives (SLOs) or deadlines. However, improving GPU utilization may compromise latency-sensitive scheduling, as concurrent tasks contend for GPU resources and thereby introduce interference. Given that interference effects introduce unpredictability in scheduling, neglecting them may compromise SLO or deadline satisfaction. Nevertheless, existing interference prediction approaches remain limited in several respects, which may restrict their usefulness for scheduling. First, they are often coarse-grained, which ignores runtime co-location dynamics and thus restricts their accuracy in interference prediction. Second, they tend to use a static prediction model, which may not effectively cope with different workload characteristics. In this paper, we evaluate the potential limitations of existing interference prediction approaches, finding that coarse-grained methods can lead to noticeable deviations in prediction accuracy and that static models degrade considerably under changing workloads.

阅读与讨论 → 访问原文 →

23.

arXiv (CS.LG) 2026-06-16 DOI: arXiv:2606.16023

IBAD: Interpretable Behavioral Anomaly Detection on Human Mobility Data

作者:

Bita Azarijoo↗John Krumm↗Cyrus Shahabi↗

arXiv:2606.16023v1 Announce Type: new Abstract: Human mobility appears highly diverse, yet much of a person's daily mobility can be explained by a small set of recurring behavioral templates, such as commuting, school-centered activities, caregiving, nightlife, or errand patterns. We present \texttt{IBAD} (\underline{I}nterpretable \underline{B}ehavioral \underline{A}nomaly \underline{D}etection), a framework that learns interpretable daily mobility templates and represents each individual as a distribution over mixtures of these templates. Rather than focusing on specific locations, IBAD characterizes activities that individuals perform across locations. This approach first discovers global behavioral templates using Latent Dirichlet Allocation (LDA), then employs a hierarchical self-supervised model to learn normal behavior of individuals from their soft behavioral templates. We also introduce a splicing benchmark that creates controlled behavioral mismatches between an individual's historical profile and injected mobility patterns. Experiments on real-world and synthetic datasets show that daily behavior can be effectively decomposed into a small number of interpretable templates. Crucially, we show that the learned behavioral archetypes transfer across distinct geographic and demographic contexts. Furthermore, IBAD maintains a robust competitive performance across all settings. For reproducibility purposes, the code is accessible at ~\href{https://github.com/USC-InfoLab/IBAD}{https://github.com/USC-InfoLab/IBAD}.

阅读与讨论 → 访问原文 →

24.

arXiv (CS.CV) 2026-06-16 DOI: arXiv:2606.09150

Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions

作者:

Luxury↗Jie Huang↗Zihao Fan↗Xiaoxiao Ma↗Jun-hao Zhuang↗Yuming Li↗Zeyue Xue↗Siming Fu↗Haoran Li↗Mingchen Zhong↗Guohui Zhang↗Shichen Ma↗…

While recent autoregressive video diffusion models achieve remarkable streaming quality, they remain confined to low resolutions (e.g., 480P), leaving efficient, scalable, real-time high-resolution video generation a fundamental open challenge. To bridge this gap, we present Ultra Flash, a cascaded streaming framework capable of real-time high-resolution video generation. Ultra Flash achieves ~30 FPS at 1K resolution and ~18 FPS at 2K resolution on a single GPU through three key contributions: (1) an architecture-preserving T2V-to-TV2V super-resolution training paradigm coupled with an AIGC-oriented data degradation pipeline that effectively preserves the generative capability of the base model, enabling enhanced high-resolution detail when cascaded after mainstream low-resolution generative models; (2) a causal streaming latent upsampler paired with a high-resolution decoder, which enhances spatiotemporal coherence while enabling efficient latent spatial scaling and precise high-resolution decoding with negligible computational overhead; and (3) a cascade high-resolution streaming video generation optimization scheme that first performs hybrid-reward-enhanced sparse causalization and single-step distillation of the super-resolution model, then introduces cascaded streaming self-forcing preference optimization with dynamic cache management, jointly enhancing overall coherence, improving quality, and enabling real-time high-resolution streaming video generation. Extensive experiments demonstrate that Ultra Flash reliably produces ultra-high-resolution streaming video while maintaining state-of-the-art visual quality and superior efficiency. Project Page: https://xin1u.github.io/UltraFlash/

阅读与讨论 → 访问原文 →

25.

PLOS Computational Biology 2026-06-15 DOI: HASH:4da4e9508751e62538097eab4d2ad8f4

WormSORT: A detection-based multiple object tracking model for individual silkworms in breeding environments

作者:

Hongkang Shi↗

by Hongkang Shi, Linbo Li, Shiping Zhu, Haibo He, Minghui Zhu, Jianfei Zhang Variety breeding has long been a cornerstone of high-quality agriculture, and recent advances in artificial intelligence have opened new avenues for accelerating biological breeding. In this study, we applied multiple object tracking (MOT) technology to silkworm breeding to achieve efficient, non-invasive, and dynamic individual monitoring. Unlike pedestrian or vehicle tracking, silkworms pose unique challenges for MOT due to their small size, dense distribution, and high inter-individual similarity, which complicate accurate tracking and behavioral analysis. To address these issues, we propose WormSORT, an enhanced tracking method based on a tracking-by-detection framework with an optimized data association strategy. A pre-trained detection model identifies silkworms in each frame, and deep feature vectors are extracted using a re-identification network. Identity association is first performed using Intersection over Union (IoU) matching, followed by deep feature similarity for unmatched cases, improving both tracking accuracy and reliability. To further enhance tracking stability, we introduce a candidate input padding mechanism, including IoU padding and feature padding, ensuring that high-confidence unmatched trajectories and detections remain involved in the matching process. To validate the proposed tracking strategy, we constructed two multiple silkworm tracking (MST) datasets: MST-50, containing approximately 50 individuals over 1000 frames, and MST-100, containing approximately 100 individuals over 1200 frames. Experimental results demonstrate that WormSORT outperforms existing methods, including DeepSORT, StrongSORT, OCSORT, ByteTrack, and BotSORT, achieving superior tracking performance. This study provides a valuable reference for silkworm tracking and behavioral analysis, contributing to the advancement of high-quality silkworm rearing and management.

阅读与讨论 → 访问原文 →