跳到正文
研踪PaperTrail

版本更新

查看已发布论文的最新修订，在详情页对照实际观测到的版本。

部分采集异常

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+93新增 AI 导读

arXiv 最近完成扫描：2026-11-16 01:34 · 全站最近入库：2026-11-14 15:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-15 02:23 — 2026-11-16 02:23（北京时间） · 点击数字查看对应简报；AI 相关包含在新增论文内。

最近完成检查：2026-11-16 01:34最近发现新增版本：2026-11-14 15:09库内论文最新更新时间：2026-11-13 02:59

每分钟刷新已保存的数据。空检查不代表采集异常；新收录可能包含历史论文。AI 导读按新增版本计数。

23,348 已收录论文19,580 AI 相关6,729 有修订112 HF 社区发现

论文修订列表

研究日报 / 周报 →按信源浏览 →

时间范围跟随排序：版本更新、本站收录或首次发表。最新收录可能包含历史论文。部分信源异常，查看状态 →

找到 6,729 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-16 01:33（北京时间）
版本更新 · v4arXiv:2210.06116

Self-stabilization and Byzantine Tolerance for Maximal Independent Set

Johanne Cohen, Laurence Pilard, François Pirot, Jonas Sénizergues

原文摘要

We analyze the impact of transient and Byzantine faults on the construction of a maximal independent set in a general network. We adapt the self-stabilizing algorithm presented by Turau for computing such a vertex set. Our algorithm is self-stabilizing and also works under the more difficult context of arbitrary Byzantine faults. Byzantine nodes can prevent nodes close to them from taking part in the independent set for an arbitrarily long time. We give boundaries to their impact by focusing on the set of all nodes excluding nodes at distance 1 or less from Byzantine nodes, and excluding some of the nodes at distance 2. As far as we know, we present the first algorithm tolerating both transient and Byzantine faults under the fair distributed daemon. We prove that this algorithm converges in $ \mathcal O(Δn)$ rounds w.h.p., where $n$ is the number of nodes and $Δ$ is the maximum degree of the network. Additionally, we present a modified version of this algorithm for anonymous systems under the adversarial distributed daemon that converges in $\mathcal O(n^{2})$ moves both in expected value and with high probability.

cs.DC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.28542

Policy-Controlled Offline-Verifiable Accountability for Cross-Organization Agent Messaging: A Preserved Evidence-Bundle Approach

Adil Alshammari, Hayretdin Bahsi

原文摘要

Cross-organization agent workflows require preserved evidence that remains independently verifiable during later audit or dispute review. Such workflows may involve multiple organizations, delegated actions, policy-relevant events, and disputed accountability claims. This is difficult when live systems are unavailable, controlled by one party, or not trusted by all participants. Existing mechanisms provide useful pieces, including authenticated logging, delegation semantics, signed checkpoints, and consistency checks. What remains missing is a verifier-centered event-level bundle for checking evidence sufficiency offline under an explicit policy. We propose a preserved evidence-bundle model and a policy-controlled offline verifier for agent-to-agent workflow events. Each bundle preserves policy-required evidence, including sender authentication, authenticated log commitment, witness-backed checkpoint evidence, append-only continuity, delegation-aware authorization evidence, and, when issued and required by policy, explicit receiver-signed receipt evidence. The verifier accepts a bundle only when all mandatory and policy-required checks succeed, giving a later dispute reviewer an offline basis for assessing evidence sufficiency. It does not infer delivery or receipt from transport behavior or log inclusion alone. In a prototype evaluation, the event-type study used 300 synthetic four-event healthcare workflow cases and 1200 valid preserved bundles. The policy-profile comparison observed its largest median latency reduction relative to the fully enabled profile when checkpoint-context validation was disabled. All 17 tested cases in the original negative-evidence diagnostic suite were rejected under the fully enabled profile. Additional functional studies examined context and signed-reference binding. These results support prototype feasibility for the evaluated workloads.

cs.CR · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.28856

Depth-guided Geometric Adaptation for Few-shot Image Classification

Zhiqi Miao, Estefanía Talavera, Weichuan Zhang, Jiapan Guo

原文摘要

Few-shot image classification (FSIC) frequently suffers from visual ambiguity, where background clutter and RGB appearance similarities hinder discriminative feature matching in data-scarce settings. To mitigate this, we propose DAFIC, a geometry-guided framework that incorporates monocular depth into representation learning, episodic adaptation, and dense support-query matching. DAFIC first learns geometry-aware token representations through RGB-D self-supervised pre-training. Subsequently, the Depth-guided Geometric Adaptation (DGA) module uses depth-derived geometry to refine patch representations with geometry-enriched class context while suppressing background interference. Spatial Bidirectional Patch Matching (SBiM) then performs bidirectional dense matching on the refined features, reducing sensitivity to spurious correspondences and background clutter. Extensive experiments on four benchmarks show that DAFIC achieves strong performance against existing methods, with ablation and robustness analyses supporting the effectiveness of coupling geometry-conditioned episodic adaptation with bidirectional matching for few-shot visual recognition.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.08874

Do Reasoning LLMs Refuse What They Infer in Long Contexts?

Yu Fu, Haz Sameen Shahgir, Huanli Gong, Zhipeng Wei, N. Benjamin Erichson, Yue Dong

原文摘要

Long-context LLMs can infer objectives that are not explicitly stated. This capability is useful for reasoning over documents, code, and tool traces, but it also introduces a safety risk. Harmful intent can be distributed across a context and become apparent only after the model combines the relevant information. Existing safety evaluations largely focus on explicitly stated harmful requests and therefore do not fully capture this failure mode. We introduce compositional reasoning attacks, a long-context attack setting in which harmful requests are decomposed into semantically incomplete fragments and embedded in long contexts. The final query is neutral, and the model must retrieve and combine the fragments to infer the implied harmful objective. Empirically, we show that models generally refuse harmful requests when they are explicitly stated. However, refusal rates drop when the same objectives must be reconstructed from fragments, and these failures often become more pronounced in longer contexts. Our analyses suggest that this gap cannot be explained by retrieval difficulties alone. Models can often reconstruct the harmful objective but do not reliably refuse it. Increasing inference-time reasoning effort improves refusal, but at a higher computational cost, with unsafe responses still occurring. Our results reveal a long-context safety gap: Models are better at refusing harmful requests they see than harmful objectives they infer.

cs.CL · cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.28480Berkeley BAIR

SuperMimic: Scaling Humanoid Whole-Body Control with One Differentiable World Model

Qiayuan Liao, Yiyang Shao, Junfeng Long, Kevin Zakka, Roberto Horowitz, Pieter Abbeel, Koushil Sreenath

原文摘要

Tracking large human-motion datasets has become the dominant route to general, expressive humanoid whole-body control, but scaling across many motions is expensive. Current pipelines use model-free reinforcement learning, either merging per-motion specialists through lossy distillation, or brute-forcing a single policy with cluster-scale compute. SuperMimic amortizes learning across all motions with one differentiable world model of their shared dynamics, fit from logged transitions of a standard rigid-body simulator. The world model and the tracking policy train together in one loop, and backpropagation-through-time over short imagined rollouts gives the policy analytic gradients. Fast imagined rollouts and analytic gradients make policy learning efficient. In 3 hours on a single GPU, SuperMimic surpasses the return of a state-of-the-art motion tracker baseline trained for 7 days on 128 GPUs. It reduces GPU-hours by more than $1000\times$ and fails on only 25 of 129,514 benchmark motions, versus 179 failures for the baseline. After 9.8 hours on two GPUs, SuperMimic achieves zero failures. From 1 to 264 hours of motion, the world model's prediction error stays stable, and GPU-hours to a target return grow slowly. Our policy transfers to a physical Unitree G1 across diverse and acrobatic motions. SuperMimic removes compute as the bottleneck to scaling humanoid whole-body control, making it practical to measure motion-tracking scaling laws.

cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00546

Low-Margin Branch Points in Deterministic LLM Deliberation

Hajime Shimao, Warut Khern-am-nuai

原文摘要

Deterministic multi-agent LLM deliberation can exactly re- play a fixed transcript, yet exact replay alone does not test local resistance to controlled internal interventions. Because each response becomes context for later agents, a changed greedy token can redirect a transcript-mediated execution. We present a white-box audit of this local failure mode in a five-agent committee under greedy decoding. We prospectively select low- and high-margin token positions, require exact no-op re- play, inject norm-relative residual displacements, and measure first transcript divergence within ten generated tokens. Low- margin positions are more branch-sensitive than high-margin controls, while matched margin-reducing gradient directions branch substantially more often than margin-increasing con- trols. We then continue selected realized branches through the committee to distinguish textual persistence from preference and final-decision changes. The contribution is a controlled audit for local branch susceptibility in this specified protocol, not an estimate of deployment frequency, decision correct- ness, or a phenomenon unique to multi-agent systems.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.00301

The Rise of Low Precision Floating Point

Guy Lemieux, Michael L. Overton

原文摘要

Floating point computing has dominated scientific computations since the 1950s because of its versatile ability to approximate real numbers with both sufficiently high precision and sufficiently great range. Since 1985, two specific formats have become standard across the industry, one with 32 bits which is adequate for many purposes and one with 64 bits which allows numbers with both much higher precision and much greater range for applications where these are needed. However, during the past decade, deep learning has come to dominate computation, and narrower floating point formats with lower precision and reduced range have steadily become more common. In this article we discuss this phenomenon, why it is happening, how various 16-bit, 8-bit and even 4-bit floating point formats have been developed, and efforts to standardize these formats.

cs.MS · cs.AR · cs.LG · math.NA

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2610.29929

Privacy Preference Controls for Agentic Systems

Shreya Kochar, Peeranat Sugsavanvit, Vidur Gupta, Joseph A. Calandrino, Deepak Kumar, Brett Frischmann, Sebastian Zimmeck

原文摘要

In response to vast and widespread online tracking, regulators and technologists alike have worked to develop laws and tools that allow people to express their privacy preferences. These measures seek to offer users greater control over the sale and sharing of personal information, putting agency in their hands to protect their privacy. However, the web is undergoing a seismic shift, away from strictly user-driven behavior towards agentic behavior, where AI agents take autonomous actions on behalf of users. In this study, we ask: What should privacy preference controls look like in the agentic web and agentic systems more generally? To answer this question, we develop a taxonomy of enforceable privacy preferences for agentic systems. Our taxonomy is informed both by laws and empirical studies of existing privacy tools as well as an audit of 30 leading AI assistants and agent platforms. To explore how our taxonomy can be implemented, we design and develop eight open-source prototypes that mirror real-world agentic applications and demonstrate how major aspects of our taxonomy can be structurally integrated in agentic protocols, such as the Model Context Protocol and Agent2Agent protocol. Ultimately, our study seeks to provide the groundwork for ensuring end-user privacy and autonomy is not lost in the newly arriving agentic world.

cs.CY · cs.HC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.10342

Shape optimisation of nonlinear Naghdi shells on discrete geometries

Ado Farsi, Alberto Paganini

原文摘要

We present an automated framework for the shape optimisation of a geometrically nonlinear, five-parameter Naghdi model on faceted triangulations. By recovering directors numerically, we remove the requirement for an analytic or spline parameterisation of the mid-surface, whereas partial selective reduced integration alleviates locking. The residual and tangent of symbolic energies are generated in an automated fashion building on Firedrake's and UFL's symbolic differentiation capabilities. Additionally, UFL's and pyadjoint's algorithmic differentiation enables automated first and second shape derivative evaluations that are verifiably correct via Taylor tests. The forward model agrees with the Sze/Abaqus semi-cylinder reference. A three-model mesh-refinement study indicates that geometry recovery and surface faceting have small effects on the predicted deflection. Numerical experiments show that 100 trust-region iterations suffice to reduce the squared-displacement functional of a semi-cylinder by 98.4% and the elastic strain energy of a bracket by 94.6%. The latter result is validated against a COMSOL benchmark. Non-uniqueness of optimal shapes is demonstrated by optimising initial designs subject to small perturbations. Comparisons with linearised designs distinguish optimisation performance from the accuracy of the predicted nonlinear response.

math.NA · cs.CE

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2509.26282

Benchmarking Stochastic Interpolants for Modeling Physical Systems

Anthony Zhou, Alexander Wikner, Amaury Lancelin, Pedram Hassanzadeh, Amir Barati Farimani

原文摘要

Generative models have recently emerged as powerful surrogates for physical systems, demonstrating increased accuracy, stability, and/or statistical fidelity. However, most approaches rely on iteratively denoising a Gaussian, a choice that may not be the most effective for autoregressive prediction tasks, where the current and future states are often closely related. We therefore benchmark generative models based on stochastic interpolants, which can learn maps between arbitrary densities, against standard Gaussian-denoising frameworks across a range of fluid and climate systems. Following prior work, we consider a transport map for dynamical systems that learns an interpolant between a point mass at the current state and a conditional distribution of future states. We find that stochastic interpolants can match or outperform Gaussian-denoising baselines in pointwise accuracy, spectral fidelity, and probabilistic skill. Furthermore, we identify a tradeoff where deterministic sampling can improve pointwise accuracy but smooth predictions, whereas stochastic sampling recovers spectral content and calibration but requires more function evaluations, as well as ensemble averaging to recover pointwise accuracy. As a whole, these results establish stochastic interpolants as a competitive baseline for generative physical emulation, and also indicate that the training loss, sampler, and transport map should be chosen with the physical system and target metric in mind.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.09505

BEiTScore++: Reference-free Image Captioning Evaluation with BEiT-3 and Conformalized Quantile Regression

Gonçalo Gomes, Bruno Martins, Chrysoula Zerva

原文摘要

Reliable uncertainty estimation is important for deploying evaluation metrics in real-world settings, where both input ambiguity and domain shifts are common. In this work, we propose an uncertainty-aware extension of the BEiTScore image captioning metric, producing conformally calibrated confidence intervals alongside alignment scores. Our approach models predictive distributions over human judgments, enabling both accurate scoring and principled uncertainty quantification in a single forward pass. We evaluate our BEiTScore++ metric across multiple benchmarks with human-annotated ratings, showing that it preserves the ranking correlation of BEiTScore, while producing intervals whose width tracks the prediction error more closely than Monte Carlo dropout on most benchmarks. The estimated uncertainty also grows under image degradation and on out-of-domain artwork images, making BEiTScore++ a practical tool for uncertainty-aware evaluation of image-caption alignment.

cs.CV · cs.AI · cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.20436

Lighting-aware Unified Model for Instance Segmentation

Qisai Liu, Alloy Das, Zhanhong Jiang, Joshua R. Waite, Aditya Balu, Adarsh Krishnamurthy, Soumik Sarkar

原文摘要

Foundation models like the Segment Anything Model (SAM) demonstrate impressive zero-shot generalization but frequently degrade under diverse real-world illumination, particularly for instance segmentation. In this work, we address this limitation by developing Lighting Convolutional-Attention (LCA), an adapter module that enhances segmentation robustness without fine-tuning the heavy backbone. LCA employs a dual-branch architecture to process RGB features alongside contrast maps, enabling physically motivated sensitivity to structural changes rather than illumination artifacts. We optimize LCA through a pairwise training strategy, introducing a targeted loss term that explicitly penalizes discrepancies between clean images and their corresponding illumination variants. To evaluate and support this architecture, we conduct a comprehensive empirical study across multiple existing benchmarks and present a novel Unity-based synthetic dataset specifically designed to accurately replicate complex real-world lighting conditions. Extensive experimental results demonstrate that our approach successfully bridges the domain gap, delivering superior lighting-robust segmentation.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.35658

A Hybrid Framework for Explainable Aviation Risk: Causal Chain Extraction from Safety Reports with Physics-Based Failure Quantification and Interventional Analysis

Yutian Pang, Yifang Tian, Xinyu Zhao, Jueming Hu, John-Paul Clarke, Hans-Arno Jacobsen

原文摘要

Aviation authorities hold decades of accident reports whose narratives record how investigators reconstructed each accident. Computational work on these archives has mostly sorted reports into fixed taxonomies. In this work, we propose a hybrid framework in which a text-based corpus identifies the leading factors of a failure mode. Physics-based models then quantify how likely that failure is at a stated operating point. Ordered causal chains extracted from 56,202 American accident reports with a local large language model aggregate into a causation knowledge graph. On an evaluation sample of 2,000 reports, the chains recover 90.8% of investigator-flagged causes. Each physical factor whose drivers the record carries receives an occurrence model calibrated to the accident population. A leaky noisy-OR fitted to the corpus combines the factors into a failure mode probability that supports intervention. For engine power loss, the carburetor icing model separates 1,205 icing accidents from other accidents using temperature and dewpoint alone, reaching 0.61 in area under the receiver operating characteristic curve against a density ratio ceiling of 0.64. Routine weather hours give no valid control, because flying concentrates in fair weather. On later years the physics adds 0.03 to that area for occurrence and nothing for severity, so its value lies in interpretability. On four named accidents, abduction gives a probability of necessity of 0.29 to 0.50 for the heat omission, under monotonicity. The Fast Causal Inference algorithm does not license the largest backdoor adjustment on the learned networks.

cs.LG · eess.SY · stat.AP

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2610.04542

Decide, Ask, or Defer: Clinical LLMs under Incomplete Evidence

Mingzhan Yang, Weili Wu

原文摘要

Clinical LLMs must decide not only what diagnosis to produce, but also whether the available evidence is sufficient for autonomous decision making. Binary DECIDE/ABSTAIN formulations merge distinct non decision states and do not explicitly evaluate information acquisition. We introduce a DECIDE/ASK/DEFER formulation together with a blinded protocol that prevents models from using evidence completeness metadata. We evaluate Qwen, Gemini, and GPT on 200 matched clinical evidence states constructed from DDXPlus. The models show substantial differences in action selection under identical evidence, with disagreement in 137 of 200 states. For Qwen, a matched targeted versus random analysis shows that selected information changes the likelihood of a subsequent autonomous decision more clearly than diagnostic correctness. Its matched DECIDE/ABSTAIN baseline further reveals a safety autonomy tradeoff: the three action policy rescues some erroneous autonomous decisions but also removes some correct autonomous deci sions. These results show that separating information acquisition from clinician deferral exposes behavior that binary abstention hides, without yielding a uniformly improved decision policy.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2605.30608

Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures

Varsha Suresh, Mohammad Mahdi Abootorabi, Mohamed Salman, M. Hamza Mughal, Christian Theobalt, Ashwin Ram, Jürgen Steimle, Vera Demberg

原文摘要

Learning a shared representation between spoken text and gesture is central to co-speech gesture retrieval, synthesis, and understanding, but remains challenging for semantically meaningful gestures whose communicative intent is not captured by motion alone. Direct contrastive alignment between transcripts and continuous motion embeddings often overemphasizes low-level kinematics and misses the symbolic content of semantic gestures. We propose semantic motion anchors, natural-language abstractions of gesture motion capturing physical form and communicative intent. Our method discretizes 3D gestures into body-hand motion primitives, verbalizes them into structured descriptions, and grounds them in the transcript to provide auxiliary contrastive supervision. On BEAT2, our method improves text-to-gesture R@1 by 8.2% over a direct text-motion baseline and outperforms prior retrieval approaches on text to gesture and gesture to text retrieval directions. Beyond aggregate retrieval metrics, semantic motion anchor supervision helps retrieve gestures that are semantically meaningful for the spoken query, rather than defaulting to generic motion patterns. A downstream retrieval-augmented gesture generation study showed that users significantly preferred gestures retrieved by our approach over a retrieval-augmented generation baseline, demonstrating that semantically grounded retrieval translates to gestures that better convey communicative intent in downstream generation.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.05664

Combining Relevant Expert Knowledge Using Mixtures of Feedback Fuzzy Cognitive Maps

Olaoluwa Adigun, Akash Kumar Panda, Bart Kosko

原文摘要

A neuro-symbolic system should combine only relevant answers from expert agents or other knowledge sources. Using only relevant experts for a given input query becomes ever more important for accuracy and scalability as the knowledge network grows and connects ever more knowledge sources. We extend the standard definition of relevance from the legal theory of evidence: An answer is relevant if and only if it is both probative and material for the matter at hand given the knowledge available. We apply this relevancy scheme to mixing the feedback fuzzy cognitive maps (FCMs) of real or artificial experts. The expert FCM directed causal graphs mix or combine into a common knowledge network. We compare the equilibrium limit-cycle predictions or answers of the experts to the answers of the mixture FCM and then estimate the probative status of answers by their difference or variation. A new Bayes-like theorem de-mixes the knowledge mixture into corresponding posterior-like FCMs that also allow relevancy-based comparisons. The result is a final set of relevancy mixing weights that produces a relevancy-mixed FCM knowledge network for the given query. So different queries produce different relevancy-mixed FCMs. We demonstrate this relevancy approach using generated synthetic FCMs from an actual 13-node expert FCM that models the causes and feedbacks of ischemic-stroke risk.

cs.AI · cs.IR · cs.SC

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.09794

Seeing What Execution Needs: Benchmarking Task-Conditioned Actionable Spatial Belief for Manipulation

Yina Jian, Mingkun Xu

原文摘要

When should a robot look at the cup, and when at the portafilter? A view that is informative for one task can be useless for another, even at the same workstation. We introduce Seeing What Execution Needs, a benchmark for task-conditioned actionable spatial belief in simulated tabletop manipulation. Its aligned three-domain track contains 1,080 frozen cases (360 each for coffee workstation, drawer/cabinet, and microwave/appliance). The primary coffee protocols -- closed-loop actionability and same-object functional out-of-distribution generalization -- produce over 115,000 evaluator episodes across evaluated methods, budgets, and inference repeats. Each case pairs candidate RGB views with a manipulation command, shared scripted skills, and hidden postconditions, directly measuring whether selected observations support execution. A metadata-assisted diagnostic reference pipeline maintains spatial-functional beliefs and ranks views by missing evidence. At primary budget settings, it reaches 98.8% closed-loop and 98.9% functional-OOD success; removing functional fields or command binding reduces functional-OOD success to 0.0% and 19.7%, respectively. Under a separate full-preview contract, seven vision-language models reach 26-43%. Replacing coverage metadata with frozen RGB-derived scores retains 98.5%/98.9% success; shuffling these scores reduces success to 15%/11%, supporting dependence on image content. Separately, the aligned three-domain evaluation at H=3 supports portability of the benchmark interface under frozen domain-specific schemas. These results suggest that spatial belief for manipulation should be evaluated by whether acquired evidence meets the current command's execution requirements.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.31235

Purin: A Biology-inspired Mechanism for Artificial Neural Networks

Zishu Liu, Chunbo Luo, Christos Grecos

原文摘要

Artificial neural networks (ANNs) usually represent neural transmission with fixed trainable weights during a training batch, which omits short-term changes in synaptic efficacy. In addition, the discrete time-step simulation requires additional temporal processing that many conventional ANN architectures do not use. To overcome these challenges, we propose Purin, a biology-inspired and ANN-compatible mechanism, that introduces synaptic efficacy modulation into conventional convolutional neural networks. Purin uses a time-interval-based abstraction for neural activities, which allows Purin to introduce short- and long-term synaptic efficacy changes without using discrete time-steps. Purin introduces a bounded factor to represent temporary synaptic efficacy changes, together with two weight matrices that represent input-side and output-side efficacy. The weight matrices are updated by backpropagation and interpreted as the long-term synaptic efficacy changes. Experimental results show that after removing the confounding factors in the AlexNet, VGG11, and GoogLeNet architectures, Purin improves the classification accuracies in all three models across the evaluated datasets.

cs.AI · cs.NE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2606.07537

From Architecture to Output: Testing the Structural Origins of Hallucination and the Amplifying Role of Data

Md. Rejaul Korim Sadi, Toufiqur Rahman Tasin, Golam Mostofa Naeem

原文摘要

Surveys of hallucination classify errors by how an output relates to its source, and often explain them by the model's structure: attention retrieves by association, the maximum-likelihood objective has no term for truth, and left-to-right decoding commits to early tokens. Data, on this account, makes these failures worse rather than causing them. The account is usually argued rather than tested. We test it with interventions that need only sampling access. Study 1 holds pretraining data, tokenizer and scale fixed and swaps attention for a state-space mixer, using five Pythia/Mamba pairs from 130M to 2.8B parameters and four further attention models, on 111 facts presented with a planted false or a planted true statement. Swapping the mixer leaves free-recall failure unchanged (both 2.8B models answer 3 of 200 SimpleQA questions), but it changes what happens to a defect in the input. From 410M upwards, every attention model repeats the planted falsehood more often than its matched state-space model (2.8B: 650 vs. 566 of 666 items, p = 2.5e-20), also on facts both models know, while the state-space models can still read planted facts they did not know. Study 2 replaces the first wrong fact in 111 erroneous answers from three instruction-tuned models. The correct fact cuts the share of answers with a downstream error from 92.5% to 48.1%, but a different wrong fact works as well (p = 0.38), and the models give the right answer in isolation on only 2 of 111 items. The structural account survives in a narrower form. The mixing component decides whether a defect in the context becomes an output error, commitment decides how an error spreads, and on long-tail questions the first error comes from missing knowledge, not from a suppressed truth.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.21317

CRAFT: Conflict-Resolved Aggregation for Federated Training

Ziqi Wang, Qiang Liu, Nils Thuerey

原文摘要

The aggregation of conflicting client updates remains a fundamental bottleneck in federated learning (FL) under heterogeneous data distributions. Naive averaging can produce a global update that improves the global objective while conflicting with specific clients, causing degradation for those clients. In this work, we propose CRAFT (Conflict-Resolved Aggregation for Federated Training), a new aggregation framework that treats the global update as a geometric correction problem. We formulate aggregation as finding the update closest to a reference direction while satisfying conflict-free alignment constraints. We derive a closed-form expression for the constrained optimization problem, avoiding the computational overhead of iterative solvers. Furthermore, we use a layer-wise adaptation to address conflicts at varying feature granularities. We provide a theoretical analysis showing that CRAFT promotes a common-descent structure and mitigates conflicts through its projection geometry. Extensive experiments on heterogeneous benchmarks demonstrate that CRAFT improves the accuracy of the global model while reducing performance disparity across clients compared with state-of-the-art baselines. The source code for CRAFT is available at https://github.com/tum-pbs/CRAFT.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.05423

Characterising divergence between heuristic and language-model ratings of mobile user interface quality

Md Rejaul Korim Sadi, Golam Mostofa Naeem, Toufiqur Rahman Tasin, Syed Mostofa Moosa, Mahmudul Hasan Emon, Mahmudur Rashid, Ferdus Ahmed

原文摘要

Automated assessment of mobile user interface quality is attractive because manual review does not scale, and large language models are increasingly proposed for the task. Whether their ratings correspond to those produced by established rule-based heuristics has not been characterised at scale. We construct a 15,000-screen corpus from the RICO dataset using six documented filters, score every screen with a literature-grounded heuristic scorer, and collect ratings from three open-weight language models across two input representations, yielding 270,000 ratings. We report linearly weighted Cohen's kappa with bootstrap confidence intervals, offset-corrected kappa, intraclass correlation, and Bland-Altman limits of agreement, together with a chance baseline for the tolerance-band agreement rule. Agreement between the two rating sources is consistently weak: raw kappa falls below 0.15 in seventeen of eighteen model-representation-dimension cells. However, fifteen of eighteen cells are statistically distinguishable from zero, and correcting for a constant offset raises five cells above 0.15, so the divergence is better described as a combination of systematic bias and weak covariation than as absence of relationship. Model ratings track structural properties of the interface, but substantially less strongly than the heuristic does, and more strongly from an untruncated structural element list than from a screenshot. We further show that dimensions elicited in a single generated response are correlated by construction, reaching rho = 0.97 in one condition, which constrains what such designs can measure. We report these results as a characterisation of divergence between two automated raters rather than as evidence that either is correct, and we set out the validation a stronger claim would require.

cs.HC · cs.CL · cs.SE

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2507.00275

Deep Double Q-learning

Prabhat Nagarajan, Martha White, Marlos C. Machado

原文摘要

Double Q-learning is a classical control algorithm that mitigates the maximization bias of Q-learning. To do so, it explicitly trains two independent action-value functions and uses them to decouple action-selection from action-evaluation when computing bootstrap targets. Double DQN adapts this decoupling to deep reinforcement learning (RL) but directly trains only a single action-value function and does not fully decouple its estimators. Consequently, the two estimators remain correlated, and overestimation persists. In this paper, we introduce Deep Double Q-learning (DDQL), a deep RL algorithm that explicitly trains two Q-functions through the Double Q-learning objective. DDQL stabilizes training through a combination of techniques, including lower replay ratios, longer target network update intervals, and shared layers. Across 57 Atari 2600 games, DDQL improves aggregate performance over Double DQN, outperforming it on 47 games while further reducing overestimation. We study key design choices of DDQL, including its network architecture, replay ratio, and minibatch sampling strategies.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2601.16759

Curated endoscopic retrograde cholangiopancreatography images dataset

Alda João Andrade, Mónica Martins, André Ferreira, Tarcísio Araújo, Luís Lopes, Victor Alves

原文摘要

Endoscopic Retrograde Cholangiopancreatography (ERCP) is a key procedure in the diagnosis and treatment of biliary and pancreatic diseases. Artificial intelligence has been pointed as one solution to automatize diagnosis. However, public ERCP datasets are scarce, which limits the use of such approach. Therefore, this study aims to help fill this gap by providing a large and curated dataset. The collection is composed of 19.018 raw images and 19.317 processed from 1.602 patients. 5.519 images are labeled, which provides a ready to use dataset. All images were manually inspected and annotated by two gastroenterologist with more than 5 years of experience and reviewed by another gastroenterologist with more than 20 years of experience, all with more than 400 ERCP procedures annually. The utility and validity of the dataset is proven by a classification experiment. This collection aims to provide or contribute for a benchmark in automatic ERCP analysis and diagnosis of biliary and pancreatic diseases.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.06356

EEGDash Corpus: A Training-Ready Public Corpus for EEG Foundation Models

Kuber Shahi, Bruno Aristimunha, Arnaud Delorme

原文摘要

Electroencephalography (EEG) foundation models are pretrained on tens of thousands of hours. The largest clinical archives restrict redistribution, while public datasets use different formats and licences. Here, we rebuild the 77 redistributable datasets of the REVE pretraining corpus that reach its 200 Hz input (14,075 hours across 7,272 subjects) and release them as eegdash-corpus-v0, with raw-file access by name through EEGDash and a checksummed Zarr store on Hugging Face, converted with REVE's preprocessing recipe. Every dataset keeps its licence, and any subset of datasets can be selected by name. To test whether this public store pretrains REVE-Base, we train the model twice from scratch with REVE's trainer and score it on seven public OpenEEGBench tasks. First, under linear probing, the frozen encoder reaches 0.331 in chance-adjusted balanced accuracy, against 0.333 for the released model (untrained: 0.200), a difference smaller than the spread between our two pretraining seeds. Second, after fine-tuning, it reaches 0.273 against 0.325 published (0.301 in our rerun), and part of this gap comes from the scoring pipeline. A public, training-ready EEG corpus can therefore pretrain the frozen representations of a foundation model and provide a shared base that other groups can audit.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.32797

Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency

Xinhan Yang, Lu Lu, Shancong Mou

原文摘要

Derivative-informed training improves neural operators by directly supervising their input-output sensitivities, which is crucial when neural operators are used as differentiable surrogates for inverse problems, PDE-constrained optimization, design, and control. However, existing methods rely on offline-generated derivative labels, making data generation slow, storage-intensive, and difficult to adapt across datasets, resolutions, or perturbation bases. We propose sketched tangent consistency loss (sTCL), an on-the-fly derivative-informed training objective that, for PDEs with a known and differentiable residual, enforces sensitivity consistency directly from the governing equation without offline tangent labels or neural-operator architecture changes. sTCL uses randomly sketched input perturbations to provide a lightweight derivative-level physics constraint during training. However, raw forward-sensitivity residual penalties can fail for stiff, ill-conditioned, indefinite, or coupled saddle-point tangent operators. To address this, we introduce lightweight operator-aware loss-conditioning mechanisms selected by a simple tangent-operator decision rule. Across Helmholtz, nonlinear diffusion-reaction, Burgers, Allen-Cahn, and Navier-Stokes, with the same neural-operator backbone for all methods, the PDE-specific sTCL losses achieve solution and Jacobian accuracy comparable to offline derivative-informed training (DIFNO) while eliminating the offline derivative-data generation and storage pipeline. These results show that on-the-fly derivative-informed training need not merely amortize offline tangent-solve cost into training; with appropriate sketching and loss design, sTCL provides an effective drop-in path to derivative-informed neural operators. Code is available at https://github.com/Mou-group-UMN/Derivative-informed-training-on-the-fly.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2609.04698

LookThere! Sparse Vision by Reinforced Selection

Sreehari Rammohan, Yousef Yassin, Anthony Fuller, Junfeng Wen, Carl Vondrick, Evan Shelhamer

原文摘要

Vision transformers typically treat every image token as equally important, yet for most tasks in computer vision only a fraction are needed. Adaptive computation methods accelerate inference by choosing which tokens to process, but existing methods struggle at extreme sparsity and require heuristics that may not generalize like token diversity and attention scores. We address these limitations with LookThere, achieving a new pareto frontier in performance-compute trade-offs through an end-to-end reinforcement learning framework that jointly trains a shallow input selector and a deep representation extractor. The selector learns where to look and the extractor learns what to see, together saving computation by selecting only what is worth processing for a given task without relying on auxiliary signals. We show that LookThere only selects the task-specific input, excelling at sparse recognition in high-resolution settings (traffic signs, billiards), and maintaining accuracy with as little as 0.2% of the input. It generalizes across tasks and models, including global recognition (ImageNet classification), local recognition (ADE20K segmentation), zero-shot classification (by distillation), and regression (counting). Across all settings, LookThere surpasses state-of-the-art selection to provide a general and scalable framework for specialized and efficient adaptive computation.

cs.CV · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2410.07787

Learning Beyond Rigid Manipulation with Hybrid Soft-Rigid Robots

Mariano Ramírez Montero, Ebrahim Shahabi, Giovanni Franzese, Jens Kober, Barbara Mazzolai, Cosimo Della Santina

原文摘要

Rigid-soft robot hybrids promise to unite the precision and repeatability of rigid manipulators with the compliance and adaptability of soft structures. Yet, full-fledged rigid-soft manipulators remain largely unexplored, in part because the intelligence required to exploit this combination is still missing. Here, we introduce a hybrid robotic system obtained by the series interconnection of a rigid arm and a soft manipulator, and systematically examine its ability to perform both established and previously inaccessible manipulation tasks. We show that a tailored imitation learning algorithm -- generally applicable to this class of hybrid systems -- leverages the complementary roles of rigid precision and soft embodiment to acquire manipulation skills and generalize them in a single shot across task variations. As a result, the system matches or exceeds the performance of rigid robots in classical tasks such as stacking, while enabling qualitatively new behaviors, including grasping objects through narrow openings.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v7arXiv:2604.11581

Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking

Solomon Messing

原文摘要

LLM evaluations drive model deployment, safety standards, research conclusions, and future projections, for example, about AI's impact on the labor market. Yet the way we often estimate noise from autoraters (LLM-as-judge) ignores variability from factors like judge model choice and prompt phrasing, which means we're underestimating error in a way that worsens with more data. This unmeasured variance can affect results enough to reverse conclusions. And judge-pipelines that fail to average this variation are more vulnerable to "benchmark hacking". This paper introduces a framework we call "total evaluation error (TEE)," which decomposes LLM pipeline uncertainty and uses design-study projections to reduce total error. In our safety and ideology applications, naive standard errors are 53-70% smaller than the corrected SE under our TEE framework. Using Chatbot Arena data, we show naive 95% CI coverage drops as n grows, while TEE-corrected coverage holds at 95%, and TEE-guided pipelines restrict the potential range of benchmark gaming by roughly 43%. We show further that a small pilot allows for the estimation of proper CIs, with the added benefit of projecting which design changes most improve precision. Using those projections to allocate API calls cut MMLU estimation error roughly in half against the answer key at the same budget, and increased per-match agreement with human voters on Chatbot Arena by 7.9 percentage points.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2502.13297

Understanding and Tackling Label Errors in Individual-Level Nature Language Understanding

Yunpeng Xiao, Kyrie Zhixuan Zhou, Youpeng Zhao, Kai Shu

原文摘要

Natural language understanding (NLU) is a task that enables machines to understand human language. Some tasks, such as stance detection and sentiment analysis, are closely related to individual subjective perspectives, thus termed individual-level NLU. Previously, these tasks are often simplified to text-level NLU tasks, ignoring individual factors. This not only makes inference difficult and unexplainable but often results in a large number of label errors when creating datasets. To address the above limitations, we propose a new NLU annotation guideline based on individual-level factors. Specifically, we incorporate other posts by the same individual and then annotate individual subjective perspectives after considering all individual posts. We use this guideline to expand and re-annotate the stance detection and topic-based sentiment analysis datasets. We find that error rates in the samples were as high as 31.7\% and 23.3\%. We further use large language models to conduct experiments on the re-annotation datasets and find that the large language models perform well on both datasets after adding individual factors. Both GPT-4o and Llama3-70B can achieve an accuracy greater than 87\% on the re-annotation datasets. We also verify the effectiveness of individual factors through ablation studies. We call on future researchers to add individual factors when creating such datasets. Our re-annotation dataset can be found at https://github.com/24yearsoldstudent/Individual-NLU

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.17326

Evaluating Long-Horizon Robot Planning under Uncertainty

Harsh Muriki, Gayathri Aravindan, Yuchen Zheng, Sonia Chernova

原文摘要

Household robots must successfully navigate im-perfect circumstances, both in their internal models and the external world. We introduce a benchmark of seven long-horizon household tasks in Habitat that vary initial robot memory and environment configurations. We evaluate adaptations of ReAct, VLM-TAMP, and Tru-POMDP within a shared execution framework across 90 tasks-environment-memory combinations, totaling 1,350 episodes. Our evaluation measures task success, partial completion, and action efficiency, along with rule-based analysis of execution traces. ReAct achieves the highest overall task success (45.3%) and completion (71.7%), while having accurate initial memory does not consistently yield the highest performance for every planner. We identify recurring placement errors, precondition errors, and redundant actions through trace analysis. These findings highlight differences in how the evaluated planners use initial knowledge and respond to uncertainty.

cs.RO

查看论文
arXiv ↗PDF ↗