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

+907新增论文
+744其中 AI 相关
+108已有论文修订
+94新增 AI 导读

arXiv 最近完成扫描:2026-11-19 06:59 · 全站最近入库:2026-11-19 06:59各信源进度 →

统计口径与数据新鲜度

统计 2026-11-18 11:50 — 2026-11-19 11:50(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:2026-11-19 06:59最近发现新增版本:2026-11-19 06:59库内论文最新更新时间:2026-11-18 08:00

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。

26,871 已收录论文22,375 AI 相关8,156 有修订112 HF 社区发现

论文修订列表

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 8,156 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-19 06:57(北京时间)
版本更新 · v2arXiv:2512.04308

ResponsibleRobotBench: Benchmarking Risk-Aware Task-Level Decision Making for Robotic Manipulation with Large Multimodal Models

Lei Zhang, Ju Dong, Kaixin Bai, Minheng Ni, Yu Fu, Zoltan-Csaba Marton, Zhaopeng Chen, Jianwei Zhang

原文摘要

Safe task-level manipulation requires a planner to recognize hazards, select appropriate mitigation actions, and satisfy their execution prerequisites without abandoning the original goal. We introduce ResponsibleRobotBench, a benchmark of 23 manipulation task configurations with separately specified goals and safety conditions. It connects hazard-category predictions, planned actions, execution feedback, and terminal outcomes at the episode level. Across evaluations of five large multimodal models, terminal safety and safe task completion can diverge: defense prompts increase terminal safety for three tested models but affect safe success in different directions. Correct hazard-category predictions also fail to ensure executable mitigation. In a cutting task under the default configuration, GPT-4o mini identifies the human hazard in all 100 episodes but never requests assistance, and every episode ends unsafe. Offering a help action and actually requesting it lead to different comparisons: outcomes differ between action menus even for a model that never requests help, and repeated requests can leave execution failures unresolved. Imitation-learning evaluations and physical robot sequences illustrate the need to coordinate mitigation with goal actions. Together, these results motivate evaluating mitigation selection, action prerequisites, and recovery alongside hazard recognition and terminal outcomes. The appendix provides task definitions, checker conditions, and prompts. Project website: https://responsible-robot-benchmark.github.io/.

cs.RO

版本更新 · v5arXiv:2601.12401

Beyond the Dirac Delta: Mitigating Diversity Collapse in Reinforcement Fine-Tuning for Versatile Image Generation

Jinmei Liu, Haoru Li, Zhenhong Sun, Chaofeng Chen, Yatao Bian, Bo Wang, Daoyi Dong, Chunlin Chen 等 9 位作者

原文摘要

Reinforcement learning (RL) has emerged as a paradigm for fine-tuning large-scale generative models, such as diffusion and flow models, to align with complex human preferences and user-specified tasks. A fundamental limitation remains \textit{the curse of diversity collapse}, where the objective formulation and optimization landscape inherently collapse the policy to a Dirac delta distribution. To address this challenge, we propose \textbf{DRIFT} (\textbf{D}ive\textbf{R}sity-\textbf{I}ncentivized Reinforcement \textbf{F}ine-\textbf{T}uning for Versatile Image Generation), an innovative framework that systematically incentivizes output diversity throughout the on-policy fine-tuning process, reconciling strong task alignment with high generation diversity to enhance versatility essential for applications that demand diverse candidate generations. We approach the problem across three representative perspectives: i) \textbf{sampling} a reward-concentrated subset that filters out reward outliers to prevent premature collapse; ii) \textbf{prompting} with stochastic variations to expand the conditioning space, and iii) \textbf{optimization} of the intra-group diversity with a potential-based reward shaping mechanism. Experimental results show that DRIFT exhibits clear Pareto dominance in task alignment and generation diversity, achieving 3.88\%$\sim$81.42\% higher diversity at matched alignment and 14.38\%$\sim$56.45\% higher alignment at matched diversity. Our code is available at \textcolor{magenta}{\href{https://github.com/NJU-RL/DRIFT}{https://github.com/NJU-RL/DRIFT}}.

cs.LG · cs.AI

版本更新 · v2arXiv:2608.22061

MEMORY Wins All: Indirect Bias Injection Attacks via Social Media Content

Minjae Seo, Wonwoo Choi, Geonwoo Han, Taekyoung Kwon, Yongsu Kim, Sang Seo, Jaewon Noh, Hankyul Baek 等 10 位作者

原文摘要

Personal AI agents consume external content such as web pages and SNS feeds, and retain selected information in persistent memory. As a result, external content has become a new attack vector for memory poisoning, which steers an agent's later actions toward an adversary's bias. However, most existing attacks embed a malicious instruction in external content to make the agent retain the poisoned information, and prompt-injection filters can detect such content. We observe that agents access external content primarily through skills while curating a subset of the content into their memory. Leveraging this curation path, we present SBIA, a Stealthy Bias Injection Attack that introduces adversarial bias through ordinary external content while relying on the agent itself to perform the memory write. The adversary posts crafted comments under hot SNS feeds and distributes an SNS feed summarization skill whose curation rule admits these comments into memory. Comment cloaking expresses the bias as an ordinary opinion rather than an instruction, comment watermarking allows the skill to identify the crafted comments, and topic anchoring records them so that later related requests recall them. On BiasBench with 7,000 crafted SNS comments and seven LLMs on OpenClaw, SBIA achieves attack success rates of at least 96% across models and even 91% on GPT-5.5 in four downstream tasks. Despite this effectiveness, its skill passes all eight evaluated malicious-skill scanners and ClawHub's official skill scanning pipeline. We further propose a memory boundary defense that detects 82.1% of injected entries at a 5.6% FPR. Our findings show that external Web content and third-party skill marketplaces form a new attack surface for personal AI agent memory.

cs.AI · cs.CY

版本更新 · v3arXiv:2202.10527

Loop unrolling of UCA models: distance labeling

Francisco J Soulignac, Pablo Terlisky

原文摘要

A proper circular-arc (PCA) model is a pair $M = (C, A)$ where $C$ is a circle and $A$ is a family of inclusion-free arcs on $C$ whose extremes are pairwise different. The model $M$ represents a digraph $D$ that has one vertex $v(a)$ for each $a \in A$ and one edge $v(a) \to v(b)$ for each pair of arcs $a,b \in A(M)$ such that the beginning point of $b$ belongs to $a$. For $k \geq 0$, the $k$-th power $D^k$ of $D$ has the same vertices as $D$ and $v(a) \to v(b)$ is an edge of $D^k$ when $a\neq b$ and the distance from $v(a)$ to $v(b)$ in $D$ is at most $k$. A unit circular-arc (UCA) model is a PCA model $U = (C,A)$ in which all the arcs have the same length $\ell+1$. If $\ell$, the length $c$ of $C$, and the extremes of the arcs of $A$ are integer, then $U$ is a $(c,\ell)$-CA model. For $i \geq 0$, the model $i \times U$ of $U$ is obtained by replacing each arc $(s,s+\ell+1)$ with the arc $(s,s+i\ell+1)$. If $U$ represents a digraph $D$, then $U$ is $k$-multiplicative when $i \times U$ represents $D^i$ for every $0 \leq i \leq k$. In this article we design a linear time algorithm to decide if a PCA model $M$ is equivalent to a $k$-multiplicative UCA model when $k$ is given as input. The algorithm either outputs a $k$-multiplicative UCA model $U$ equivalent to $M$ or a negative certificate that can be authenticated in linear time. Our main technical tool is a new characterization of those PCA models that are equivalent to $k$-multiplicative UCA models. For $k=1$, this characterization yields a new algorithm for the classical representation problem that is simpler than the previously known algorithms.

cs.DS · cs.DM

版本更新 · v2arXiv:2609.05522

Diffusion models for eye-gaze trajectory generation using position and velocity representations

Laxman Basnet, Alexander Szorkovszky, Pedro G. Lind, Anis Yazidi, Shailendra Bhandari

原文摘要

Eye-tracking data are expensive to collect, requiring specialized hardware and controlled laboratory conditions, and difficult to share due to privacy regulations, which together limit the quantity and diversity of gaze data available for research. We investigate unconditional gaze generation using diffusion models in position and component-wise velocity representations. The models are trained and evaluated on eight-second visual-search trajectories from 28 participants, using a split of 23 training participants and five held-out validation participants, with three training seeds. Evaluation includes kinematic distributions, trajectory geometry, event statistics, and a temporal Wasserstein GAN with gradient penalty as a learned comparator. Across eight position-derived features, mean Jensen-Shannon divergence is $0.016 \pm 0.004$ for the position model and $0.037 \pm 0.002$ for the velocity model, with standard deviations calculated across training seeds. These scores do not establish that representation choice caused the difference. A separate comparison using the same evaluation method shows that the ordering of the models varies across training seeds. The position model also produces smaller feature discrepancies than a kinematic Markov baseline. Differences in saccade counts between real and generated data depend strongly on the velocity threshold used to detect events. The results provide quantitative reference measurements for unconditional gaze generation on this visual-search task and show how evaluation choices affect conclusions about generated gaze.

cs.CV · cs.AI · cs.NE

版本更新 · v2arXiv:2609.22160

Uncertainty and Business-Aware Remaining Useful Life Estimation for Semiconductor Manufacturing

Davide Frizzo, Francesco Borsatti, Gian Antonio Susto

原文摘要

Remaining Useful Life (RUL) estimates guide maintenance in semiconductor manufacturing, where a late intervention can disrupt production but an early one discards usable equipment life. A single prediction does not express the uncertainty needed to choose between these outcomes. We combine Deep Learning (DL) sequence models with Simoultaneous Quantile Regression (SQR) to estimate RUL at selectable quantile levels, and evaluate maintenance decisions using Unexpected Breaks (UB), Unexploited Lifetime (UL), and a cost-weighted objective. On the $F_1$ fault mode of the 2018 PHM Data Challenge (PHM18) ion-milling dataset, we compare recurrent, Transformer, and State Space Models (SSM) architectures. Diagonal State Spaced (S4D) gives the strongest overall RUL accuracy across the evaluated quantiles. Varying the quantile and maintenance window exposes the trade-off between failure risk and early intervention; under the examined cost ratios, the resulting decisions have lower cost than the Preventive Maintenance (PvM) baselines.

cs.LG

版本更新 · v2arXiv:2610.14749

Solving Distributed Flexible Job Shop Scheduling Problem Using SAT

Phuong Dang Anh, Duc Nguyen Kim Trung, To Van Khanh

原文摘要

The Distributed Flexible Job Shop Scheduling Problem (DFJSP) requires the joint determination of factory assignment, machine selection, and operation sequencing to minimize the makespan. This paper presents an exact SAT-based approach built on an efficient SAT formulation that exploits problem structure through propagation, symmetry breaking, and incremental SAT solving to effectively address these coupled decisions. The proposed method is evaluated on 76 standard benchmark instances from the Fattahi, Brandimarte, and rdata datasets under two- and three-factory configurations. Together with previously established results, the new SAT optimality certificates bring the total number of proven-optimal instances to 72 out of 76, including three newly certified instances; for two of these instances, SAT also improves the previous best-known makespans. Across the benchmark configurations, SAT achieves the best results on four of the five configurations and remains competitive with strong exact approaches such as CP and LBBD1_CPIL, as well as existing metaheuristic methods. These results demonstrate that the proposed SAT framework is an effective exact approach for the DFJSP, combining strong solution quality with rigorous optimality certification and offering a complementary exact method for future DFJSP studies and evaluations on additional benchmark instances.

cs.LO

版本更新 · v2arXiv:2607.10064

Fair Division with Binary Valuations: Characterizations

Florian Brandl, Warut Suksompong, Nicholas Teh

原文摘要

We consider the fair allocation of indivisible goods with binary valuations. In this setting, the maximum Nash welfare rule, the leximin rule, and all additive welfarist rules with a strictly concave function coincide. We show that for any number of agents, this rule is the only rule that satisfies envy-freeness up to one good, strategyproofness, neutrality, minimal completeness, and invariance under disapproving unassigned goods (IDU). Moreover, we present an alternative characterization for two agents, where we replace IDU with non-redundancy and resource-monotonicity. In both characterizations, all axioms are necessary.

econ.TH · cs.GT

版本更新 · v3arXiv:2610.40131

VideoMemBench: How Well Do MLLMs Remember in Video Conversations?

Zhengdong Hu, Chao Wang, Kaituo Feng, Huanjin Yao, Mingfei Lu, Hehe Fan, Yi Yang

原文摘要

Multimodal large language models (MLLMs) can now process hour-long videos, making extended multi-turn dialogue over a single video a natural mode of use. Sustaining such a dialogue requires more than answering each question in isolation: the model must retrieve and reuse information established earlier in the conversation, both what it has seen and what it has said, an ability we term in-context video memory. Existing video QA benchmarks leave this ability unmeasured: their questions are mutually independent, never reference one another, and each is answerable from the video alone, so nothing ever requires carrying information across turns. We introduce VideoMemBench, in which each sample pairs a single video with a long multi-turn dialogue, whose turns are connected by typed cross-turn dependencies: an Episodic Dependency refers back to a visual episode described in an earlier turn, probing memory of what the model has seen, while an Answer Dependency builds on the model's own earlier answer, probing memory of what the model has said. Every dependency is verified considering two properties: 1) necessity, meaning the question cannot be answered without its earlier turns, and 2) non-leakage, meaning the question does not restate the information from its earlier turns. To enforce these properties, we design a construction pipeline with three LLM roles: a planner, a generator, and a judger, with each dialogue reviewed by human experts. VideoMemBench comprises 326 videos with 2,476 turns, of which 1,387 depend on earlier turns, including multi-parent dependencies and long-range call-back. Among over 20 evaluated open- and closed-source MLLMs, Claude Opus 5 performs the best with an overall score of only 45.7%, highlighting the challenge of in-context video memory. Our dataset and evaluation are released.

cs.CV

版本更新 · v2arXiv:2611.02030

Query-efficient scan-and-search watermark localization

Liyuan Wang, Xinsong Ma, Ziye Ma

原文摘要

Recently, the detection of AI-generated content has been of particular importance in various fields of our society. For accountability purposes, many large language models (LLMs) have implicitly watermarked their outputs. Localizing such watermarks requires a piece of text to undergo an additional verification process. Existing localization methods typically rely on dense token-level scoring, making verification costly even when an LLM-generated watermark only sparsely appears. To tackle this problem, we design a new adaptive allocation strategy that first maintains broad document coverage and then progressively concentrates the detection budget on regions that exhibit stronger watermark evidence or are more likely to contain watermarked content. We then transform the statistical signals from the selected regions into e-values and employ the proposed token-weighted e-BH procedure to determine the localized watermark regions. The resulting framework is called BELL (Budgeted E-evidence Localization for LLM Watermarks). Theoretically, BELL can control the token-weighted false discovery rate (FDR) without independence assumptions across regions. Finally, extensive experimental results demonstrate that BELL consistently outperforms competing methods across multiple LLMs, datasets, and watermarking schemes.

cs.CR · cs.AI

版本更新 · v2arXiv:2504.01491

How to Define the Quality of Data? A Feature-Based Literature Survey

Markus Matoni, Arno Kesper, Gabriele Taentzer

原文摘要

Data is generated in almost every digital interaction, and using it effectively requires high quality. But what exactly is data quality? The literature offers many, widely diverging answers. This article presents a systematic literature review that screened more than 8,700 records on data quality and identified 35 providing original, dimension-based definitions. Using feature-oriented domain analysis, a feature model of these heterogeneous definitions is derived and used to classify all identified publications. The classification reveals a heterogeneous landscape: despite an ISO standard and a few highly cited quasi-standards, no consensus exists on which quality dimensions to consider or how to define them. As definitions increasingly emerge for specific domains, contexts of use, and new types of data, the respective communities need to deliberately converge on how data quality is defined in their field.

cs.DB

版本更新 · v2arXiv:2411.14442

AI Ethics by Design: Implementing Customizable Guardrails for Responsible AI Development

Kristina Šekrst, Jeremy McHugh, Jonathan Rodriguez Cefalu

原文摘要

This paper explores the development of an ethical guardrail framework for AI systems, emphasizing the importance of customizable guardrails that align with diverse user values and underlying ethics. We address the challenges of AI ethics by proposing a structure that integrates rules, policies, and AI assistants to ensure responsible AI behavior, while comparing the proposed framework to the existing state-of-the-art guardrails. By focusing on practical mechanisms for implementing ethical standards, we aim to enhance transparency, user autonomy, and continuous improvement in AI systems. Our approach accommodates ethical pluralism, offering a flexible and adaptable solution for the evolving landscape of AI governance. The paper concludes with strategies for resolving conflicts between ethical directives, underscoring the present and future need for robust, nuanced and context-aware AI systems.

cs.CY · cs.CL

版本更新 · v2arXiv:2602.10867

Deep Learning of Compositional Targets with Hierarchical Spectral Methods

Hugo Tabanelli, Yatin Dandi, Luca Pesce, Florent Krzakala

原文摘要

Why depth yields a computational advantage over shallow methods remains a central open question in learning theory. We study this question in a controlled high-dimensional Gaussian setting, focusing on compositional target functions. We analyze their learnability using an explicit three-layer fitting model trained via layer-wise spectral estimators. The target combines polynomial latent features with a scalar readout, and its compositional structure allows learning to proceed in stages. Recovering an intermediate representation reduces the problem to lower-degree spectral estimation tasks, as in multi-index models. Our analysis establishes Gaussian comparison bounds for projected moments when $0<\varepsilon<1/3$, and motivates separations in sample complexity between two- and three-layer learning strategies, conditional on a conjectured spectral recovery step.

stat.ML · cs.LG

版本更新 · v2arXiv:2605.04183

Optimal Zonotope Containment via Adaptive Gaussian Sampling

Friedrich Eisenbrand, Thomas Rothvoss, Matteo Russo, Ruben Skorupinski

原文摘要

We investigate the convex-body containment problem $\max\{s >0 : s Z \subseteq Q\}$, where the outer body $Q \subseteq \mathbb{R}^d$ is described by a membership oracle and the inner body $Z \subseteq \mathbb{R}^d$ is a zonotope. Our main result is a sampling-based $O(\sqrt{d/\log d})$-approximation algorithm for this problem that matches the lower bound of $Ω(\sqrt{d/\log d})$ by Khot and Naor in the oracle model. Starting from approximate Lewis position, the algorithm samples Gaussian directions and adaptively shortens and repositions the generators. Its analysis combines preservation of the support in a fixed direction with contraction of the corresponding functional after renormalization. Crucially, the algorithm works directly with the input generators and does not use zonotope sparsification. We complement this result with a \emph{universal} $Ω(\sqrt{d/\log d})$ lower bound holding for \emph{all} full-dimensional zonotopes when the number of oracle queries is polynomial in $d$. Finally, we consider containment problems $\max\{s >0 : s K \subseteq Q\}$, for general convex bodies $K \subseteq \mathbb{R}^d$. A result of Nasz{ó}di on approximating $K \subseteq \mathbb{R}^d$ by a polytope implies a $Θ(d/\log d)$ approximation algorithm in polynomial time when the centroid of $K$ is the origin. We show the tightness of this approximation factor in the oracle model via a reduction to the circumradius computation. Our lower bound holds for centrally symmetric convex sets, implying that Barvinok's optimal $O(\sqrt{d})$-approximation of a centrally symmetric convex body by a polytope with a polynomial number of vertices cannot be computed in polynomial time.

cs.DS · math.MG

版本更新 · v6arXiv:2609.07979

The Stretch Factor of Planar Delaunay Triangulations Is Nearly Determined

Guanlin Mo, Kangke Cheng, Hu Ding

原文摘要

The Delaunay triangulation is a classical geometric structure on a finite set of points in the plane. Its stretch factor is the largest ratio of the shortest-path distance along its edges to the Euclidean distance between the same two points. Determining the worst-case stretch factor of planar Delaunay triangulations is a long-standing open problem. We prove a uniform upper bound of 1.5949, improving the previous bound of 1.998 and narrowing the gap to the best known lower bound of 1.5932 from 0.4048 to less than 0.0017, nearly pinpointing the worst-case stretch factor. A central difficulty is that the line segment between two points may cross arbitrarily many triangles. Our progress accounting framework addresses this by converting the global bound into a family of local inequalities, each involving only a fixed number of real parameters regardless of the number of triangles crossed. Two further geometric lemmas make computer-assisted verification tractable: the pencil lemma decomposes each local transition into two geometrically independent stages, reducing verification over infinitely many possible next disks to a single differential condition; and the corner lemmas handle degenerate boundary cases where direct verification would fail. With these reductions, the proof ends with a finite verification of an explicit potential in exact rational arithmetic and outward-rounded interval arithmetic. Numerous geometric network constructions use the Delaunay stretch factor as a black box, so the tighter bound directly improves stretch-factor guarantees for a range of downstream applications, including bounded-degree plane spanners and low-weight spanners.

cs.CG

版本更新 · v2arXiv:2607.29069

Rethinking AI Cloud Infrastructure for Agentic Serving Systems with the Aries Experimentation Framework

Jooyoung Park, Leonid Kondrashov, Boxi Zhou, Hongrui Liu, Zonghao Liu, Chengzhi Lu, Riccardo Mancini, Esha Choukse 等 17 位作者

原文摘要

Autonomous agents challenge conventional LLM serving with long-lived, cross-component execution and evolving system state. These characteristics complicate controlled systems experimentation and attribution of end-to-end behavior across the serving stack. We present Aries, a full-stack experimentation framework that separates task specifications from execution configurations, reconstructs cross-component agent trajectories with correlated system telemetry, and exposes stateful tool execution through a consistent interface across heterogeneous sandbox substrates. We use Aries to conduct reproducible experiments on open agent harnesses and benchmarks. We complement these experiments with production traces from a commercial platform, grounding low-level systems research in observed production behavior. Our results show that (1) token-centric metrics miss non-inference bottlenecks, (2) retaining additional context yields diminishing accuracy benefits while reducing serving capacity, and (3) tool sandboxes alternate between long idle periods and short resource bursts, while current snapshot-based state management makes aggressive suspension costly. We then discuss the vision for agent-native serving systems designed around trajectory-level metrics, adaptive context management, and elastic sandbox resource management.

cs.DC

版本更新 · v2arXiv:2609.26788

Quantum Advantage for Distributed Symmetry Breaking

Maxime Flin, Longcheng Li, Jukka Suomela

原文摘要

We present a distributed quantum algorithm that $3$-colors cycles in $O(1)$ rounds, with high probability. It follows that all locally checkable labeling problems (LCLs) that have round complexity $O(\log^* n)$ in the classical LOCAL model can be solved in $O(1)$ rounds in the quantum-LOCAL model, with high probability; this includes problems such as maximal independent set and maximal matching in bounded-degree graphs. This presents the first natural examples of graph problems with an asymptotic distributed quantum advantage for the LOCAL model; all prior examples that separate LOCAL and quantum-LOCAL are artificial problems constructed merely for the sake of demonstrating quantum advantage.

quant-ph · cs.DC

版本更新 · v3arXiv:2610.41290

SAT-ACT: Learning CDCL Branching from Outcome-Derived Action Preferences

Zhenchao Sun, Chongyang Tao, Ping Lu, Tongkai Lu, Jianling Gao, Shuai Ma

原文摘要

Learning-based approaches have increasingly been explored for SAT solving, with particular attention to improving branching decisions in conflict-driven clause learning (CDCL) solvers. These approaches derive branching guidance either from static structural properties of SAT formulas or from dynamic signals obtained through solver feedback and execution traces. However, these forms of supervision provide limited evidence about state-dependent branching effects, while different outcome measures may favor different branching choices. To address these limitations, we propose SAT-ACT, an outcome-derived learning framework for CDCL branching. We design three complementary outcome comparison criteria to extract action preferences from independent branching action rollouts initiated at the same solver state. The criteria identify preferences supported by the outcomes and leave comparisons unresolved when the evidence is insufficient or conflicting, instead of forcing an ordering using a predefined scalar metric. A state-conditioned network learns branching priorities from the extracted preferences and uses them to guide CDCL search directly without online action rollouts. We further introduce non-dominated heuristic action supervision, which retains the solver-selected action as a training target only when it remains non-dominated under these preferences. Solver-level experiments show that SAT-ACT consistently reduces CDCL search costs on three SAT families and improves PAR-2 on the SAT Competition benchmarks.

cs.AI · cs.LG

版本更新 · v2arXiv:2610.12676

WoodBR-Cross: A public wood-image dataset and individual-tree-disjoint benchmark for species identification

Daniel Casanova, Alexandre Bahia Gontijo, Arnaldo Candido Junior, Silvana Nisgoski, Pedro Luiz de Paula Filho

原文摘要

Wood identification supports timber inspection and species conservation. However, benchmarks can overestimate generalization when photographs of the same tree occur in training and test sets. We present WoodBR-Cross: 4,875 transverse-surface microscope images, 38 operational taxonomic classes and 303 catalogue-linked trees. A species subset contains 3,406 images, 20 classes and 214 trees. Task A evaluates all classes using duplicate-aware image partitions. B1 partitions images of the species subset, allowing different photographs of one tree across partitions. B2 keeps each tree's photographs together, testing recognition of unseen trees on the same subset. We benchmark three backbones and baselines across three folds and five training seeds. Validation-selected ConvNeXt-Tiny achieves B2 tree-level macro-F1 of 0.8621 +/- 0.0317; frozen DINOv2 features yield 0.9000 +/- 0.0722. Values are means +/- SD across three folds; fine-tuned scores are seed-averaged within folds. This resource supports reproducible, group-aware evaluation.

cs.CV

版本更新 · v2arXiv:2610.27877

Gaze2HOI: Gaze-Aware Intention Disambiguation for Egocentric Hand-Object Interaction Forecasting

Chuanyang Ma, Chenye Wang, Yixuan Wang, Huiling Zhou, Man Zhang, Xingqun Qi, Muyi Sun, Caifeng Shan 等 9 位作者

原文摘要

Anticipating how users will interact with their surroundings is essential for proactive systems that provide timely assistance in extended reality and embodied applications. Prior work typically forecasts hand-object interactions directly from historical observations, leaving intention and contact geometry implicit. However, similar observation histories can precede semantically or geometrically distinct futures. Inspired by behavioral evidence that gaze can provide early cues for underlying intention, we propose Gaze2HOI, a gaze-aware framework that formulates hand-object interaction forecasting as a hierarchical problem comprising intention inference, contact grounding, and coupled hand-object motion generation. Specifically, Gaze2HOI first weights gaze cues by fixation strength and recency, and uses them to modulate the visual representations of a vision-language model (VLM) through Temporal Gaze Saliency Modulation (TGSM), thereby reducing semantic ambiguity in intention inference. Subsequently, an Anticipatory Contact Grounding (ACG) module maps these structured intentions into explicit contact, support, and placement fields, effectively mitigating geometric ambiguity. Driven by these explicit conditions, a diffusion-based model jointly generates the six-degree-of-freedom (6-DoF) object trajectories and future articulated motion of both hands. To evaluate Gaze2HOI, we further introduce EgoAIM, a phase-aware benchmark that organizes egocentric hand-object interactions into four phases defined by evolving hand-object relations and provides fine-grained intention annotations. Extensive experiments demonstrate that Gaze2HOI achieves state-of-the-art performance in both intention inference and motion forecasting, even approaching oracle-level end-to-end performance in specific interaction phases. Project page: https://gaze2hoi.github.io/.

cs.CV

版本更新 · v3arXiv:2602.02699

Sparsely Supervised Diffusion

Wenshuai Zhao, Zhiyuan Li, Yi Zhao, Mohammad Hassan Vali, Martin Trapp, Joni Pajarinen, Juho Kannala, Arno Solin

原文摘要

Diffusion models have shown remarkable success across a wide range of generative tasks. However, they often suffer from spatially inconsistent generation, arguably due to excessive correlations learned by the model. This can produce samples that are locally plausible but globally inconsistent. We propose a principled method to mitigate this issue. Our method, sparsely supervised diffusion (SSD), is a simple yet effective masking framework that can be implemented with only a few lines of code. We analytically show that SSD fundamentally alters diffusion model training by modifying the spectrum of the data covariance and that it suppresses correlations in the data covariance matrix. Experiments show that our method more accurately approximates the underlying population score function, reduces memorization on small datasets, and promotes the use of essential contextual information during generation. Moreover, even when up to 98\% of pixels are masked, it achieves competitive FID scores across a range of datasets and, importantly, avoids the training instability commonly observed on small datasets.

cs.LG · cs.AI

版本更新 · v2arXiv:2610.07340

CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening

Loka Li, Jin Tian, Kun Zhang

原文摘要

Protein-molecule virtual screening is increasingly cast as a problem of representation learning in a shared embedding space. Existing methods rely on dense holistic alignment, entangling invariant binding determinants with nuisance correlations and limiting transfer to new targets. Binding in protein-molecule systems involves sparse cross-modality interactions: binding is governed by a small contact interface and a few decisive local interactions (e.g., hydrogen bonds, hydrophobic contacts, and salt bridges) rather than the global structures of the protein and molecule. We hypothesize that uncovering and leveraging sparse interaction patterns is critical for generalization beyond the training data, as these patterns are reusable and expected to improve performance across different scenarios. Since the training data contain only observed binding pairs, we formalize this prior via a V-structure causal model under Heckman-style selection, and establish three theoretical results: (i) when the compatibility between concepts is bilinear, the latent concepts of interacting proteins and molecules are not identifiable, even if the interaction is sparse; (ii) with a non-bilinear compatibility function, these concepts and their sparse interaction support are component-wise identifiable under a sparse antichain condition; and (iii) a low-rank relaxation yields subspace identifiability of the interaction modes, and applies to bilinear compatibility as well. Inspired by these principles, we propose CausalBind with three implementation variants. Extensive experiments on DUD-E and LIT-PCBA benchmarks show that all variants consistently outperform strong retrieval baselines, with the largest gains on LIT-PCBA early enrichment, and further generalize to target- and scaffold-level out-of-distribution splits. Code and scripts are freely available at https://github.com/lokali/CausalBind.

cs.LG · cs.AI

版本更新 · v2arXiv:2606.21309

WildBox: A Dataset and Benchmark for Aerial Monocular 3D Detection of African Savanna Wildlife

Vandita Shukla, Kilian Meier, Lucie Laporte-Devylder, Camille Rondeau Saint-Jean, Jenna M. Kline, Blair R. Costelloe, Devis Tuia, Fabio Remondino 等 9 位作者

原文摘要

We introduce WildBox, a dataset and benchmark for monocular 3D detection of wildlife from drone video, comprising 237,505 3D bounding box annotations across seven African savanna species grouped into six benchmark classes. Annotations follow a KITTI/Omni3D-compatible format in a per-segment scale-normalised camera frame, with instance identities maintained across each segment. We evaluate two open-vocabulary monocular 3D architectures, OVMono3D-LIFT and DetAny3D, under zero-shot, ground-truth 2D box prompt, and supervised fine-tuning protocols. Open-vocabulary 2D foundation models provide usable zero-shot wildlife localisation (50.55 AP@50), but zero-shot 3D detection collapses to 0.00 AP across both architectures and every 2D-input condition tested, including ground-truth 2D box prompts, thus isolating the failure to the 3D stage. Fine-tuning on WildBox recovers performance to 8.68 +/- 0.47 AP-BEV@0.50 and 13.17 +/- 0.69 AP3D macro. Depth contributes 84% of normalised Hausdorff distance after fine-tuning and over 99% in zero-shot, identifying monocular aerial depth as the dominant open problem in this regime. A coarse-to-fine curriculum, i.e. pretraining on a merged zebra class before fine-tuning on the Grevy's/plains split, improves macro 3D performance with less total compute, with the largest gains on the two zebra subclasses. WildBox is released with video-level splits and baseline checkpoints to enable progress in 3D wildlife perception from drone video.

cs.CV

版本更新 · v2arXiv:2406.14936

On the growth of the parameters of approximating ReLU neural networks

Erion Morina, Martin Holler

原文摘要

This work focuses on the analysis of fully connected feed forward ReLU neural networks as they approximate a given, smooth function. In contrast to conventionally studied universal approximation properties under increasing architectures, e.g., in terms of width or depth of the networks, we are concerned with the asymptotic growth of the parameters of approximating networks. Such results are of interest, e.g., for error analysis or consistency results for neural network training. The main result of our work is that, for a ReLU architecture with state of the art approximation error, the realizing parameters grow at most polynomially. The obtained rate with respect to a normalized network size is compared to existing results and is shown to be superior in most cases, in particular for high dimensional input.

cs.LG · math.NA

版本更新 · v2arXiv:2602.08099

VidVec: Unlocking Video MLLM Embeddings for Video-Text Retrieval

Issar Tzachor, Dvir Samuel, Rami Ben-Ari

原文摘要

Recent studies have adapted generative Multimodal Large Language Models (MLLMs) into embedding extractors for text-vision tasks, typically by fine-tuning them to produce universal representations. However, their performance on video-text retrieval often remains below that of dedicated Video Foundation Models. In this paper, we revisit the video-text retrieval capabilities of MLLMs. We first analyze the zero-shot retrieval capabilities of pretrained MLLMs and show that they already encode substantial retrieval-relevant information: combining intermediate-layer embeddings with a calibrated MLLM head yields strong performance without any training. To further exploit these capabilities, we introduce a lightweight text-based optimization strategy that requires no paired multimodal data. Our method uses dense video captions as rich textual surrogates for video semantics and short summaries as compact, query-like views, showing that a carefully designed text-alignment objective can improve multimodal alignment through the shared MLLM backbone. We backup these findings through in-depth analysis. Remarkably, our lightweight text-only optimization outperforms its counterpart trained with paired video-text supervision, which is substantially more computationally expensive. Furthermore, our method outperforms existing approaches, often by a substantial margin, and achieves state-of-the-art performance across common video-text retrieval benchmarks. More broadly, our findings highlight the untapped retrieval capabilities of pretrained MLLMs and establish text-only optimization as a more efficient and effective substitute for large-scale visual supervision.

cs.CV · cs.AI

版本更新 · v2arXiv:2609.09986

A Sharp Barrier of Consistent Submodular Maximization: Any Improvement over $2-\sqrt{2}$ Entails Exponential Queries or Linear Recourse

Shi Fu, Qixin Zhang, Dacheng Tao

原文摘要

Consistent submodular maximization aims to maintain a high-utility subset of size at most $k$ as new elements arrive one by one, while changing only a limited number of elements per update. Previously, [DFL+25](STOC '25) established an information-theoretic bound of $2/3$ and gave the first polynomial-time randomized algorithm with a $0.51$-approximation guarantee. However, a fundamental question remained open: Is it possible to design an efficient algorithm for consistent submodular maximization that matches the classical offline $(1-1/e)$-approximation? In this paper, we answer this question in the negative by proving that the sharp approximation threshold achievable with polynomially many value queries and worst-case constant recourse is \[β:=2-\sqrt{2}\approx0.5858<1-1/e.\] Specifically, we develop an improved poly-time randomized algorithm, which can attain a $(β-\varepsilon)$-approximation in expectation at each fixed time with $O(\varepsilon^{-2})$ worst-case recourse. The cornerstone of this algorithm is a novel anchored sampling scheme, which uses only value queries on subsets of the elements seen so far to construct a solution that remains competitive under unknown future arrivals. Conversely, we establish a matching lower bound by showing that any fixed improvement over $β$ requires either exponentially many value queries or $Ω(k)$ changes per update. Furthermore, we characterize the impact of curvature by establishing a sharp threshold of $1-(\sqrt{2}-1)\vartheta$ for consistent submodular maximization, where $\vartheta\in[0,1]$ denotes the total curvature. Surprisingly, for weighted coverage objectives, we devise a poly-time randomized algorithm that can match the optimal $(1-1/e-\varepsilon)$-approximation with $O(\varepsilon^{-1})$ worst-case recourse, thereby separating coverage maximization from general submodular maximization in the consistent settings.

cs.DS · cs.LG

版本更新 · v2arXiv:2609.35453

Hermite Brings a Laptop: Analyzing Frieze-Jerrum Rounding Yields Improved Approximations for Clustering Problems

David García-Soriano, Atsushi Miyauchi

原文摘要

The Frieze-Jerrum rounding is a standard tool for rounding SDP relaxations of graph partitioning and clustering problems, assigning nodes to at most $k$ clusters using $k$ independent Gaussian vectors. Its analysis hinges on the collision probability $P_k(ρ)$ that two nodes whose SDP vectors have inner product $ρ$ are assigned to the same cluster. No tractable closed form for $P_k$ is known for $k\geq 4$, making it difficult to certify approximation guarantees and hindering the systematic search for better algorithms. We develop a Hermite-coefficient certification framework to derive accurate and tractable bounds on $P_k$. Using the Hermite expansion of Gaussian noise stability, we express $P_k$ as a power series with nonnegative coefficients, reduce these coefficients to one-dimensional Gaussian integrals, and certify finitely many of them, yielding rigorous bounds on $P_k$ over the entire correlation range. Our framework yields strengthened polynomial-time approximations for several clustering problems. For MaxAgree Correlation Clustering, we derive a $0.7818$-approximation, the first improvement in two decades over the $0.7666$ ratio of Swamy (2004). We also improve the best known ratios for the variant with at most $K$ clusters, MaxAgree$[K]$ (e.g., from $0.77$ to $0.8151$ for $K=3$). For Max $K$-Cut we resolve, via a structural property of the Hermite expansion, a conjecture of de Klerk et al. (2004) characterizing the Frieze--Jerrum approximation ratio for every $K\ge3$; we show that this ratio is tight, and determine it to within $10^{-6}$ accuracy for $K\le16$. Finally, we reduce the additive approximation error for modularity maximization from $0.42084$ (Kawase et al., 2021) to $0.3790$. On the hardness side, we show that approximating Maxagree within $0.802+ε$ is Unique Games-hard via a construction in Gaussian space analyzed by Borell's inequality.

cs.DS

版本更新 · v3arXiv:2609.09091

Impossibility of One-Way One-Round Quantum 4-Coloring via Matrix-Space Stability

Tom Gur, Longcheng Li

原文摘要

We show that one-way one-round quantum-LOCAL algorithms cannot $4$-color directed cycles with high probability. This is the first lower bound in the high-probability quantum LOCAL setting that goes beyond the non-signaling and bounded-dependence models, exploiting the structure of distributed quantum algorithms. Our proof establishes a bidirectional connection between distributed quantum computing and extremal combinatorics. We obtain our lower bound by proving a Mantel-type stability theorem for weighted matrix spaces.

quant-ph · cs.DC

版本更新 · v3arXiv:2604.15001

COEVO: Co-Evolutionary Framework for Joint Functional Correctness and PPA Optimization in LLM-Based RTL Code Generation

Heng Ping, Peiyu Zhang, Shixuan Li, Wei Yang, Anzhe Cheng, Shukai Duan, Xiaole Zhang, Paul Bogdan

原文摘要

LLM-based RTL code generation methods increasingly target both functional correctness and PPA quality, yet existing approaches decouple the two objectives, optimizing PPA only after full correctness is achieved. Sequential multi-agent pipelines, evolutionary search with binary correctness gates, and hierarchical reward dependencies all discard partially correct but architecturally promising candidates. Moreover, existing methods reduce the multi-objective PPA space to a single scalar fitness that obscures the trade-offs among area, delay, and power. To address these limitations, we propose COEVO, a co-evolutionary framework that unifies correctness and PPA optimization within a single evolutionary loop. COEVO formulates correctness as a continuous co-optimization dimension alongside area, delay, and power, enabled by an enhanced testbench with fine-grained scoring. The framework allows PPA-promising but partially correct candidates to guide the search toward jointly optimal solutions, and further employs four-dimensional Pareto-based non-dominated sorting to preserve the PPA trade-off structure without manual weight tuning. On VerilogEval 2.0 and RTLLM 2.0, COEVO surpasses all agentic baselines across four LLM backbones. With GPT-5.4-mini, COEVO achieves 97.5\% and 94.5\% Pass@1 and attains the best PPA on 43 out of 49 synthesizable RTLLM 2.0 designs.

cs.AI

版本更新 · v2arXiv:2610.42010

TurnTurk-GPT: Text-Based Turn-Taking Prediction for Turkish

Ahmet Tuğrul Bayrak, Fatma Nur Korkmaz, Nur Yağmur Tuncer, Mustafa Sertaç Türkel

原文摘要

This paper presents TurnTurk-GPT, a text-based turn-taking predictor for Turkish obtained by fine-tuning a Turkish GPT-2 model with the TurnGPT objective on synthetic and real dialogue, and evaluates it on real Turkish conversation against rule baselines, a zero shot Turkish language model and a widely used multilingual end-of-turn detector. Evaluation uses word-level decision points on unpunctuated, lower-cased text approximating the output of streaming speech recognisers, recording-disjoint and speaker-disjoint folds, nested threshold selection and paired cluster bootstrap tests. TurnTurk-GPT outperforms the multilingual detector under both recording-disjoint and speaker-disjoint evaluation. Its gain over a zero-shot Turkish language model is largest for speakers seen in training, while on unseen speakers it matches this strong baseline. Removing the suffixes of the turn-final word reduces AP by up to 44%, against 2% for a sentence-internal word, locating the Turkish end-of-turn cue in verb-final morphology. Synthetic dialogue alone yields the weakest trained model, and when a speaker pauses the zero-shot and multilingual baselines remain close to chance. The model and the evaluation protocol are publicly released.

cs.CL