跳到正文
研踪PaperTrail

YOUR RESEARCH, IN SIGHT

让下一篇重要论文，不再错过。

覆盖计算机全学科，以 AI 为快捷入口。关注方向、作者和关键词，把发现变成持续的研究积累。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+2471新增论文
+2025其中 AI 相关
+163已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-10 20:36 · 全站最近入库：2026-11-10 15:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-09 21:49 — 2026-11-10 21:49（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：2026-11-10 20:36最近发现新增版本：2026-11-10 15:22库内论文最新更新时间：2026-11-10 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。

20,643 已收录论文17,531 AI 相关5,643 有修订112 HF 社区发现

浏览论文库

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 20,643 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-10 20:33（北京时间）
新论文 · v1arXiv:2610.35312

OVM-Occ: Open-Vocabulary Monocular Occupancy Prediction via Geometry-Aware Vision-Language Distillation

Shuyang Yu, Haibo Qin, Shaohan Hu, Wei Shan, Xiaoqing Guan, You Wang, Guang Li

原文摘要

Monocular occupancy prediction in indoor scenes aims to recover a scene's 3D geometry and semantics from a single RGB image. Existing methods are restricted to a closed set of predefined categories, limiting their ability to generalize to unseen categories. This limitation is particularly critical in indoor scenes, where objects exhibit highly diverse and fine-grained semantic categories. We study open-vocabulary monocular occupancy prediction for indoor scenes and present OVM-Occ, a Gaussian-based occupancy framework with an instance-aware vision-language teacher. Specifically, we adopt Language-Embedded Gaussians as the intermediate scene representation, propose a geometry-aware deformable attention module to refine Gaussian semantic features, and construct instance-level vision-language embeddings to provide reliable semantic supervision. We further introduce geometry-aware decoupled semantic distillation to mitigate the interference between geometry learning and semantic learning. To evaluate open-vocabulary occupancy prediction performance, we introduce OpenOcc-ScanNet and OpenOcc-Replica, two extended benchmarks with more diverse and fine-grained semantic categories. Experiments show that our method achieves state-of-the-art performance in open-vocabulary monocular occupancy prediction for indoor scenes, outperforming the previous state-of-the-art approach by 12.2 mIoU and 0.6 IoU on the Occ-ScanNet dataset, with consistent gains under new open-vocabulary evaluation protocols.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35311

Temporal-Difference Calibration of Black-Box Simulators

Min Zeng, Xin Wen, Xi Chen, Yichen Zhang, Wen-Xin Zhou

原文摘要

We develop a derivative-free temporal-difference (TD) framework for calibrating black-box simulators using one-step transitions from a target system and noisy simulator-generated continuation values. The calibration parameter is defined through Bellman orthogonality, recovering the physical parameter under correct simulator specification and yielding a near-optimal $L_2$ approximation of the policy value under misspecification. We propose three TD algorithms based on random-direction finite differences, distinguished by their query costs and reuse of noisy simulator evaluations. We establish almost-sure convergence, last-iterate mean-square error bounds, and central limit theorems for Polyak-Ruppert averages across four query-noise regimes. Our analysis reveals a specification-dependent bias phenomenon: for two algorithms, the finite-difference bias of the TD estimating equation vanishes at the calibration target under correct specification, even when the gradient surrogate remains biased. This permits a fixed perturbation radius and rate exponents approaching $1/2$ in the simulator rollout budget, whereas misspecification generally recovers the classical Kiefer-Wolfowitz rates. We also develop a few-replicate online bootstrap that yields Student-$t$ calibrated confidence intervals under negligible query noise, and identify a covariance mismatch that can invalidate conventional multiplier inference along Markov trajectories. Finally, a second-stage TD recursion corrects the remaining value discrepancy without additional simulator queries.

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35308

Quantitative Reachability Properties Beyond Decisiveness

Raphaël Faure, Alain Finkel, Lina Ye

原文摘要

Decisiveness is central to reachability algorithms for infinite Markov chains, but is a qualitative notion: it guarantees that path-enumeration algorithms terminate, without an a priori bound on the horizon. We study decisiveness quantitatively of Markov chains, and apply our results to the approximate quantitative coverability problem for effective probabilistic well-structured transition systems (pWSTS). We introduce truncation sets, which represent the horizons sufficient to approximate the reachability probability within a precision $\varepsilon$. These sets reformulate decisiveness quantitatively, and their elements can be computed when it is decisive. To obtain such horizons, before any exploration, we introduce geometrically reachable sets, for which the probability of not reaching them within n steps decreases exponentially in n, up to a prefactor depending on the initial state. Horizons valid for all initial states exist iff this prefactor can be chosen uniformly for boundedly coarse chains. For such pWSTS, including probabilistic vector addition systems and Galton-Watson processes, we obtain a priori global horizons growing at most logarithmically in $1/\varepsilon$. In the non-uniform case, we give a drift condition ensuring the existence of a finite geometrically reachable set. Under this condition, we derive a priori horizons growing at most logarithmically in $1/\varepsilon$ and in the weight w(x) measuring the size of the initial state x. In both cases, we compute a horizon function whose evaluation on any initial state and precision requires only a constant number of elementary operations $(+, -, \times, / \text{ and } \log)$. For probabilistic lossy channel systems, this yields, to our knowledge, the first explicit a priori horizons from arbitrary initial states, and it extends to $ν$-pLCS, a new infinitely branching variant with probabilistic emissions.

cs.LO · cs.FL

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35304

Inference Latency-Aware Tsetlin Machine Training

Yefan Zeng, Shengyu Duan, Rishad Shafik, Alex Yakovlev

原文摘要

The Tsetlin Machine (TM) is a logic-based machine learning model well suited to low-latency inference on resource-constrained edge devices. Because each clause is an AND over Boolean literals, both the literals and their associated Tsetlin Automaton (TA) actions can be represented at the bit level, enabling bitwise evaluation and an early exit that is triggered as soon as any included literal evaluates to zero, forcing the clause output to zero. In this work, we study how the two TM training hyperparameters, T and s, govern both classification accuracy and inference latency. Building on the inversely proportional T-s relationship along which accuracy is nearly constant, we find that inference latency is reduced primarily by increasing s; rather than exhaustively searching the (T, s) grid at high training cost, we propose a directed search strategy that treats accuracy as a constraint and advances toward larger s to reduce inference latency within a fixed evaluation budget. Experimental results on the gem5 simulator with an ARM processor show that, for certain datasets, the search is able to increase s while preserving the baseline accuracy, thereby reducing inference latency at negligible accuracy cost: across six datasets, the method reduces inference latency by up to 16.34%, while some datasets exhibit an accuracy reduction of only 0.06%. The proposed strategy requires far fewer configuration evaluations than an exhaustive grid search.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35303

InterQ-RL: Interaction-Aware Correction of Execution Mismatch in Quantized Agentic RL

Yingbo Hao, Song Liu, Guanghua Yu, Zhaojing Zhou, Jianchen Zhu, Yi Zou

原文摘要

Multi-turn agent reinforcement learning (RL) relies on long closed-loop rollouts, making generation and KV-cache costs a major bottleneck. Quantized rollout reduces these costs, but its low-precision executor also serves as the behavior policy and can induce execution mismatch with the learner. Existing quantized-RL methods are designed primarily for single-turn generation. They align the learner forward with quantized rollout or correct the current-token rollout-learner ratio, without modeling the policy history that produces each agent state. Even after quantization alignment, residual rollout-learner mismatch accumulates along the state-reaching policy history, so a current action may look locally aligned despite a mismatched history. We introduce InterQ-RL (Interaction-aware Quantized Reinforcement Learning) to correct this post-alignment mismatch. It applies bounded execution-prefix correction over the state-reaching policy history, allocates correction strength across action segments by effective support under a fixed displacement budget, and requires no additional model forward pass. We evaluate dense and mixture-of-experts (MoE) backbones from 4B to 30B on ALFWorld, WebShop, and ScienceWorld, with all quantized arms sharing the same rollout with 8-bit weights, activations, and KV cache (W8A8-KV8). Across four environment-backbone settings, InterQ-RL achieves the strongest quantized endpoint result, matching BF16 to within 0.7 points and exceeding it in two settings. It matches or exceeds the learning speed of alignment alone while avoiding its late performance regression.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35989

Layerwise Repacking: Variable-Length Hybrid-Attention Training without an Extra Redistribution Pass

Jiahao Zhang, Junwei Feng, Dongliang Huang, Xiaoling Zhou, Yiqiao Liao, Chengru Song

原文摘要

Variable-length training creates conflicting parallelism requirements across the layers of a hybrid-attention model. The longest samples require wide sequence-parallel (SP) groups of 16 or 32 ranks for full attention, whose cost grows quadratically with sequence length. Sparse-attention layers, dominated by near-linear MoE work, can instead balance most evaluated workloads within node-local SP8 groups. Reusing the wide groups for these layers pushes their all-to-all communication across nodes, where the observed effective rate is 7.0x lower. Yet switching to smaller groups changes which ranks own each sample; a separate redistribution at every full-sparse boundary would introduce another data transfer. Layerwise Repacking keeps each SP16/32 parent for full attention and repacks its samples into node-local sparse children at SP{1, 2, 4, 8}, where hidden states persist between full layers. The layout change rides on the two existing full-layer Ulysses sites: at each, one variable-size all-to-all performs both the head exchange and the sample repacking, so no redistribution pass is added. Because the balance the children can reach depends on which samples share a parent, an auxiliary parent solver rebalances parent membership before the children are formed. On all 22 steps with SP16/32 parents among the first 200 training steps of a 1F3S hybrid-attention model (one full-attention layer per three sparse-attention layers), repacking alone reduces the mean end-to-end time by 5.95% and raises model FLOPs utilization (MFU) by 3.75 percentage points over the baseline with repacking disabled; with the improved solver, end-to-end time falls by 7.61% and MFU rises by 4.83 percentage points.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2605.29803

Gating and Learnable Temperature for Graph Attention Mechanisms

Zhongtian Ma, Hao Wu, Yexin Zhang, Qiaosheng Zhang, Chao Gao

原文摘要

Graph attention networks learn neighbor importance through data-dependent coefficients, but standard layers lack explicit control over unreliable feature dimensions and use fixed sharpness of attention coefficient distributions. This paper proposes gated graph attention and learnable temperature for common graph attention mechanisms. Gated graph attention filters feature or message responses to reduce the influence of unreliable dimensions, while learnable temperature dynamically adjusts the sharpness of the attention coefficient distribution. We conduct experiments on five standard node classification benchmarks and five heterophilic benchmarks. On most of these benchmarks, our two modifications improve upon the corresponding graph attention backbones, and combining them can yield further gains. Controlled noise experiments further verify the behavior of the proposed mechanisms under feature perturbations. Theoretical analysis explains these results by showing that gating improves robustness when only part of the feature coordinates are reliable, while temperature is beneficial when global noise weakens the discriminability of node features.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35987

PROBE: Frontier Coding Agents Find Different Bugs Than Maintainers Fix

Marco Paina, Mark Niklas Müller, Niels Mündler-Sasahara, Martin Vechev

原文摘要

Proactive bug discovery is an important software-engineering problem. Even though coding agents are already widely deployed in this domain, their capabilities remain understudied. In particular, the challenging task of finding all bugs that human maintainers would repair across an entire repository has not been studied yet. To close this gap, we introduce PROBE, a benchmark consisting of all 2,457 bugs fixed over the course of 18 months across 20 diverse GitHub repositories, together with a method for matching candidate findings to this partial reference set. We evaluate coding agents across frontier models and find they all achieve a recall of below $21\%$ and a precision of less than $9\%$ with respect to the reference set. While stronger models increase recall substantially from $8\%$ to $17\%$, they do not improve precision. Surprisingly, despite the low precision, LLM and human evaluators still judge $85\%$ of findings valid. Crucially, we find that found bug distributions are similar across agents but differ substantially from those of bugs fixed by maintainers. The practical relevance of bug discovery and the low recall of frontier models make this benchmark a valuable resource for both model users and developers.

cs.SE · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35298

LLM-Enhanced Heterogeneous Graph Learning with Business Semantics for Financial Fraud Detection

Yixuan Chen, Hongyu Zhan, Jie Sheng, Weiyu Han, Shuai Chen, Tianyi Zhang, Xiao Tan, Jun Xia

原文摘要

Financial fraud detection increasingly relies on heterogeneous transaction graphs, in which entities such as cards and merchants play distinct business roles and the risk meaning of an attribute depends on the entity's role: a high transaction volume may be routine for a merchant but unusual for a card. Heterogeneous graph neural networks preserve typed entities and relations but typically treat these attributes as role-agnostic inputs and leave their business meaning implicit. Meanwhile, most existing methods integrating large language models (LLMs) with graphs focus on homogeneous graphs or heterogeneous graphs with naturally available textual attributes, leaving their use on transaction graphs with structured attributes underexplored. To address this issue, we propose SemHGT, an LLM-enhanced framework that interprets structured attributes according to entity roles and makes the business semantics explicit in three stages: (1) role-aware prompts elicit risk-related business descriptions from node attributes, and a text encoder maps them to semantic vectors that enrich node representations; (2) semantic similarity guides multi-round sampling of target-specific path instances under transaction-to-transaction schemas; (3) schema-level tokens that combine local path evidence with global neighbor summaries are processed together with the target transaction by a unified transformer. Across three benchmark datasets, SemHGT leads the evaluated baselines on most dataset--metric comparisons. Further analyses provide additional evidence for the effectiveness of SemHGT's design and clarify how its semantic modeling and evidence selection contribute to fraud detection. Code is available at https://anonymous.4open.science/r/SemHGT-528A/.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35297

Testing with Coding Agents: A Large-Scale Comparison of Agent-Supported and Human-Authored Pull Requests

Roberto Milanese, Francesco Salzano, Hovhannes Muradyan, Jingjing Wu, Remo Pareschi, Fausto Fasano, Mattia Fazzini

原文摘要

Context. Coding agents increasingly contribute tests through pull requests that developers then maintain, so how testing work is divided affects long-term maintainability. Objective. We compare pull requests in which developers and coding agents collaborate (agent-supported) with pull requests without detectable agent involvement (human-authored) along five dimensions: the frequency and extent of test changes, their type and context, test structure, test smells, and code coverage. Method. We analyze 114,134 pull requests merged between January 2025 and April 2026 in 391 Java repositories, identifying five coding agents through pull-request-level and commit-level signals. Since agent adoption varies across projects, we compare the two groups within repositories with mixed-effects models that control for change size. Results. Pooled across repositories, both groups change test code almost equally often; within repositories, the odds that an agent-supported pull request does so are 1.65 times higher. Agent-supported pull requests add tests more often (odds ratios 1.50-1.58) and modify (0.70-0.76) and delete (0.51-0.77) them less often. We detect no difference in most structural characteristics of the tests they add, which more often have an oracle, nor, in the 95 repositories we could build, in the coverage of their production changes; in test-only pull requests, however, their tests cover less of the code they exercise. Differences in test smells are borderline and not reproduced for individual test methods. Conclusions. Agent participation is associated with a different mix of testing work, which pooled comparisons across projects can hide or reverse; its relationship with test quality remains uncertain.

cs.SE

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35296

Trim: Fee Level Matters More Than Skew in Lightning Routing

Huiping Sun, Peilu Guo, Yiming Zhu, Yueqi Wu, Zhong Chen

原文摘要

Lightning routing nodes lend their channel balance for a posted fee. Operators' tools move that fee with the balance around a hand-set level, and which part of the fee drives revenue is unclear. We present Trim, which models a channel as a two-sided inventory with costly refills. Its optimal fee is a level, set by demand and replenishment, plus a balance skew, the shadow price of liquidity. The level is first order: no fee rule beats the ceiling demand and replenishment set, and on exactly solved channels the best flat fee comes within $1.6\%$ of the optimum at the median, whereas a level off by a factor of two loses tens of percent. The skew is second-order insurance: it adds at most what the flow-balancing flat fee loses to refused forwards. So the level should be chosen: Trim's rule traces the revenue--success frontier, posts one level on every channel, and adds a skew only where refills stay frequent and costly. On a 2026 snapshot with synthetic payments, no tuned tool beats that frontier by over a few percent, and a skew changes gross revenue by a few percent.

cs.NI · cs.CR · cs.GT · eess.SY

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35295

Did the Model Use That? Counterfactual Training Boosts Self-Attribution in Language Models

Zikai Zhou, Jiacheng Sang, Yilin Xu, Yufei Jin, Monica S. Lam

原文摘要

A fundamental challenge for explainable and accountable language models is revealing how external information influences their answers. This paper examines whether models are self-attributive: that is, whether they indicate when -- and only when -- their responses to questions are influenced by information provided alongside the question. Furthermore, we explore how self-attribution can be improved through counterfactual training, which explicitly teaches models to distinguish between answers that do and do not depend on supplied information. We found that most of the eleven frontier models rarely attribute influential information in their answers, and the rest attribute non-influential information. Training acknowledgment into reasoning does not fix this: the acknowledgment does not reach the final answer. We introduce CREDIT, which directly supervises final-answer self-attribution with counterfactual labels, without the need for human annotation. CREDIT substantially improves attribution in four open models, including two distilled reasoning models, and outperforms reasoning-level fine-tuning and prompting baselines. Among answers that agree with a user's suggestion, CREDIT distinguishes those changed by the suggestion from those the model would have given anyway. Gains transfer partly to unseen information types and prompts containing sources that support conflicting answers.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35294

Application of Artificial Intelligence in the Management of Climate Change-Related Health Issues in Africa

Peter Kokol, Martha Kachweka, Helena Blazun Vosner, Samuel Chol Buol, Jernej Zavrsnik, Bojan Zlahtic, Grega Zlahtic

原文摘要

While climate change disproportionately impacts African public health, AI predictive modeling remains heavily constrained. Using a Synthetic Knowledge Synthesis approach and VOSviewer, we conducted a bibliometric analysis of Scopus-indexed literature, comparing Global and African corpora. Network analysis reveals stark divergences: global research emphasizes complex, predictive models for planetary health, whereas African research focuses on localized, reactive solutions for immediate infectious disease triage. Severe structural barriers in Africa, including compute deficits, data silos, and energy instability, hinder advanced AI scaling. Ultimately, international funding must shift from siloed pilot projects toward building foundational digital infrastructure and localized AI frameworks.

cs.AI · cs.CY

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.26893

Learning Faithful Reasoning Processes with Spatio-Temporal Latent Dynamics for Large Language Models

Weijiang Lv, Wentong Zhao, Jiayu Wang, Yuhao Wu, Jiaheng Wei, Xiaobo Xia

原文摘要

Chain-of-Thought (CoT) reasoning has significantly enhanced the reasoning capabilities of large language models (LLMs). However, existing reinforcement learning methods primarily optimize outcome-level rewards, providing limited supervision over the reasoning process. As a result, models may produce shortcut-prone or unstable reasoning trajectories even when the final answer is correct. We propose GeoFaith, a spatio-temporal latent dynamics framework for learning faithful reasoning processes without process reward models. GeoFaith combines final-state latent uncertainty, which measures whether a completed trajectory lies in a well-supported manifold region, with predictive-entropy dynamics, which penalize abnormal uncertainty patterns such as premature collapse, oscillation, and prolonged uncertainty. These signals are incorporated as process regularization into GRPO, jointly optimizing answer correctness and reasoning quality without step-level process annotations. Experiments show that GeoFaith consistently improves reasoning accuracy, produces more efficient reasoning trajectories, and outperforms both outcome-only reinforcement learning and process-supervision baselines.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35293

AgenticCity-Bench: Longitudinal Multimodal Observations of Urban Dynamics with Agentic Reasoning

Xiaofei Yu, Kailai Sun, Yanyu Mao, Baoshen Guo, Heye Huang, Yongcai Wang, Baotong Mi, Alok Prakash 等 10 位作者

原文摘要

City systems are shaped by interactions among infrastructure, human activity, and environmental conditions. Existing earth observation and urban benchmarks are limited in unified modeling and in capturing their joint dynamics. We introduce AgenticCity-Bench, a longitudinal multimodal benchmark for multi-layer unified state modeling and agentic city task reasoning. The benchmark covers 16 cities in 12 countries across six continents from 2000 to 2025, and includes 18 modalities spanning urban function, activity, and environmental state. It organizes heterogeneous data sources around a common spatial reference and calendar index while preserving spatial and temporal coverage, provenance and tile-level availability. On this foundation, AgenticCity-Bench supports urban cross-modal translation together with diverse agentic city tasks involving forecasting, planning and resource analysis. This study provides a unified benchmark for studying the transition from multimodal urban and earth observation to joint understanding and agentic city decision-making. The dataset is available at https://anonymous.4open.science/r/AgenticCity-Bench.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35291

BROCADE: Broker-based Contract Design for the Multi-Agency Model

Yangguang Shi, Ron Lavi, Jie Zhang

原文摘要

We study welfare maximization in a contract model with $m$ principals who privately value a public project's success and $n$ agents whose costly effort is unobservable. Contracts induce truthful dominant strategies for principals and equilibrium effort by agents, maximizing the expected total value of eligible principals. We develop three tools: a broker that separates payments from principals and payments to agents, an extension of Myerson's Lemma characterizing dominant-strategy incentive compatibility (DSIC), and a black-box reduction to budget-constrained single-principal contract design. When the success probability is a strictly monotone XOS function of agents' actions, these tools yield three results. First, a deterministic DSIC contract achieves a constant approximation against a benchmark that qualifies every principal and maximizes success probability using budget $\sum_j v^j$, but may violate budget balance (BB). Second, against benchmarks with budgets at least the largest principal value, deterministic DSIC and BB contracts admit no finite approximation guarantee, even with two agents. Universally DSIC and universally BB randomized contracts have an $Ω(n)$ approximation lower bound, even for a fixed number of principals. Third, using one quarter of the optimal fixed-price revenue supported by at least two principals as the benchmark budget, we obtain a universally DSIC and universally BB randomized contract with an $O(\log m)$ approximation ratio independent of $n$.

cs.GT

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35289

Reward-Guided RRT* for Budgeted Task and Motion Planning

Vinícius Araújo de Oliveira, Gabriel Ferreira Mendes Lourenço, Paulo L. J. Drews-Jr, Armando Alves Neto, Douglas G. Macharet

原文摘要

Robotic missions involving spatially distributed tasks often require jointly selecting rewarding locations and planning feasible motions under limited travel budgets. This paper proposes Reward-Guided RRT*, a new sampling-based framework that constructs a budget-feasible mission through a sequence of locally joint task-selection-and-motion-planning stages, evaluated directly in the continuous state space, without requiring a precomputed task-transition graph. The method incrementally builds a mission using reward-guided RRT* searches, while a return-feasibility procedure ensures that each selected task can be visited without violating the mission budget. Experiments with increasing obstacle complexity and number of tasks show solutions comparable to VNS-PRM* while requiring substantially fewer sampled states. We also extend the framework to Dubins steering and evaluate it in CoppeliaSim with a scaled car-like robotic platform, demonstrating its ability to incorporate vehicle kinematic constraints.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.32878

Advancing SVD-based LLM Compression via Layer-Wise Error Model Search

Moritz Thoma, Maximilian Groezinger, Maximilian Forstenhäusler, Emad Aghajanzadeh, Manoj Rohit Vemparala, Christos Anagnostopoulos, Pierpaolo Mori, Nael Fasfous 等 11 位作者

原文摘要

Low-rank SVD-based compression offers a powerful strategy to reduce the computational costs of LLMs. However, existing methods face two key limitations: (i) global rank allocation, where uncalibrated error proxies fail to capture complex error propagation, and (ii) decomposition quality, where Fisher-based estimators suffer from severe rank collapse. In this work, we address these limitations by introducing Layer-wise Error Modeling Search (LEMS) and KFAC-SVD. LEMS advances rank allocation by introducing a layer-wise error surrogate that integrates local and global layer importance alongside a propagation bias, enabling effective global rank allocation via an ILP formulation. KFAC-SVD improves decomposition quality by utilizing token-wise statistics, mitigating the rank deficiency observed in prior Fisher-based SVD approaches. Across Mistral, Qwen3, and Llama 3 model families, we show that LEMS consistently outperforms existing search strategies, delivering significant zero-shot accuracy gains of up to 4.7 p.p. that generalize to model sizes of 70B parameters, while KFAC-SVD achieves an average perplexity improvement of 19%. Project page and code: https://lems-svd.github.io

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35288

Proof-of-Agentness: Towards Verifying Agents on the Web

Zuyao Xu, Xiang Li

原文摘要

CAPTCHAs and bot detection have helped protect Web services from automated abuse for decades by distinguishing humans from bots. However, the emergence of LLM-powered agents introduces a new setting: Web services increasingly accommodate agents as legitimate users. Without a way to distinguish agents from other automated clients such as simple bots and scripts, these services risk large-scale automated junk submissions that waste service resources and consume users' attention or tokens. In this paper, we investigate a novel question for today's Web: "How can a Web service obtain evidence that a client is an agent?" We introduce the concept of "Proof-of-Agentness" (PoA), a mechanism for distinguishing agents from other automated clients, motivated by the parallel between human attention and an agent's inference resources. We outline two approaches: active verification through challenge-response and passive analysis of service-visible signals. Eight language models achieve an overall accuracy of 96.5% on our challenges, with an average overhead of 1,647 tokens. For passive analysis, we conduct an IRB-approved user study comparing the Web interactions of twelve human participants and representative Bot and Agent implementations, achieving an average classification accuracy of 95.8% across four classifiers, motivating further study.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.09699

Cranio-Diff: Diffusion-based Cross-domain Craniofacial Reconstruction with 2D X-ray Skull Guidance and Structural Identity Constraints

Ravi Shankar Prasad, Naresh Gurjar, Shashank Baghel, Chirag, Dinesh Singh

原文摘要

The identification of unknown human remains is a persistent humanitarian and forensic challenge. In forensic investigations, it becomes even more challenging when common biometric DNA identifications, such as soft-tissue or hair strands are not present, as they degrade with time. To narrow down the process of identification, few attempts have been made to identify an individual by reconstructing a face from the given skeletal remains ( i.e., skull) using generative AI models, such as CycleGAN, Pix2Pix, and diffusion models. However, they fail to effectively capture semantic information in craniofacial reconstruction, due to a mismatch in the alignment of structural information across modalities. To address this issue, we propose Cranio-Diff, a diffusion-based framework for craniofacial reconstruction from 2D X-ray skull images. The proposed approach integrates skull-conditioned structural guidance through ControlNet with biometric text prompts to generate a face. The proposed Cranio-Diff method is evaluated on skull-face dataset obtained from X-ray scans of 120 subjects in lateral and frontal views. To enable controlled evaluation, each face image is artificially synthesized across three age groups (25, 45, 65) and three BMI variations 10%, yielding 4320 paired samples. This dataset is also curated across different facial modalities ( RGB and sketch) with different appearance conditions (hair and without hair). To the best of our knowledge, this is the only X-ray-face dataset with this magnitude. Extensive experiments showed that the proposed method achieves improved performance over the recent existing approaches in both generated image quality and retrieval task. Finally, to evaluate the performance of our proposed method, we have evaluated the quality of the generated image using FID, SSIM, LPIPS score.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35282

Satellite Intelligence: Distributed Training, Collaborative Inference,and LLM Adaptation in LEO Constellation

Zheng Lin, Zhanwei Wang, Yuxin Zhang, Yafei Wang, Ons Aouedi, Zihan Fang, Jinfeng Xu, Jing Yang 等 12 位作者

原文摘要

The proliferation of orbital sensing data and the real-time demands of emerging global services are pushing low Earth orbit (LEO) satellite networks from bent-pipe relays toward intelligent onboard processing. This shift confronts a fundamental tension, where modern artificial intelligence (AI) training paradigms require intensive computation, abundant memory, and stable connectivity, all of which are scarce under the dynamic topologies, intermittent links, and severe size, weight, and power (SWaP) constraints of satellite networks. Addressing this tension demands rethinking AI workflows, from training and inference to the emerging deployment of large language models (LLMs), under a constraint-aware design philosophy. To the best of our knowledge, this paper provides the first survey that jointly covers all three, whereas prior surveys examine these aspects in isolation. We begin by identifying the deployment challenge of satellite intelligence (SI) and deriving design principles for SI. We then examine three advancing paradigms: i) distributed training, where federated learning (FL) and split learning (SL) enable satellite-ground co-training under resource limitations; ii) collaborative inference, which exploits single-satellite, multi-satellite, and satellite-ground architectures to meet real-time service demands; and iii) on-orbit LLM adaptation and serving, which tackles the frontier challenge of deploying LLMs under severe orbital constraints and resource-aware serving. Finally, we identify open challenges and future directions. By bridging the AI and satellite networks, this paper provides a research roadmap for the implementation of space-native AI technologies.

cs.NI · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35985

Let the Gate Decide: Per-Lookup Precision for Quantized Conditional Memory in LLMs

Tianqi Chen, Xunchao Li, Linchuan Xie, Guanghua Yu, Jianchen Zhu, Peisong Wang, Jian Cheng

原文摘要

Conditional memory layers, such as DeepSeek's Engram, attach large hashed n-gram tables to a language model, and removing them from DeepSeek-V4.1-Flash costs 36.8 PopQA points. Low-bit quantization loses long-tail facts first, and the standard remedy, giving more bits to frequently accessed rows, backfires: refining lookups by access frequency is worse than refining them at random. We trace this to the gate that scales each retrieved row. A lookup's quantization error is weighted by its gate, which is small for frequent n-grams, large for the rare n-grams of long-tail entities, and computable from a 1-bit code. GateRQ therefore stores each row as a ladder of 1-bit residual codes, keeps level 1 in GPU memory to compute the gate, and reads deeper levels only for the lookups the gate ranks highest. Without retraining, GateRQ cuts GPU table memory by 7.8x on DeepSeek-V4.1-Flash, which raises vLLM throughput by 11%-31% over FP8 tables, while losing about 1 PopQA point at 1.50 bits read per lookup and 0.2 points at 2.10 bits across two models.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35984

Enhancing Deep Learning Model Performance through Data Generation Strategies: Classification of Olive Tree Diseases

Hicham El Akhal, Abderrahim Waga, Aissa Ben Yahya, Abdelbaki El Belrhiti El Alaoui

原文摘要

Deep learning models are highly effective in a wide range of domains, particu larly in plant disease diagnosis. However, their performance is often limited by challenges such as insufficient data and class imbalance. In our work, we propose a comprehensive data generation strategy to overcome these limitations. First, we apply various data generation techniques, including traditional augmentation methods, CutMix, MixUp, and synthetic image generation using Deep Convolu tional Generative Adversarial Networks (DCGANs), to create new data samples. Second, we exploit this generated data in three scenarios: (S1) balancing class distribution in the original dataset, (S2) increasing the number of samples per class, and (S3) expanding the dataset while maintaining balanced classes. Third, we evaluate the impact of these data distributions (S1, S2, S3) on model perfor mance using the EfficientNetV2B0 architecture with pre-trained and fine-tuned weights. The experimental results show a substantial improvement in classifica tion accuracy, emphasizing the critical role of data diversity and class balance. These findings highlight the effectiveness and adaptability of the proposed strat egy of data generation and distribution for enhancing dataset quality, offering promising applications in plant disease detection and precision agriculture.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35280

Self-Supervised Pretraining for PHM: What Transfers, What Does Not, and What Federating It Costs

José Sanz-Durán, David Solís-Martín

原文摘要

Self-supervised pretraining has produced capable time-series foundation models, but its value for Prognostics and Health Management (PHM) has not been measured under leakage-controlled conditions. We measure it on a corpus of 47 public PHM datasets, harmonized to a single tensor contract and partitioned so that 11 datasets are withheld from pretraining in full. Transfer turns out to be task-dependent: a compact channel-independent Transformer encoder (801,808 parameters) pretrained with masked patch prediction raises fault-classification macro-F1 from 0.350 to 0.812 on CWRU and from 0.569 to 0.951 on HSG18, yet on CMAPSS remaining-useful-life estimation no pretrained checkpoint reliably improves upon a from-scratch baseline. We pretrain under two regimes---centralized, and simulated cross-silo federated with ten clients grouped by physical domain---holding architecture, objective, source data and optimization budget fixed. Two further findings are negative. At matched budget the centralized encoder leads by 15.5--20.2 macro-F1 points in four of four comparisons, although the comparison is confounded by a learning-rate schedule that favours the centralized arm and rests on a single pretraining run per regime; on RUL the two regimes are indistinguishable. And the intrinsic SSL loss is not a valid selection criterion: the centralized encoder more than halves the federated reconstruction loss without a corresponding gap on RUL, and a server-momentum sweep moves downstream validation macro-F1 by up to 0.29 while the SSL loss varies by 0.021. Transfer also hinges on the backbone learning rate: the same checkpoint yields 0.169 or 0.829 macro-F1 on CWRU depending on a single order of magnitude. We release the corpus pipeline, the protocol and the code.

cs.AI · cs.CE · cs.LG · cs.PF

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2603.12272

ActTail: Global Activation Sparsity in Large Language Models

Wenwen Hou, Xinyuan Song, Wenqian Weng, Shiwei Liu

原文摘要

Activation sparsity is a promising approach for accelerating large language model (LLM) inference by reducing computation and memory movement. However, existing activation sparsity methods typically apply uniform sparsity across projections, ignoring the heterogeneous statistical properties of Transformer weights and thereby amplifying performance degradation. In this paper, we propose ActTail, a TopK magnitude-based activation sparsity method with global activation sparsity allocation grounded in Heavy-Tailed Self-Regularization (HT-SR) theory. Specifically, we capture this heterogeneity via the heavy-tail exponent computed from each projection's empirical spectral density (ESD), which is used as a quantitative indicator to assign projection-specific sparsity budgets. Importantly, we provide a theoretical analysis that establishes an explicit relationship between the activation sparsity ratio and the heavy-tail exponent under the HT-SR regime, offering principled guidance for sparsity allocation beyond heuristic design. Experiments on LLaMA and Mistral models show that our method improves both perplexity and downstream task performance at high sparsity compared to uniform allocation. At 80% sparsity, perplexity is reduced by 21.8% on LLaMA-2-7B, 40.1% on LLaMA-2-13B, and 9.4% on Mistral-7B.

cs.CL · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35277

Identities, Not Pairs: Distribution-Free False-Accept Control for Embedding-Based Verification

Salim Khazem

原文摘要

Embedding-based verification often calibrates a false-accept threshold from all impostor pairs among $m$ identities, although these pairs share identities. We characterize a worst-case limit: when hub identities score highly against a fraction $ρ$ of the population, a calibration-only threshold with marginal false-accept rate (FAR) at most $α$ under every identity-exchangeable law reaches the hub score on hub-free calibration sets with probability at most $(m+2)α/(2ρ)$. Uniformly accepting near that score at levels well below $ρ/m$ therefore requires trial information. We propose COVE, which ranks the trial pair among all $N=\binom{m+2}{2}$ pairs formed by augmenting the calibration units with the probe and reference. Under identity exchangeability, its marginal FAR is at most $\lfloorαN\rfloor/N$, with first possible acceptance at $1/N=O(1/m^2)$. The rule also retains this guarantee with a fixed symmetric cohort-normalized score using an independent cohort. On 6 benchmarks and 8 frozen encoders, realised FAR was consistent with the exact bound. Where both valid calibration-only baselines accepted nothing, COVE retained a median $100\%$ of the sampled oracle's true-accept rate over reliable comparisons. In contrast, an empirical quantile over dependent pairs reached 2.87$\,α$ FAR, and a binomial upper confidence bound over pairs missed its nominal 95\% conditional-FAR target in up to 55\% of calibration draws. Symmetric CSLS raised COVE's true-accept rate by up to 4.3-fold in the tested settings. The code is available in https://github.com/salimkhazem/Cove.git

stat.ML · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v4arXiv:2610.10270

Video Prediction Policy 2: Predict Better, Act Better

Yanjiang Guo, Haodong Yan, Zhide Zhong, Zhongru Zhang, Qingyuan Yang, Qingzhou Lu, Xiaoyu Chen, Yen-Jen Wang 等 18 位作者

原文摘要

World action models (WAMs) have emerged as an important class of generalist robot policies, aiming to transfer video prediction priors to action learning. However, we find that existing WAMs frequently produce incorrect motion predictions in open-ended environment, leading to erroneous actions. We attribute this limitation to two factors: (1) base video models are not optimized for manipulation, and (2) naively incorporating action components into video models can substantially degrade their generalization capabilities. We introduce Video Prediction Policy 2 (VPP2), a WAM that enables strong zero-shot generalization in both video prediction and action generation. First, we curate a large-scale, diverse dataset of manipulation videos to continue pretraining the base video foundation model. We annotate video clips with detailed captions and perform \textit{event-level} video pretraining to promote generalization across open-ended manipulation tasks. Second, we post-train and distill the video model into a single-step visual planner with fixed prediction horizon. Finally, we introduce action module via a mixture-of-transformers (MoT) architecture to learn implicit inverse dynamics model. Experiments demonstrate three key results: (1) VPP2-14B outperforms Cosmos3-64B by 11.0\% points in video prediction instruction-following success rate on open-ended tasks; (2) VPP2 surpasses the strongest baseline by 18.5\% points in success rate on real-world zero-shot ALOHA manipulation tasks; and (3) following benchmark-specific post-training, VPP2 achieves the highest success rates among evaluated methods on the challenging LIBERO-Pro, LIBERO-OOD, and RoboDojo benchmarks.

cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.12063

Learning Loco-Manipulation From SMPC Demonstrations With Sparse Offline-to-Online RL

Martin Schuck, Maks Sorokin, Simone Manni, Duy Ta, Angela P. Schoellig, Marco Hutter, Simon Le Cleac'H, Jan Brüdigam

原文摘要

Integrating locomotion and manipulation is essential for robot autonomy, but scaling standard Reinforcement Learning (RL) to complex tasks is severely bottlenecked by the slow, manual process of dense reward shaping. To bypass this limitation, we leverage Sample-based Model Predictive Control (SMPC) entirely in simulation as an automated, rapidly tunable expert to generate massive offline datasets. Because this data solves the fundamental exploration problem, we can train an off-policy RL agent using purely sparse task rewards, drastically reducing the time required to learn new skills and eliminating the need for manual tuning. Integrating this high-level agent with a low-level dynamic stability controller yields more optimal behaviors that strictly align with true task objectives, ultimately allowing the learned policies to surpass the original optimal control teacher. We validate the robustness of this sim-to-real framework by successfully deploying complex loco-manipulation skills across different morphologies, including an arm-equipped Spot quadruped and a G1 humanoid.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2610.35272

The Voice on the Line

Husein Zolkepli

原文摘要

A transcriber listening through one microphone also hears everyone near it. We train causal voice isolators: masking transformers of 140M, 243M and 374M parameters, 20 ms of latency, enrolling the caller from the call itself. Short evaluation windows hide two failures that real calls expose: forgetting the caller when another voice talks alone for a while, and damaging a caller who is alone. Long calls with turns, memory beyond the attention window, real headset crosstalk and drifting caller levels address both, but each trades one against the other. WavLM-Large's own weights, made causal and trained with the model, move the trade: M with them (555M parameters) lowers the error on our development sets from 11.44% to 10.55%; a student trained from scratch to imitate WavLM does not, and w2v-BERT 2.0 and Whisper's encoder, pre-trained on far more audio, help less or not at all. A lone caller loses most at the start of a recording: no training call opened with someone already talking. Training on windows cut from longer calls lowers the error on clean development calls from 3.92% to 2.96%; this is our release. Live, the release makes 16.13% word errors on 60 s AMI windows, against 23.66% for VoxLock, the strongest open isolator, and 10.19% on its own AMI windows, against 11.71%; it is level on Krisp's benchmark (5.74% against 5.63%), and a caller who is alone still loses more words than with VoxLock (5.58% against 2.92% on clean test calls). Distilled into 22.1M parameters without WavLM, it runs live on one CPU thread inside a LiveKit agent, at 33% of a core per call in 20 ms frames, with 10.66% error on our development sets (the release 10.49%). We open-source the release and this CPU model, with a LiveKit plugin, at https://huggingface.co/collections/Scicom-intl/voice-isolator.

cs.SD · cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2602.10230

Encode Once, Decode Never: Reusing Audio LM Internals for Efficient Temporal Localization

Joseph An, Phillip Keung, Jiaqi Wang, Orevaoghene Ahia, Noah A. Smith

原文摘要

Audio language models process input audio into rich frame-level representations, but the standard approach to temporal localization generates timestamps as sequences of text tokens, which discards the frame-level representations in favor of autoregressive decoding. However, generating timestamps as tokens is slow and not parallelizable, and tends to hallucinate when producing timestamps outside the training distribution. We propose internal frame-level reuse, a method that trains audio LMs to reuse their own internal audio representations for temporal localization directly, bypassing token generation altogether. We introduce a lightweight prediction head trained via different frame-level objectives: a binary frame classifier and a novel inhomogeneous Poisson process (IHP) loss that models temporal event intensity. Across word localization, speaker diarization, and event localization tasks, our approach can achieve a >50x inference speedup over token-based generation and demonstrates robust length generalization, maintaining high accuracy on out-of-distribution audio durations where token-based models collapse completely. We find that reusing audio frame-level representations yields localization accuracies comparable to (and often better than) finetuned token-based baselines.

cs.LG · cs.SD · eess.AS

查看论文
arXiv ↗PDF ↗