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

+1072新增论文
+845其中 AI 相关
+94已有论文修订
+100新增 AI 导读

arXiv 最近完成扫描：2026-11-09 16:31 · 全站最近入库：2026-11-09 13:22各信源进度 →

统计口径与数据新鲜度

统计 2026-11-08 17:02 — 2026-11-09 17:02（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：2026-11-09 16:31最近发现新增版本：2026-11-09 13:22库内论文最新更新时间：2026-11-07 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。

18,172 已收录论文15,506 AI 相关4,527 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 4,579 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-09 16:29（北京时间）
版本更新 · v2arXiv:2610.33026

False Belief Dissemination, Persistence and Mitigation in Multi-Agent Social Networks Through the Lens of the Mandela Effect

Dianzhi Yu, Hongru Wang, Ziheng Xiong, Yanyu Chen, Zixing Song, Jianting Chen, Zhenfei Yin, Jeff Z. Pan 等 10 位作者

原文摘要

Multi-agent social networks are emerging as communities in which agents communicate, retain memories, and publish information that others can find as evidence. These interactions create opportunities for false claims to spread and remain influential beyond their original sources, analogous to the Mandela effect in human societies, in which many people recall the same false memory. In this paper, we systematically study false-belief dynamics through the lens of the Mandela effect, focusing on dissemination, persistence, and mitigation. Specifically, we build a controlled framework connecting agent communication, private memory, and a shared simulated web to mimic information dissemination in practical social networks, supported by 540 fabricated claims spanning 8 domains and 4 plausibility levels. For dissemination, we measure how widely and quickly claims gain acceptance across models and communication topologies. For persistence, we withdraw agents promoting fabricated claims while retaining existing articles and memories, and track subsequent acceptance. For mitigation, we compare preventive measures applied before implantation with corrective interventions introduced after claims have spread. Experimental results show that evaluated models readily accept and disseminate fabricated claims, with dissemination reach as high as 96.0%. Dissemination reach varies with claim plausibility, domain, and network size and composition, while communication topology shapes dissemination speed across model families. Acceptance barely declines after fabricators withdraw, and targeted corrective interventions outperform the preventive measures without eliminating false beliefs. These findings identify persistent false beliefs as a safety challenge for multi-agent social networks and highlight the need to address both their initial dissemination and the accumulated evidence that sustains them.

cs.SI · cs.LG · cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2606.16190

Embedded Arena: Iterative Optimization via Hardware Feedback

Zhihan Zhang, Alexander Le Metzger, Jiuyang Lyu, Chun-Cheng Chang, Jiayi Shao, Yujia Liu, Emmanuel Azuh Mensah, Edward Wang 等 13 位作者

原文摘要

As AI moves into the physical world, from robots to environmental sensors to medical wearables, it increasingly relies on local inference to meet latency, communication, or privacy constraints. Optimizing models for heterogeneous edge hardware such as microcontrollers (MCUs) requires simultaneously satisfying hard physical constraints on memory, power, and temperature while preserving accuracy, a multidimensional optimization that is today performed manually by experts. We ask whether an LLM agent can autonomously navigate this complex, multi-turn pipeline guided by real hardware feedback, and introduce a hardware-in-the-loop agent arena in which the agent iteratively refines both model and firmware by compiling, flashing, and measuring on real hardware, enabling closed-loop optimization. Frontier models, including Claude Opus 4.7 and Gemini 3.1 Pro, fail entirely without hardware feedback (0% deployment success), whereas our hardware-in-the-loop formulation achieves the first successful deployment within three iterations and can surpass human expert results within seven. This agentic co-optimization achieves 250x compression for vision models with <3.3% accuracy loss and 400x for audio with <6% Feature Error Rate loss, enabling battery-free operation on a commercial MCU via solar harvesting. We demonstrate practical impact in two real-world systems: an elk-detection camera trap (96.7% accuracy) and a phonetic-transcription wearable (8.37% FER) for child development research.

cs.AR · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09065

MongoBench: Do LLMs Know What a MongoDB Query Will Do?

Qibai Chen, Haoting Qiu, Yezhou Cheng, Mengxiao Qian

原文摘要

LLM agents increasingly operate databases on their own: they generate queries and run them against live data. Two checks are commonly used to judge such an agent - whether it produces a valid query, and whether it reaches the right final answer - but neither tells us whether the agent knows what its query will actually do before it runs. We argue that this consequence prediction ability must be evaluated in its own right, and we build MongoBench to measure it: given a collection of documents and a MongoDB find() filter, a model must return the exact set of matching _ids, with ground truth from a real mongod server. The 300 items each compose three or four documented matching pitfalls and are proposed symmetrically by three vendors' models, so results stratify by item source. Evaluating four models - frontier systems from three vendors and one open-weight reasoner - accuracy ranges from 70.1% to 92.1%, a 22-point spread. Each proposer mispredicts 10-31% of the items it wrote itself, so producing a query does not imply predicting its effect. A failure-mode analysis shows errors are better predicted by which semantic pitfall a query exercises - range comparisons and null - than by surface measures such as document count or the number of composed rules. Prepending a verified rule sheet helps unevenly; executing the original filter against the engine yields reliable match sets, but delegation must be checked: on 28% of items (averaged over three runs) one model's executed filters never passed a canonical check against the intended query, and it answered about 22 of them wrong, while the other three passed on every item. We release the benchmark, the mongod oracle, and the evaluation code with all prompts at https://github.com/research-repo-bai/MongoBench.

cs.SE · cs.DB

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2512.24637

Towards Fully-fledged GPU Multitasking via Proactive Memory Scheduling

Weihang Shen, Yinqiu Chen, Rong Chen, Haibo Chen

原文摘要

Limited HBM capacity has become the primary bottleneck for hosting a growing number of increasingly larger-scale GPU tasks. While demand paging extends capacity via host DRAM, it can incur order-of-magnitude slowdowns due to the massive working sets of GPU workloads. However, we observe that GPU memory accesses are inherently predictable from kernel launch arguments, prior executions, and the asynchronous execution nature. Leveraging this opportunity, we propose MSched, an OS-level scheduler that extends GPU context switching to include proactive working set preparation. This approach coalesces fragmented, eventual, and expensive page faults into a single efficient migration. MSched combines parameterized templates with page fault feedback to accurately predict working sets, and co-designs the task scheduler and memory manager to resolve global access order and enforce near-optimal page replacement. Across scientific, deep learning, and LLM workloads, MSched outperforms demand paging by up to 186.69x and whole-process swapping by up to 8.63x. MSched is open-source and has been integrated into https://github.com/XpuOS/nvxsched.

cs.OS

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09061

Does Reasoning Improve Psychological Depth in Large Language Models?

Ruichen Zheng, Yihe Wang, Fabrice Harel-Canada, Sara Khosravi, Zeynep Senahan Yildiz, Amit Sahai, Nanyun Peng

原文摘要

Benchmark gains from reasoning-enhanced large language models encourage the assumption that these models should broadly perform better on complex generative tasks, but this remains underexplored in open-ended, creative domains shaped by nuances of reader experience. We tested this assumption through the lens of psychological depth in short stories. We compared DeepSeek-R1 vs. DeepSeek-V3, our closest available contrast for reasoning-oriented post-training, and GPT-5 vs. GPT-4o, through 60 blinded pairwise evaluations in which seven human annotators and an ensemble LLM-as-a-Judge rated prompt-matched story outputs. Human evaluations showed no universal reasoning advantage: GPT-5 was slightly preferred over GPT-4o (60.0-62.9% across two reasoning-effort settings), whereas DeepSeek-R1 fell behind DeepSeek-V3 (42.9%). Although this pattern was marked by low inter-annotator agreement (Krippendorff's $α= 0.070$), our annotation-quality checks suggested genuine evaluative subjectivity, plausibly reflecting distinct annotator decision schemes rather than annotation failure. In contrast, the LLM-as-a-Judge showed a strong pro-reasoning bias (98.3% of pairs vs. 55.2% of human votes), consistent across its five configurations and partly tracking sentence length. These findings suggest that, at the frontier, reasoning-related quality differences are small enough to be dominated by reader subjectivity, and that LLM-as-a-Judge evaluators can obscure this subjectivity in nuanced creative-generation tasks.

cs.CL

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2512.18563

OpenView: Empowering MLLMs with Out-of-view VQA

Qixiang Chen, Cheng Zhang, Chi-Wing Fu, Jingwen Ye, Jianfei Cai

原文摘要

Recent multimodal large language models (MLLMs) show great potential in natural image understanding. Yet, they perform well, mainly on reasoning in-view contents within the image frame. This paper presents the first study on out-of-view (OOV) understanding, i.e., the ability to reason about objects, activities, and scenes beyond the visible frame of a perspective view. Our technical contributions are threefold. First, we design OpenView, a four-stage pipeline that leverages panoramic imagery for large-scale and diverse multi-choice VQA synthesis, where full-scene coverage enables flexible view framing while preserving global scene awareness. Second, we curate OpenView-Dataset, a high-quality synthetic dataset from diverse real-world panoramas to empower MLLMs upon supervised fine-tuning. Third, we build OpenView-Bench, a benchmark that jointly measures choice and rationale accuracy for interpretable and diagnosable evaluation. Experimental results show that despite having a large gap from human performance in OOV VQA answer selection, multiple MLLMs, upon empowered by OpenView, can consistently boost their performance, uplifted from 48.3% to 62.3% on average. Code, benchmark, and data are available at https://github.com/q1xiangchen/OpenView.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09055

OmniLatent: Unified Latent for 3D Part Modeling

Yunhan Yang, Yunfei Zhao, Zeqiang Lai, Jiachen Xu, Minxiu Wang, Xintong Han, Xiangyu Yue, Xihui Liu 等 9 位作者

原文摘要

3D part decomposition is a central capability for editable asset creation, yet existing workflows typically segment a completed mesh as a post-processing step, making the result sensitive to geometric artifacts, texture ambiguity, and limited part-level annotations. We present OmniLatent, a unified latent modeling framework for 3D part decomposition. Instead of predicting part labels in isolation, OmniLatent learns a shared latent space that jointly encodes geometry, deformation, appearance, and binary part IDs, allowing data-rich geometric and visual priors to support data-scarce part learning. Given a single input image, the base model generates geometry, deformation, texture, and surface part IDs in one pass, producing a part-aware 3D asset without a separate segmentation stage. We further tune the pretrained model for two extensions: a point-prompt adapter that maps arbitrary 3D point prompts with binary part IDs into latent tokens for full segmentation, refinement, and part subdivision, and an amodal part completion model that completes partial surface masks into a coherent full-object decomposition through dynamic per-part token allocation, cross-attention to the given geometry latent, and alternating part-local and global attention. Extensive experiments show that OmniLatent produces semantically meaningful part segmentations with precise boundaries, supports interactive part editing, and completes partial part observations while preserving global object consistency.

cs.CV

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2607.13460

LPM: Industrial-Scale Generative Video Restoration

Bichuan Zhu, Fulin Li, Jiachao Gong, Jinhua Hao, Kai Zhao, Kun Yuan, Pengcheng Xu, Qiang Wang 等 18 位作者

原文摘要

We present the Large Processing Model (LPM), a diffusion-based generative framework for photorealistic video restoration under complex, in-the-wild degradations. To our knowledge, LPM is the first generative video restoration model deployed at industrial scale. LPM addresses the diverse degradations in user-generated content (UGC) through a unified system encompassing large-scale data engineering, foundation-model training, and efficient inference. Its enhanced architecture, progressive training strategy, and temporal-pyramid inference mechanism jointly enable high-fidelity, temporally consistent restoration of arbitrarily long videos across the broad content distribution encountered on UGC platforms. LPM has been deployed in production at Kuaishou, where videos processed by the model account for approximately 45% of total viewing time, delivering consistent improvements across key quality-of-experience metrics. Beyond perceptual enhancement, LPM delivers substantial system-level benefits: at comparable perceptual quality, it reduces bitrate by 20% relative to Kuaishou's in-house codec, yielding annual bandwidth cost savings on the order of hundreds of millions. Its low serving cost also enables integration into products such as Kling, demonstrating that generative restoration can be practical, scalable, and cost-effective for large-scale video processing.

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09042

Failure Profiling and Reachable Trajectory Selection for Reasoning Distillation

Yijun Zhu, Jianxin Wang, Chengchao Shen

原文摘要

Training smaller language models on reasoning solutions generated by a larger teacher model is the prevailing approach for transferring mathematical reasoning capabilities. However, the student tends to overfit the output distribution of the teacher and generalizes poorly when its own behavior at inference time deviates from the training data. Recent methods attempt to bridge this gap by incorporating error data, yet the corrective trajectories still reflect the reasoning patterns of the teacher, which the student cannot reliably reproduce, leaving the distribution mismatch largely unresolved. We propose a method, Failure Profiling and Reachable Trajectory Selection (FPRT), built on the insight that effective training data should be jointly determined by what the student fails on and what it can realistically learn. Our method first profiles the failure behavior of the student on each problem through repeated sampling, characterizing it in terms of error rate and error consistency to reveal qualitatively distinct failure modes. Each mode demands a fundamentally different training signal. The diagnosed mode then guides candidate generation from the teacher via distinct prompting strategies tailored to each failure type. Among the correct candidates, our method selects the one whose initial reasoning steps after the point of divergence are most reproducible by the student. These first corrective steps constitute the primary bottleneck, while the remaining steps follow an already corrected context and can therefore be continued more readily. This contrasts with standard reranking approaches, which score the trajectory as a whole and thereby dilute the signal at the critical reasoning transition. Experiments demonstrate that our method achieves the SOTA performance across the five benchmarks on both student backbones.

cs.CL · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09041

DobotTrack: Target-Grounded Vision-Language-Action Learning for Embodied Person Tracking

Shengjun Deng, Yinghan Zhang, Chengrui Wei, Liu Liang, Songyuan Liu, Pengkun Zheng, Yajun Zheng, Ying Zhang 等 11 位作者

原文摘要

Language-guided embodied person tracking requires a mobile agent to identify a target from a referring description and consistently follow the target under egocentric observations. We present DobotTrack, a target-grounded vision-language-action (VLA) framework that integrates auxiliary grounding supervision with efficient temporal modeling. We systematically investigate five auxiliary tasks---person segmentation, bounding-box grounding, visual-spatial classification (VSC), future DINO feature prediction, and future-frame prediction---and adopt complementary mask and bounding-box supervision to enhance target delineation and localization. We introduce Q-identity, a target-conditioned historical visual compression module that leverages target-grounding predictions to selectively preserve identity-discriminative appearance features and spatial cues in compact historical tokens. On EVT-Bench, our 0.8B-parameter model achieves an average success rate of 77.9%, exceeding OmTrackVLA by 16.9 percentage points across the three tasks. We further construct a real-world person-tracking dataset collected using a quadruped robot, comprising 126 episodes and 596,323 mask-annotated frames. The target masks enable automatic derivation of bounding boxes and visual-spatial labels encoding horizontal position and apparent image scale, providing additional grounding supervision without separate manual annotation of these labels. Together, our framework and annotation pipeline support learning target-grounded tracking policies from simulated and real-world data. Code is available at https://github.com/Dobot-Team/dobot_track.

cs.RO · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09036

ToolDex: An Ego-Exo Human Demonstration Dataset for Creative Physical Tool Use

Mohamed Elmoghany, Kehan Li, Ruoqu Chen, Tarun Chiruvolu, Shutong Zhang, Ryan Wang, Stephen Tian, Yaru Niu 等 14 位作者

原文摘要

Creative tool use is a fundamental human capability and an important step toward general-purpose embodied intelligence. It requires agents to reason about object affordances, physical constraints, and manipulation strategies, especially when standard tools are unavailable. However, progress in this area is limited by the lack of real-world datasets that capture human tool-use behavior with sufficient scale, fidelity, and diversity. Existing benchmarks are often simulation-based, focus on simplified interactions, or lack detailed observations and annotations. We introduce ToolDex, a large-scale egocentric-exocentric (ego-exo) human demonstration dataset for creative physical tool use. ToolDex captures scenarios in which humans select, adapt, and repurpose available objects as tools. Using synchronized egocentric cameras and eight exocentric cameras, the dataset provides high-fidelity multi-view observations and rich annotations for hands, tools, target objects, and their deformable interactions. Beyond data collection, we establish a benchmark suite characterizing three core capabilities: physical tool-use reasoning, sparse-view 3D and 4D reconstruction, and robot policy learning. ToolDex provides a foundation for studying human tool-use behavior and developing embodied agents that can adaptively use tools in complex real-world environments. Dataset visualizations and benchmarking results are available at https://tooluse-dataset.github.io/.

cs.RO · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.08251

VoxCanvas-41M: A Large-Scale Bilingual Dataset for Instruction-Based Speech Editing and Its Learning Dynamics

Zhikang Niu, Wenming Tu, Yalin Li, Yanru Huo, Junxi Liu, Tianrui Wang, Ruiqi Yan, Junxuan Liang 等 11 位作者

原文摘要

Recent advances in speech generation have spurred the development of speech editing techniques. However, achieving high-quality speech editing remains challenging due to two key limitations. First, the major hurdle is the lack of large-scale, high-quality speech editing datasets. Constructing such datasets is costly, while open-source, scalable data pipelines remain limited. Second, the learning dynamics of speech editing models remain poorly understood. In particular, how models acquire editing capabilities and the relationship between generation and editing remain unclear. To address these challenges, we introduce VoxCanvas-41M, a large-scale bilingual dataset comprising approximately 41 million speech editing pairs. VoxCanvas-41M covers two major categories: content editing, including single-span, multi-span, and location-reference editing, and paralinguistic editing, covering the insertion and deletion of 39 classes of nonverbal events such as laughter, sighs, and coughs. Building on VoxCanvas-41M, we train VoxCanvas-Edit, an instruction-based speech editing model, demonstrating the effectiveness of our dataset in improving editing performance. Furthermore, we systematically investigate the learning dynamics of speech editing, examining how models learn different editing operations and how data scale, task interactions, and training strategies affect editing performance. The dataset, pipeline, and demos are publicly available.

cs.SD · eess.AS

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2611.08080

Spatiotemporal Dynamics-Aware Industrial Anomaly Detection and Reasoning

S-Wei Chen, Siangyu Yang, Yi-Chen Jan, Chun-Yi Lee, Shao-Yuan Lo

原文摘要

Industrial Anomaly Detection (IAD) is a long-established problem that aims to detect defects in industrial products during manufacturing for quality control. Most existing studies focus on static visual patterns as the basis for detection. However, in real manufacturing environments, many anomalies are dynamics-based, such as irregular movements that cannot be perceived from static cues alone. We observe that even recent Multimodal Large Language Model (MLLM)-based approaches fall short in identifying such dynamic anomalies due to limited temporal modeling capability. To address this, we introduce MUSTARD: MUltimodal SpatioTemporal Anomaly Reasoning and Detection, a framework that equips MLLMs with fine-grained spatiotemporal dynamics awareness for detecting and reasoning about dynamics-based defects. MUSTARD introduces optical-flow-guided keyframe selection and augmented modalities to capture critical motion irregularities through local motion patterns and global dynamic evolution. Its normal pattern-based reasoning pipeline requires only a few normal reference samples as the detection basis, avoiding any model updates. This enables efficient adaptation across various products and provides high decision interpretability. MUSTARD is the first MLLM-based framework for dynamics-based IAD. Experiments demonstrate its superior performance in detecting spatiotemporal anomalies and providing plausible explanations. Our code is available at https://github.com/racercode/Mustard

cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09030

A Controlled Study of Models, Skills, Feedback, and Curriculum in Agentic Robotics

Kaiyuan Chen, Xinyue Zhu, Shuangyu Xie, Uksang Yoo, Thi Thu Phuong Luong, Marcus Gualtieri, Christian Juette, Liu Ren 等 10 位作者

原文摘要

Agentic robotics asks coding agents to implement and iteratively improve robot policies from simulated and real-world physical interactions. We study the self-learning loop of agentic robotics through a controlled simulation study spanning nine manipulation tasks, 631 different experiment configurations, and 28K coding agent rollouts, systematically varying model capability, skill priors, feedback structure, and curriculum. The experiment data suggests that the bottleneck is often not the access to sufficient information, but interpreting it into the right policy update. Across these factors, a successful self-learning loop depends on how effectively agents attribute failures, reason task-relevant spatial and geometric structure, and selectively restructure code to improve policies.

cs.RO · cs.AI · cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.08777

Measuring and Decomposing Mode Separation via the Canonical Diffusion

Shaul Tolkovsky, Ori Meidler, Or Zuk

原文摘要

Mode separation, namely how sharply a distribution fragments into barrier-separated clusters, is a fundamental geometric property of densities, difficult to quantify in high dimensions. Modes are often the meaningful alternatives in the data, such as the conformations of a molecule or the distinct semantic types among a generative model's outputs. Mode separation is distinct from dispersion, which is what standard label-free tools capture: differential entropy rises with spread regardless of fragmentation, and PCA orders directions by variance regardless of barriers. Mutual information does capture it, but only given the latent component labels, which are usually unavailable. We measure mode separation through a single stochastic process intrinsic to the density, namely the unique reversible diffusion with $f$ as its stationary distribution and a constant scalar diffusion coefficient. From its autocovariance matrix we extract two readouts. The first, SSA (Sum of Squared Autocorrelations), is a scalar barrier-sensitive measure. The second, DA (Dominant Autocorrelation directions), gives linear projections ordered by metastability rather than variance. Under an isotropic-Gaussian null, we derive the limiting spectrum of the empirical autocovariance in closed form, generalizing the Marchenko--Pastur law. Its upper edge gives a noise floor that separates metastable directions from sampling noise. Both readouts use only samples and a score function, scaling to high dimensions through pretrained score-based generative models via Tweedie's identity. We apply our framework to three settings: (i) synthetic Gaussian mixtures, where SSA tracks mutual information; (ii) SDXL text-to-image generations, where SSA and DA capture structure that entropy and PCA miss; and (iii) molecular dynamics of alanine dipeptide, where DA recovers the known slow backbone dihedrals from static samples alone.

stat.ML · cs.LG · math.PR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09006

Rethinking Latent Reasoning for Generative Recommendation: Beyond Teacher-Generated CoT and Recurrent Hidden-State Feedback

Yiwen Chen, Fuwei Zhang, Zehao Chen, Deqing Wang, Hehan Li, Peizhi Xu, Hanmeng Liu, Shuanglong Li 等 11 位作者

原文摘要

Latent reasoning in generative recommendation faces two practical barriers: constructing teacher-generated chain-of-thought (CoT) supervision is costly, and recurrent hidden-state feedback requires a specialized execution loop. We revisit both the supervision source and the computation interface. A step-level diagnosis measures how recommendation CoT supports next-item prediction and trace coherence. In the analyzed traces, history analysis is the only step with positive mean contributions on both dimensions, while later preference and intent steps have negative mean answer contributions. Guided by this finding, we propose PHiT (Prefilled, History-Informed Thought Tokens), which learns intermediate states from semantic targets extracted directly from observed item histories. PHiT aggregates cached sparse item encodings to construct these targets and supervises the contextual states of distinct vocabulary thought tokens. All thought tokens are supplied together as ordinary input IDs during a single causal prefill, removing the need for recurrent final-state feedback. With supervised fine-tuning alone, PHiT outperforms the compared baselines across four recommendation benchmarks. Controlled ablations support the value of input-matched semantic supervision, while cost measurements show fast target construction with training time comparable to the recommendation-only thought-token baseline.

cs.IR

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.09004

Sharing the Road: LLM-Based Bargaining in Mixed-Autonomy Traffic

Lingxiao Zhou, Di Chen, Jia Li

原文摘要

Mixed-autonomy traffic involves heterogeneous driving populations competing for shared road space. Previous studies have shown the existence and emergence of collective rationality using game-theoretic and reinforcement learning approaches, which rely on explicitly specified behavioral assumptions or reward functions for driving agents. However, how bargaining behaviors between driving agents evolve and lead to collective outcomes based on richer agent characteristics and language-based reasoning remains less understood. To fill this gap, we develop a bargaining framework based on large language models (LLMs) in which population-level autonomous vehicle (AV) and human-driven vehicle (HV) agents negotiate road-space allocations under heterogeneous objectives and private information. Through controlled experiments varying traffic composition, agent objectives, and traffic-domain knowledge, we examine bargaining behavior, coordination, and resource utilization. Results show that negotiated allocations respond to relative traffic density without strictly following proportional sharing, while density-balanced states exhibit greater coordination difficulty. Fairness-oriented objectives substantially improve agreement rates but do not necessarily yield equally high road-space utilization. Furthermore, domain knowledge affects bargaining outcomes differently across objective configurations, shaping both coordination and the role-dependent effects of fairness. These findings demonstrate the potential of LLM-based bargaining for modeling and designing interactions among driving agents in mixed-autonomy traffic.

cs.MA

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2509.23178

Limit Analysis for Symbolic Multi-step Reasoning Tasks with Information Propagation Rules Based on Transformers

Tian Qin, Yuhan Chen, Zhiwei Wang, Zhi-Qin John Xu

原文摘要

Transformers are able to perform reasoning tasks, however the intrinsic mechanism remains widely open. In this paper we propose a set of information propagation rules based on Transformers and utilize symbolic reasoning tasks to theoretically analyze the limit reasoning steps. We show that the limit number of reasoning steps is between $2^{L-1}-1$ and $\frac{3^{L-1}-1}{2}$ for a model with $L$ attention layers in a single-pass. In addition, we find that, for problems with a fixed number of reasoning steps, Transformers exhibit a preference for generating sequences that satisfy certain ordering relations. Ultimately, we construct a Transformer and prove that the limiting reasoning depth is achievable.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08996

UniMore: Fine-Grained Supervision for Unified Understanding and Generation

Haoyue Bai, Yinyi Luo, Yicheng He, Qingsong Wen, Sharon Li, Jindong Wang

原文摘要

Unified multimodal models combine image understanding and generation within one system, creating an opportunity to improve both capabilities through paired image--text supervision. We examine the outputs of a pretrained unified model in both directions and observe a loss of specificity: generated images can contain the requested objects with incorrect attributes, while captions identify a scene without expressing its distinguishing details. These failures call for supervision that specifies both the visual content to realize and the descriptive differences to distinguish. We propose UniMore, a post-training method that derives these complementary learning tasks from the fine-grained content of image--text pairs. The generation route predicts grounded crops from their corresponding phrases, matching the scope of the condition and visual target while using the native visual objective. The understanding route combines positive-caption fitting with ranking against captions that omit or alter details, conditioned on the full image. The two routes are optimized independently, and their learned updates are combined into a single unified model without changing its inference procedure. Experiments show gains across multiple understanding and generation benchmarks.

cs.MM · cs.CV

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08993

When2What: A Timing-Conditioned Framework for Long-Horizon Forecasting of Continuous Cardiovascular Waveforms

Chaoqi Zhang, Shujie Yan, Zhao Zhang, Yanhua Sun, Yu Wang, Li Li, Lingzhong Meng, Xiaoyi Chen 等 9 位作者

原文摘要

Long-horizon forecasting of quasi-periodic cardiovascular waveforms, such as the electrocardiogram (ECG), arterial blood pressure (ABP), and photoplethysmogram (PPG), requires predicting both when future cardiac events will occur (beat timing) and what the local structural pattern looks like around each event (beat morphology). However, standard sequence forecasters trained with pointwise mean squared error (MSE) average across uncertain future heartbeat phases, flattening sharp R peaks and pulse upstrokes into featureless baselines. Our analysis of intraoperative ECG reveals a clear temporal asymmetry: beat-time predictability from history decays within seconds due to stochastic heart-rate variability, whereas local beat morphology aligned at true beat times remains stable over several minutes. Guided by this insight, we introduce When2What, a timing-conditioned framework comprising three stages: Predict, Commit, and Generate. Given a 120-s history, When2What predicts a dense 60-s timing map, selects and sharpens discrete beat events into unit-height Gaussian impulses, and conditions a neural waveform generator on both these committed events and the observed history. Across intraoperative ECG, When2What substantially outperforms existing time-series and physiological forecasters, achieving a near-term waveform event skill of 0.644 and reproducing 95.62% of its predicted heartbeats in the generated waveform where direct long-horizon forecasters collapse into flat baselines. Furthermore, When2What transfers zero-shot to external hospital and atrial fibrillation cohorts, extends effectively to ABP and PPG pulse waveforms, and is supported by ablations and synthetic analyses that establish explicit timing conditioning as an effective paradigm for quasi-periodic long-horizon waveform forecasting.

cs.LG

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08989

LEF-JEPA: Denoising-Trained Latent Energy Fields for Spatial Representation Learning

Zhiyuan Liu, Zhihao Xu, Sicheng Liu, Huanhuan Huang

原文摘要

A joint-embedding predictive architecture (JEPA) that applies prediction supervision only at masked positions struggles to clearly capture object shapes and boundaries in its latent representations. We further observe that some existing methods improve spatial structure while also retaining rich variations in texture and color. However, preserving more low-level visual information does not necessarily make representations better suited to prediction and action. This raises a key question: how can we strengthen the spatial structure in latent representations that supports prediction and action without over-encoding these details? We introduce LEF-JEPA, which learns spatial structure through target-guided latent recovery and transfers this supervision to the visual encoder through a relative-energy constraint; the energy module is used only during pretraining and adds no inference overhead. To reduce the cost of energy optimization during pretraining, we further construct a conditional Ising Hamiltonian that allows low-energy-state search to be performed by specialized Ising solvers. On physical hardware, we validate the feasibility of achieving lower forward latency with fewer local updates. Under a unified CIFAR-10 pretraining and frozen-encoder evaluation protocol, both realizations outperform V-JEPA2.1 in image classification, foreground segmentation, and visual planning.

cs.CV · cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08985

NotaryMark: Multi-Bit Watermarking for Black-Box DatasetUsage Auditing in Text-to-Image Diffusion Models

Xinyi Yu, Linkang Du, Zhou Su, Min Chen, Yuntao Wang, Zhikun Zhang

原文摘要

As generative artificial intelligence (AI) models increasingly require data, more publicly available yet licensed data is being harvested and used without authorization. Although several previous studies have proposed watermarking methods for dataset copyright auditing, their applicability to the text-to-image (T2I) setting remains notably limited. The core drawback is that watermarks embedded by existing techniques are often treated as noise and are gradually filtered out and attenuated during the latent noising-denoising process of diffusion model training. We propose NotaryMark, to our knowledge the first multi-bit watermarking method specifically designed for black-box auditing of T2I training dataset use. The core idea of NotaryMark is to align the watermark with the latent denoising of diffusion models, thereby overcoming the signal decay that plagues existing multi-bit methods during sampling. We evaluate NotaryMark across three datasets and three diffusion models spanning watermark capacities from 8 to 1024 bits. With a watermark capacity below 32 bits, it achieves a high average bit accuracy of 0.85-0.90. With a watermark capacity exceeding 32 bits, it maintains bit accuracy between 0.67 and 0.80, consistently outperforming existing multi-bit watermark methods whose bit accuracy is around 0.42-0.60. Furthermore, we design a voting-based aggregation scheme to boost the bit accuracy with a modest budget of 30 queries. Building on this, we incorporate error-correcting codes to enable reliable decoding and tracing of the embedded identifier information. Robustness evaluation against fifteen evasion attacks spanning seven categories shows that NotaryMark remains robust under most evaluated settings, while stronger attacks generally suppress watermark evidence only at the cost of substantial utility degradation, demonstrating its practical reliability against malicious tampering.

cs.CR

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2610.11316

MetaEncoder: Exploring the Limit of Bi-Encoders for Multimodal System One Decision Making with Natural Language Interface

Jianpeng Cheng, Guangyu Sun, Aashu Singh, Benyu Zhang, Haixing Dai, Hossein Mansour, Jiangfan Zhang, Shlok Kumar Mishra 等 14 位作者

原文摘要

System One models prioritize fast, low-latency decision-making and calibrated probability distributions over token generation. While prevailing systems rely on structured schemas and typed outputs, candidate-scoring trade-offs remain poorly understood. We systematically investigate the scaling dynamics, accuracy, and inference efficiency of three scoring architectures adapted from a pre-trained decoder: bi-encoders, cross-encoders, and constrained decoders. Experiments show clear performance scaling with model size across all three architectures. Cross-encoders consistently achieve the highest accuracy across model sizes, while bi-encoders and constrained decoders perform similarly as training tokens scale. Efficiency-wise, bi-encoders maintain near-constant inference latency as candidate pools grow because candidate embeddings can be cached offline, whereas cross-encoder and constrained-decoder costs scale quadratically with candidate size. This efficiency advantage makes bi-encoders uniquely suited to bridge small closed-set decisions and massive open-set retrieval. For closed-set tasks, including all candidate options in the request prompt is critical for bi-encoder competitiveness. Guided by these insights, we introduce MetaEncoder, a multimodal encoder fine-tuned from a Muse-Glimmer decoder via unidirectional contrastive learning to match requests and candidates. We present packed contrastive training to maximize efficiency for dynamically allocated negative candidates, enabling memory-efficient full fine-tuning of a 30B decoder into an encoder. Evaluated across 12 benchmark suites spanning closed-set decision-making, multimodal understanding, and open-set retrieval, MetaEncoder outperforms state-of-the-art multimodal embedding baselines on decision tasks and MMEB-v3 image/video retrieval, while scaling to open candidate spaces far too large for current decision models.

cs.CL · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2608.01684

GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks

Jiarui Tan, Zhongjian Zhang, YaBo Guo, Jiawei Liu, Yujie Xing, Muhan Zhang, Cheng Yang, Chuan Shi

原文摘要

Large language model (LLM) agents are increasingly capable of planning, using tools, and interacting with external environments. They are typically supported by harnesses, which manage state and coordinate multi-step execution. Graph analysis provides a promising setting for evaluating their agentic capabilities, because it requires agents to access data and execute operations in a graph environment. However, existing graph benchmarks for LLMs provide limited coverage of graph tasks and graph types, making it difficult to comprehensively evaluate LLM agents. Moreover, they typically formulate graph analysis as text-based question answering, where graph information is directly provided in the prompt, limiting the evaluation of end-to-end agentic capabilities. To address these limitations, we introduce GABench, a comprehensive benchmark for agentic graph analysis. GABench spans three graph types and covers four graph analysis task categories: graph retrieval, graph theory, graph machine learning, and graph open-ended question answering. GABench also provides 84 executable tools for accessing graph data and performing diverse graph operations. Building on these tools, we develop an agentic graph analysis task generation pipeline and construct 10,400 tasks with verifiable ground truth.Using GABench, we evaluate a range of frontier LLMs and agent harnesses. Our experiments reveal three key findings: (1) Existing LLM agents still struggle with complex graph analysis tasks. (2) Harness choice significantly affects performance, yet existing harnesses remain limited on complex graph tasks. (3) Graph analysis depends more on tool-call quality than quantity. Our findings provide practical insights into the development and evaluation of LLM agents for graph analysis.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08977

Energy-Based Reasoners: Your Recurrent Reasoner Should Be an Energy-Based Model

William Xingxu Chen, Alexi Gladstone, Zeyu Michael Li, Heng Ji, Yilun Du

原文摘要

Looping is a powerful inductive bias for reasoning. By repeatedly iterating a recurrent block, looped models can scale their effective depth and enable multi-step reasoning in latent space. However, existing looped models are not inherently guided by an explicit measure of progress, making it difficult to determine when to stop looping and how to improve upon the current state. To enable this, we introduce Energy-Based Reasoners (EBRs), which learn an energy function over latent reasoning states and formulate looped updates as gradient descent on this energy. The energy scores latent states, while its gradient guides refinement and provides a signal for stopping. To train EBRs effectively, we further introduce exploration-based training to discover additional modes and to better shape the energy landscape over a broader set of states. Across four algorithmic reasoning benchmarks, EBRs match or outperform prior recurrent reasoning models, achieving 99.9% accuracy on Sudoku-Extreme while using 345$\times$ less inference compute than the next-best model and maintaining comparable training compute. On all multi-solution benchmarks, EBRs achieve state-of-the-art coverage of distinct valid solutions while maintaining near-100% single-sample accuracy. These results suggest that energy-based models are a promising approach for strong reasoning performance.

cs.LG

查看论文
arXiv ↗PDF ↗
版本更新 · v3arXiv:2608.08802

Improving Generalization Robustness of Multimodal RLVR

Pengfei Zhou, Zhiwei Tang, Chenrui Zhou, Lama Moukheiber, Yixing Ma, Bin Xu, Jiajun Song, Zhenglin Wan 等 13 位作者

原文摘要

Reinforcement Learning with Verifiable Rewards (RLVR) makes Multimodal Large Language Models more accurate, but the gains are brittle: simply paraphrasing a question or changing the prompt template can degrade them, which challenges reliable deployment in high-stakes scenarios like medical VQA. We trace this to two issues of the standard RL objective. First, the binary verifier conflates format with content, so the reward signal cannot tell a wrong answer apart from a misformatted one. Second, the training distribution covers only a thin slice of the real-world prompts that the model might meet at deployment, so policies that perform well on the training distribution can behave differently under unseen prompts during test. Both failures call for a robust post-training method that helps the policy cover a broader distribution of semantically equivalent prompts, and we identify two measures that help achieve this objective: separating format from semantics in the reward, and applying policy invariance across perturbed prompts with equivalent semantics. We therefore propose Prompt-Invariant RLVR (PIRL), consisting of a dynamic trinary reward and a consistency regularizer based on an embedding-space adversary. Under stress testing, PIRL's average accuracy on benchmarks drops by only $\le 1\%$, where GRPO drops ~3%. On dynamic evaluation, PIRL also achieves the smallest performance drop.

cs.AI

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08969

PhysioWave-T: Token-Efficient Wavelet Foundation Models for Biosignals

Yanlong Chen, Simone Benatti, Luca Benini, Cuntai Guan, Yawei Li

原文摘要

We present PhysioWave-T, a token-efficient wavelet foundation model family for EEG, ECG, and sEMG. Dynamic scale folding recombines J+1 wavelet subbands prior to tokenization, compressing sequence length from (J+1)CS to CS tokens for J levels, C channels, and S temporal patches. Route-specific front ends and learned channel-name embeddings allow one Transformer per modality to handle diverse montages and sampling rates, while unseen setups reuse the backbone via lightweight adapters. We pre-train a 30M-parameter EEG model on over 15M windows (19--128 channels), alongside ECG (30M) and sEMG (12M) encoders. Across four EEG routes, scale folding cuts Transformer latency by 4.0--7.2x and peak memory by 6.8--12.7x over scale expansion without accuracy loss. Our EEG encoder leads 8 of 9 metrics against BENDR, BIOT, LaBraM, and EEGPT, and surpasses LUNA-L on wearable seizure detection with fewer parameters. Reliability-aware latent fusion (RALF) further integrates summary tokens from independently pre-trained encoders via sample-adaptive weights. On SeizeIT2, RALF raises event sensitivity at 11 false alarms/h from 61.4% to 74.4% and window AUPRC from 0.321 to 0.399 over the best unimodal baseline, outperforming weighted-logit and concatenation fusion across all variants. PhysioWave-T also achieves state-of-the-art sEMG accuracies and top macro-F1 on PTB-XL Super and Chapman-Shaoxing. Code and models: https://github.com/ForeverBlue816/PhysioWave.

cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2604.01025

Fast and Accurate Probing of In-Training LLMs' Downstream Performances

Zhichen Liu, Tianle Lun, Yang Xu, Zhibin Wen, Hao An, Yulin Ou, Jianhui Xu, Hao Zhang 等 10 位作者

原文摘要

The paradigm of scaling Large Language Models (LLMs) in both parameter size and test time has pushed the boundaries of AI capabilities, but at the cost of making the traditional generative evaluation paradigm prohibitively expensive, therefore making the latency of LLM's in-training downstream performance evaluation unbearable. However, simple metrics like training loss (perplexity) are not always correlated with downstream performance, as sometimes their trends diverge from the actual task outcomes. This dilemma calls for a method that is computationally efficient and sufficiently accurate in measuring model capabilities. To address this challenge, we introduce a new in-training evaluation paradigm that uses a lightweight probe for monitoring downstream performance. The probes take the internal representations of LLM checkpoints (during training) as input and directly predict the checkpoint's performance on downstream tasks measured by success probability (i.e., pass@1). We design several probe architectures, validating their effectiveness using the OLMo3-7B's, OLMo3-32B's, and Apertus-8B's checkpoints across a diverse set of downstream tasks. The probes can accurately predict a checkpoint's performance (with avg. AUROC$>$0.75), have decent generalizability across checkpoints (earlier predicts later), and reduce the computation latency from $\sim$1 hr (using conventional generative evaluation method) to $\sim$3 min. In sum, this work presents a practical and scalable in-training downstream evaluation paradigm, enabling a more agile, informed, and efficient LLM development process.

cs.LG · cs.AI

查看论文
arXiv ↗PDF ↗
版本更新 · v2arXiv:2605.30844

Fine-Tuned Language Models Exhibit Improved Information Conveyance

Yuwei Cheng, Weiyi Tian, Haifeng Xu

原文摘要

Fine-tuning is often believed to reduce uncertainty and diversity in large language models, but existing analyses overlook output length, a key confounder, and therefore fail to capture how uncertainty is distributed across an entire generation rollout. To address this, we propose Canopy Entropy ($\mathrm{CE}^\star$), a measure that views language generation from a tree perspective, where "canopy" represents the space of all possible rollouts, making $\mathrm{CE}^\star$ naturally quantify the effective size of the generation space. $\mathrm{CE}^\star$ jointly captures uncertainty in both the output length $N$ and the generated sequence $Y_{1:N}$ -- indeed, we show that it equals total Shannon entropy $H(N, Y_{1:N}\mid X)$, where $X$ denotes the prompt. This formulation yields interpretable metrics, including a length-entropy correlation term $ρ(N, r_N)$, where $r_N$ is the entropy rate, quantifying information conveyance efficiency by indicating whether longer outputs are more or less informative per token. Empirically, across tasks and model families, we find that fine-tuned models predominantly exhibit more positive correlation $ρ(N, r_N)$, even when total entropy decreases. Furthermore, after controlling for model family, task, prompt, and output-length effects, we find that fine-tuning nearly triples the correlation strength between entropy rate and semantic diversity, suggesting that aligned models convert token uncertainty into semantic diversity more efficiently. Overall, these results demonstrate that fine-tuning does not simply reduce uncertainty, but fundamentally reorganizes it into more informative and semantically meaningful generations. Our code is available at https://github.com/WeiyiTian/canopy-entropy.

cs.CL · cs.AI · stat.ML

查看论文
arXiv ↗PDF ↗
新论文 · v1arXiv:2611.08946

Flex-RSI: Benchmarking Recursive Self-Improvement of Frontier Agents

Jingdong Zhang, Jionghao Wang, Zhengming Yu, Yancheng Cai, Wei Chow, Chris Choy, Zhiyang Dou, Hang Hua 等 22 位作者

原文摘要

Frontier language models are increasingly deployed as agents, and how well an agent performs depends not only on its model but also on its harness: the prompts, tools, memory, and control loop through which the model acts. When an agent is applied to a new problem, a natural question is whether it can use the feedback of the task to improve the way it works, and not merely its answer. Most existing benchmarks keep the agent's harness fixed and score the solution it produces, or target large-scale model training. We introduce Flex-RSI, a benchmark for the recursive self-improvement of agents on vision and robotics tasks under a fixed budget. In each round, an executor improves the task solution, which is kept only if it scores higher on held-out validation data, and an improver then revises the harness, including the executor and itself. Every run starts from the same general-purpose harness, and the final solution is scored on hidden test data. Evaluating closed-source and open-weight models on tasks spanning perception, reasoning, robot action, 3D reconstruction, visual creation, and infrastructure, we find that self-improvement helps most when the agent builds its own solution, that feedback recording only success or failure holds back open-weight models, and that open-weight models fall furthest behind where outputs must pass strict checks of physical stability or exact correctness. Paired runs further show that editing the harness itself contributes to the gains.

cs.AI · cs.CV · cs.RO

查看论文
arXiv ↗PDF ↗