跳到正文
研踪PaperTrail

论文库

检索计算机领域论文,按研究方向、作者或关键词筛选。

部分采集异常
正在读取账号与研究记录…

全站更新概况

+0新增论文
+0其中 AI 相关
+0已有论文修订
+92新增 AI 导读

arXiv 最近完成扫描:2026-11-23 01:07 · 全站最近入库:2026-11-21 12:19各信源进度 →

统计口径与数据新鲜度

统计 2026-11-22 07:43 — 2026-11-23 07:43(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:2026-11-23 01:07最近发现新增版本:2026-11-21 12:19库内论文最新更新时间:2026-11-20 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。

29,158 已收录论文24,181 AI 相关8,992 有修订112 HF 社区发现

浏览论文库

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 52 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-23 01:05(北京时间)
新论文 · v1arXiv:2611.26423

Seer:用共享决策模型引导小型深度研究智能体

Seer: Guiding Small Deep-Research Agents with Shared Decision Models

Yuhao Zhou, Yang Zhou, Yuanxi Li, Jindi Lv, Dan Si, Qing Ye, Jiancheng Lv

AI 速读 基于摘要

Seer 在推理阶段把智能体的动作提议与后果预测、价值估计分离,用离线训练、可跨智能体复用的模拟器与价值估计器为小型本地深度研究智能体提供引导。

cs.AI

查看原文摘要

Deep-research agents repeatedly decide what to search, read, and verify, often using large cloud-hosted language models for action proposal. However, privacy and local control motivate running agents on users' devices, where limited memory and compute favor smaller models and complicate on-device training. Yet inference-time guidance faces three obstacles: exploring alternatives through real execution adds tool calls, prompted self-evaluation is bounded by the agent's judgment, and model-specific guidance risks repeated adaptation costs. We introduce Seer, an inference-time framework providing local guidance that separates the agent's action proposal from learned consequence prediction and value estimation. From a shared corpus of real research trajectories, we train two models: a tool-response simulator on observed call--response pairs and a value estimator on histories labeled with discounted terminal correctness. The simulator and estimator are trained offline and reused across agents without further training. Moreover, Seer executes only the selected action and adds only real tool responses to the committed history, avoiding tool calls on discarded candidates at additional inference cost. Across multiple deep-research benchmarks, Seer substantially improves agent performance for different language models. For instance, GAIA accuracy rises from 13.6% to 41.7% for Qwen3.5-4B and from 22.3% to 50.5% for Qwen3.5-9B. Furthermore, our analyses suggest that broader candidate coverage can compensate for imperfect simulation, while prediction and scoring errors limit the benefits of wider imagined search. These findings highlight the potential of reusable models for prediction and evaluation to strengthen small research agents through extra local computation without the real execution of the discarded candidates.

新论文 · v1arXiv:2611.26349

Perfumer:基于大语言模型的智能体框架加速第一性原理计算中的结构弛豫与电子能带预测

Perfumer: A Large Language Model-based Agentic Framework Accelerating Structural Relaxation and Electronic Band Prediction for First-Principle Calculation

Zhiwei Li, Yuhao Zhou, Yikai Yang, Haonan Wang, Qing Ye, Jiancheng Lv, Kazunari Matsuda

AI 速读 基于摘要

Perfumer 是一个基于大语言模型的智能体框架,耦合 Quantum ESPRESSO 与两个预测模型,加速结构弛豫和电子能带预测。

cond-mat.mtrl-sci · cs.LG

查看原文摘要

First-principles structural relaxation and band calculations require substantial computation and expertise. Here we present Perfumer, a large language model-based agentic framework that couples Quantum ESPRESSO with two predictive models. Across tested structures, pre-relaxation with Perfumer-relax model followed by QE refinement yielded a 2.75-fold overall speedup over QE alone. Perfumer-band model combines a periodic graph neural network with a latent Hermitian spectral head returns 12 band energies at any requested wavevector, preserving reciprocal lattice periodicity and time-reversal symmetry without constructing Hamiltonian. Trained on 125,153 self-curated band structures, Perfumer-band model reaches a median per-material mean absolute error of 0.157 eV on 2,607 test materials, including lanthanide, actinide and magnetic compounds, from held-out composition families spanning 85 elements, taking about 97 ms per material on two consumer CPU cores. The agent turns natural-language requests into relaxation-to-band workflows, from a single uploaded structure to automatically constructed new candidates and returns predicted properties.

新论文 · v1arXiv:2611.24395

RSIBench-Infra: Can Agents Optimize Their Own Training and Inference Infrastructure at Production Scale?

Hanlin Wu, Yifei Wang, Zhicheng Cai, Huan-ang Gao, Wei-Ying Ma, Ya-Qin Zhang, Jingjing Liu, Hao Zhou

原文摘要

Improving the efficiency of training and inference infrastructure is a practical component of recursive self-improvement. Existing benchmarks for agent-driven optimization largely focus on individual software layers such as kernel, leaving unclear whether agents can deliver end-to-end performance gains under production workloads. We introduce RSIBench-Infra, a benchmark of 20 training and inference tasks spanning diverse model families and modalities, with deployments of up to 32 accelerators on NVIDIA GPUs and Ascend NPUs. Agents start from runnable baselines derived from official recipes and can modify the software stack across engine, kernel, and instruction levels. An OCI image-layer submission protocol captures these changes for reproducible deployment, while independent evaluation measures end-to-end performance under task-specific quality constraints. Across all task results, 66.2% exceed $1.10\times$ validated speedup. These results demonstrate that current agents can improve production-scale training and inference performance, but identifying effective optimization strategies and consistently translating local improvements into end-to-end gains remain challenging.

cs.LG

版本更新 · v2arXiv:2606.25319

V-Zero: Gating On-Policy Distillation with Contrastive Visual Evidence for Fine-Grained Visual Reasoning

Haoxiang Sun, Zhihang Yi, Langxuan Deng, Yuhao Zhou, Peiqi Jia, Jian Zhao, Li Yuan, Jiancheng Lv 等 9 位作者

原文摘要

Fine-grained visual reasoning requires multimodal large language models (MLLMs) to identify task-relevant visual evidence and ground their reasoning in local image regions. Existing methods typically rely on reinforcement learning with verifiable rewards or supervised fine-tuning on large-scale annotated reasoning traces, resulting in costly exploration, hand-designed verification rules, or heavy dependence on textual supervision. While On-Policy Distillation (OPD) offers a promising alternative via dense teacher supervision, its token-level objective inherently focuses on local token corrections, failing to assess global trajectory quality. In this work, we first reinterpret OPD as a stop-gradient alignment objective, revealing that its potential is limited by the absence of trajectory-level discrimination. Motivated by this observation, we propose V-Zero, which gates on-policy distillation with contrastive visual evidence. Specifically, V-Zero evaluates each trajectory under paired positive and negative visual views; the resulting likelihood contrast forms a trajectory-level gate that selectively amplifies updates from visually well-supported reasoning paths while suppressing ungrounded ones. Experiments on multiple visual reasoning and perception benchmarks show that V-Zero improves the Qwen3.5-4B backbone by 3.9 points on average while preserving strong generalization. Notably, V-Zero achieves more than 3$\times$ and 6$\times$ training speedups over representative supervised fine-tuning and reinforcement learning baselines, respectively. It requires neither annotated textual reasoning traces nor external reward signals. Code and dataset are released at https://github.com/eVI-group-SCU/V-Zero.

cs.CV

版本更新 · v2arXiv:2611.21072

Sage S2.1 Flash Technical Report

Kun Cai, Haodong Chen, Guangran Cheng, Qingxiu Cheng, Xu Dai, Guanting Dong, Qiming Ge, Lixin Gu 等 206 位作者

原文摘要

We introduce Sage S2.1 Flash, a 320-billion-parameter general-purpose mixture-of-experts model designed to reason over scientific evidence and act in interactive environments. Sage Sci-Perception uses dedicated encoders for molecular graphs and biological sequences and represents spectra as ordered patches of measurements. Modality-specific projectors map these representations into the input space of a shared backbone, which processes them alongside text and images. To develop the model's agent capabilities, we construct verifiable environments for tool use, search, and coding, as well as specialized workflows involving machine learning experiments and scientific software. Task completion is checked against execution results, changes in environment state, or submitted artifacts. We evaluate Sage S2.1 Flash on 33 benchmarks across seven domains. In the primary comparison against five baselines, it ranks first on OfficeQA Pro (72.2), MLE-bench Lite (90.3 HumanRank), Harvey LAB, and SpreadsheetBench 2, and second on OSWorld-Verified (85.2), WebArena-Verified (67.6), and DeepResearch Bench II (54.2). These results show particular strengths in using documentary evidence, producing verifiable workbooks, and carrying out machine learning tasks, alongside competitive performance in desktop and browser workflows that require the model to act on visual feedback.

cs.AI

新论文 · v1arXiv:2611.22657

SpatialCast: Reading the 3D World via Cast Shadows

Enhan Li, Jinghao Zhou, Jiaze Zhang, Hongyang Du

原文摘要

As multimodal large language models (MLLMs) advance toward understanding and interacting with the physical world, spatial reasoning becomes essential for understanding scene structure and anticipating the effects of physical changes. Existing spatial benchmarks have made substantial progress in evaluating spatial relations, memory, and viewpoint reasoning, but less systematically assess how models connect physical scene conditions with visual observations. We introduce SpatialCast, a benchmark that uses cast shadows to evaluate this ability. Cast shadows provide observable evidence of a 3D scene. Their image appearance depends on object geometry and pose, illumination, and viewpoint. We examine this relationship through three complementary tasks that assess scene-projection consistency, predict intervention-induced changes, and infer the physical changes behind visual transitions. The benchmark contains 21,000 synthetic questions with separate scene and geometry test partitions, complemented by 200 SpatialCast-Real questions from 20 photographed scenes. Evaluations show that closed-source MLLMs outperform general-purpose open-weight MLLMs and MLLMs designed for spatial reasoning, which remain near chance on the synthetic benchmark, while even strong closed-source models struggle with shadow-length and light-height judgments. We also use SpatialCast training data for GRPO post-training, improving open-weight MLLM performance on the benchmark. Further evaluations show improvements on several external spatial benchmarks, suggesting transfer of the learned capabilities. These experiments support SpatialCast as a controlled resource for diagnosing spatial reasoning capabilities and studying their learning and generalization.

cs.CV

新论文 · v1arXiv:2611.22109

VTT: Reading Vehicle Size and Powertrain Type from Motion Trajectory Across Unseen Car Models

Yuhang Wang, Yuechen Guo, Jingxin Yang, Chuheng Wei, Suyang Chen, Abdulaziz Alhuraish, Yiyi Wang, Mingyang Ban 等 10 位作者

原文摘要

Vehicle size and powertrain information can enrich trajectory data for traffic analysis and simulation. We present VTT, a dataset and benchmark for identifying these attributes from motion and controller area network (CAN) signals across unseen car models. The dataset contains 9,062 drives, about 3,950 h, from 1,431 vehicles and 174 car models. It provides three footprint-based size classes, powertrain labels, and evaluation on unseen car models and unseen drivers. Using 60-s windows, we compare four sequence architectures, statistical features and physical features proposed by large language models. Training with auxiliary physical targets, data augmentation and task-specific weighting raises drive-level macro-F1 to 92.6-93.0% for battery-electric versus combustion vehicles and from 62.9% to 67.1% for size classification. On public logs from 4,061 additional drivers, the full-input model identifies powertrain correctly for 86 of 88 car models; size accuracy is 63.2%, close to the internal vehicle-level result of 63.5%. Physical-feature analysis links powertrain recognition to deceleration behaviour and size recognition to steering response. Errors near size-class boundaries and limited gains from longer observations highlight the importance of label resolution and training-fleet coverage for cross-model generalisation.

cs.LG · cs.RO

新论文 · v1arXiv:2611.18442

CANTraj:从自然驾驶中的CAN信号恢复车辆轨迹

CANTraj: Recovering Vehicle Trajectories from CAN Signals in Naturalistic Driving

Yuhang Wang, Jingxin Yang, Chuheng Wei, Suyang Chen, Haozhuang Chi, Hao Zhou

AI 速读 基于摘要

作者发布自然驾驶数据集CANTraj及评测基准,系统比较六种轨迹恢复攻击,发现结合转向信号与路网约束能显著提升从CAN信号恢复轨迹的精度。

cs.CR · cs.DB

查看原文摘要

Open driving releases and usage-based insurance programs often claim to prevent privacy breaches by omitting GPS records when sharing or collecting vehicle data. However, removing GPS coordinates from driving logs does not erase the location information carried by vehicle signals. While prior route-inference attacks have demonstrated that speed, steering, and driving events can be matched to road networks to reconstruct trajectories, existing studies rely on inconsistent prior assumptions and evaluation metrics and are tested only on small, restricted datasets, making their results difficult to compare and their real-world effectiveness uncertain. We release CANTraj, a naturalistic driving dataset pairing decoded CAN events with time-aligned GNSS trajectories (3,940 drives, 454 drivers), and CANTraj-Bench for evaluating trajectory recovery (3,675 drives, 431 drivers, 1,380 hours, 85,919 km). On 776 evaluation drives from 94 unseen drivers, we compare six re-implemented attacks and benchmark baselines under explicit information-access protocols, paired comparisons, and metrics incorporating failures. Experiments show that combining steering signals with road-network constraints yields the largest gain: With a known start and heading, adding steering to speed raises the online map filter's five-minute route recovery from 56% to 87%, with a median average displacement error of 43 m versus 921 m for map-free dead reckoning. Offline beam search recovers 88% of test routes with the heading and 81% without it. Because methods fail on different windows, we also evaluate an LLM harness that selects among candidate routes on 659 five-minute windows; its best configuration recovers 79% of routes on test and 83% on few-shot, outperforming the best baseline on test and matching it on few-shot. Data and code at huggingface.co/datasets/HenryYHW/CANTraj and github.com/WangYuHang-cmd/GPS--CAN.

版本更新 · v4arXiv:2510.20279

CS-54k: A Paper-Grounded Corpus and Benchmark for AI Research QA

Penghao Wang, Yuhao Zhou, Mengxuan Wu, Ziheng Qin, Bangyuan Zhu, Shengbin Huang, Xuanlei Zhao, Panpan Zhang 等 15 位作者

原文摘要

Large language models (LLMs) are increasingly being used to support computer science research. To contribute reliably, these systems must be able to work with information distributed across research papers and across different aspects of the research process. However, large-scale resources that systematically organize such information into structured supervision for both model evaluation and post-training remain limited. To address this gap, we propose a systematic paper-to-QA construction pipeline that organizes information from AI research papers into structured QA pairs supported by source evidence. Using this pipeline, we construct CS-54k, a 54k-pair corpus derived from 14,474 openly licensed AI research papers. The corpus covers eight recurring paper components, including research domain, prior work, existing challenges, motivation, findings and assumptions, methods, experimental settings, and experimental results. We further derive two complementary subsets: CS-4k, a benchmark for evaluating LLMs on paper-derived research QA, and CS-50k, a companion corpus for post-training. Extensive evaluations on CS-4k reveal substantial performance differences across existing LLMs and paper components, with experimental settings and results remaining particularly challenging. Moreover, post-training on CS-50k substantially improves Qwen2.5-7B-Instruct on CS-4k, demonstrating the practical utility of structured, paper-derived supervision. Together, CS-4k and CS-50k provide a unified and scalable resource for benchmarking and improving LLMs on research paper question answering.

cs.LG

新论文 · v1arXiv:2611.16451

HIFC-IQA: Train-Free Cross-Domain Image Quality Assessment via Dual-Process Cognition

Yu Li, Zhengran Shen, Puchao Zhou, Yukang Ding, Yachun Mi, Boyuan Yang, Xi Zhai, Shaohui Liu

原文摘要

The gap between controlled synthetic distortions and complex real-world degradations introduces a critical domain shift challenge for No-Reference Image Quality Assessment. Although Unsupervised Domain Adaptation (UDA) approaches attempt to address this issue, they remain constrained by substantial retraining overhead and cumulative error propagation inherent in iterative pseudo-labeling. Inspired by the dual-process theory of human cognition for remarkable generalization ability, we propose Hierarchical Intuitive and Fuzzy Consensus (HIFC), a completely train-free Cross-Domain IQA framework. HIFC employs asymmetric perceptual decomposition to disentangle semantic content from distortion-sensitive representations. The final quality score is fused through the synergy of two complementary branches: a memory consensus branch that retrieves a stable Fuzzy Quality Centroid from a synthetic reference gallery, and an intuitive branch that captures aesthetic polarization via zero-shot vision-language alignment. Extensive experiments show that HIFC achieves state-of-the-art performance across multiple benchmarks, attaining the highest average SRCC and PLCC among competing UDA methods. Most notably, in the challenging synthetic-to-authentic cross-domain setting, HIFC achieves a substantial performance margin over competing methods, demonstrating remarkable robustness and generalization.

cs.CV

新论文 · v1arXiv:2611.13819

Game-Enhanced Embodied Learning with Event and Foresight Pretraining

Lianlei Shan, Han Jin, Yaunchao Ma, Xinpeng Chen, Linhao Zhou, Xin Bin

原文摘要

Human gameplay supplies paired observations, actions, and visual consequences that can supplement robot-policy training. We study event-and-foresight pretraining for InternVLA-A1.5, combining recorded keyboard/mouse event prediction with history-conditioned visual supervision through a frozen video model. Coverage-preserving anchor selection constructs one-second targets, and an attention mask prevents teacher-forced future actions from entering foresight queries. The selected corpus contains 394 recordings across 20 games, with 223.36 hours of recorded timestamp span and 2,072,084 training anchors. After 12,400 game-pretraining updates, we compare the resulting initialization with the public base under the same suite-specific robot fine-tuning protocol. Across four LIBERO suites, aggregate success increases from 1,718/2,000 (85.90%) to 1,811/2,000 (90.55%), a gain of 4.65 percentage points. Suite gains are 9.2, 6.8, 0.2, and 2.4 points on Spatial, Object, Goal, and Long. The 40-task breakdown shows 24 improvements, 10 declines, and six ties. These results support the practical value of the complete game-pretraining stage in this evaluated setting, while revealing heterogeneous task outcomes. The comparison includes additional optimization and does not isolate the effects of game data, the two objectives, or training variability.

cs.RO

新论文 · v1arXiv:2611.13768

Unified Far-field and Near-field Codebook Design for XL-array Systems

Chao Zhou, Changsheng You, Liujia Yao

原文摘要

While extremely large-scale antenna arrays (XL-arrays) hold immense promise for next-generation wireless networks, the paradigm shift encompassing new near-field communications renders conventional discrete Fourier transform (DFT)-based Type-I codebooks inefficient. Meanwhile, existing near-field alternatives usually impose prohibitively high storage and/or feedback burdens. To tackle these challenges, we propose in this letter a unified codebook applicable to both far-field and near-field XL-array systems. Our key idea is to express the near-field channel steering vector in an equivalent form, which is a Hadamard product of an angular vector and a curvature-related vector. This new representation allows direct reuse of the legacy Type-I codebook for angle quantization, while only a lightweight auxiliary codebook is newly added for additional curvature quantization. Subsequently, we optimize the auxiliary curvature codebook by maximizing the average beamforming gain given the information of user distribution. By leveraging the local monotonicity of the beamforming gain with respect to curvature mismatch, the optimization problem is further reduced to a quantization-error minimization problem, for which suboptimal curvature codewords are obtained. Numerical results demonstrate that the proposed unified codebook achieves near-optimal beamforming performance that approaches its upper bound based on perfect channel state information (CSI), while significantly reducing the required feedback overhead as compared to various benchmark schemes.

cs.IT

新论文 · v1arXiv:2611.13536

Adaptive catalyst discovery emerges from composable scientific intelligence

Wentao Li, Qilong Cai, Qi Lei, Jinxing Chen, Ruixuan Chen, Jiangjie Qiu, Botian Wang, Kai Zhao 等 24 位作者

原文摘要

Catalysis underpins chemical manufacturing, yet knowledge for catalyst design remains dispersed across experimental observations, computational data and catalysis subdisciplines. To overcome this challenge, we present Composable Catalytic Intelligence (CatAI), a physics-grounded modular AI framework that learns 1.8 million structure-property relations and organizes them into 30 physicochemical encoders. This reusable intermediate layer enables task-specific models to guide catalyst discovery for targeted reactions and objectives. Across benchmark tasks, CatAI achieves a 7.8% lower task-averaged prediction error than the next-best models. In experimental validation, CatAI identified a new confined-passable pocket catalyst applicable in industrial homogeneous polymer synthesis with 9 times the activity of the commercial benchmark. In parallel, it guided autonomous closed-loop optimization of a highly active Cu-based geminal-atom photocatalyst for C-O coupling reactions surpassing the traditional Ni-based systems. This approach connects property-level data to catalytic objectives, supporting physicochemical knowledge reuse across mechanistically distinct systems through computational screening and iterative model-experiment feedback.

cs.LG

新论文 · v1arXiv:2611.13530

UniWeaver: Harnessing Unified Multimodal Models for Interleaved Text-Image Generation

Hongxu Chen, Zixuan Zhong, Donghao Zhou, Haodong Li, Xiaomin Yu, Tianhao Li, Shiyao Yu, Zhongwei Wan 等 9 位作者

原文摘要

Unified multimodal models (UMMs) have opened up new possibilities for generating rich interleaved text-image content. However, they generally lack native support for coordinating the two modalities, and translating coarse user requests into coherent multimodal compositions also requires explicit planning. We propose UniWeaver, a structured, model-agnostic harness framework that integrates multimodal planning, generation, and visual feedback to produce coherent interleaved outputs. To train UMMs for this task, we construct UniWeaver-10K, a dataset of 10,000 tasks across 20 task families, paired with execution trajectories guided by UniWeaver. We also introduce UniWeaver-Bench, a task-oriented benchmark systematically assessing text coverage, writing quality, visual coverage, and image-text alignment. Experiments show that UniWeaver achieves state-of-the-art performance and improves interleaved text-image generation across multiple UMM backbones.

cs.CV

版本更新 · v2arXiv:2608.06931

Science Edge Evaluation: SEE the Missing Step Toward Real Scientific Discovery

Taolin Han, Yuchen Zhang, Jinghang Wang, Yun Wu, Wai Yuet Chiu, Zhaohai Li, Yifei Zhang, Jinxin Wang 等 25 位作者

原文摘要

Large language models (LLMs) are increasingly involved in scientific discovery, yet it remains unclear whether they can support complex real laboratory science. Here we introduce Science Edge Evaluation (SEE), a multimodal benchmark of expert-curated questions grounded in peer-reviewed literature and experimental practice in chemistry, biology, and materials science. Evaluation of 28 multimodal large language models (MLLMs) shows that even the best-performing model reaches only 54.9% accuracy. Moreover, general-purpose models outperform science-specialized models on average. In the visual-agent evaluation, the use of tools increases the best accuracy to 56.1%. Tool use can expand the information available to models, but more information does not necessarily lead to reliable scientific reasoning. The key challenge is whether models can manage tool-derived information within the boundaries of the original experimental evidence. Together, these findings reveal that current MLLMs still cannot reliably make justified and evidence-bounded inferences from experimental results, which is an essential capability in real scientific discovery. Bridging this gap requires MLLMs to transition from explaining established scientific concepts to deriving novel and evidence-based insights from experimental data.

cs.AI

新论文 · v1arXiv:2611.12337

From LLM Hallucinations to Inspiration in Creative Work

Xinrui Lin, Heyan Huang, Shuning Zhang, Qi Wang, Youchao Zhou, John Vines

原文摘要

Large language models (LLMs) can introduce unexpected ideas through hallucinations, yet little is known about when creative practitioners find these errors inspiring or how these judgments shape interactions. We conducted a retrospective qualitative study with 20 experienced practitioners in research, design, and social media content creation, thematically analyzing 41 hallucination cases and 20 semi-structured interviews. Our framework links inspiration judgments of hallucinations based on goal relevance, task stage, content adaptability, and type-specific factors to behaviors across not-inspired, inspired-by, and inspired-to states. We characterize downstream interaction consequences, showing how hallucination-inspired experiences vary across creative stages and reshape role-differentiated trust, and propose these consequences as a dimension of hallucination evaluation. Finally, we derive design recommendations for stage-sensitive control of divergence and adherence, user-defined constraint priorities, differentiated hallucination labels, and salvage support for preserving useful ideas while correcting errors. These contributions deepen HCI understanding of hallucinations and responsible LLM design in creative work.

cs.HC

版本更新 · v3arXiv:2606.07642

Do VLMs See What Sensors Feel? A Scalable Expert-Guided Design for Wheelchair Accessibility Assessment from Street View

Dongdong Wang, Alina Hagen, Isabelle Gatmaitan, Hao Zhou, Yiwen Dong, Shabboo Valipoor, Vivian W. H. Wong, Lingyao Li

原文摘要

Assessing built-environment interaction, such as wheelchair accessibility, is challenging because real-world mobility is shaped by context-dependent and temporary barriers that are difficult to capture at scale. This paper examines whether vision-language models (VLMs) can identify potential accessibility barriers from Google Street View (GSV) imagery. We propose an expert-guided retrieval-augmented framework that combines GSV imagery, ADA-informed guidance, and expert-derived rubrics to evaluate multiple accessibility dimensions. We collect a campus-scale dataset at the University of Florida, linking 407 unique GSV locations with GPS-derived wheelchair dwell behavior as a proxy for potential mobility friction. Results show that VLM ratings are negatively correlated with dwell time and exhibit distributional similarity, with the expert-guided configuration strengthening the correlation from $r=-0.40$ to $r=-0.54$ for the strongest model. Visual cue analysis further shows that features such as curb ramps and crosswalks are associated with higher VLM accessibility scores, while correspondence remains limited for subtle surface conditions, transient obstructions, and viewpoint-dependent barriers. Overall, our findings demonstrate the potential of expert-guided VLMs for scalable preliminary accessibility screening and prioritizing locations for further investigation.

cs.CV · cs.CY

版本更新 · v2arXiv:2505.20536

Covariate-Adjusted Deep Causal Learning for Heterogeneous Panel Data Models

Guanhao Zhou, Yuefeng Han, Xiufan Yu

原文摘要

This paper studies the task of estimating heterogeneous treatment effects in causal panel data models with covariate effects. We propose a novel Covariate-Adjusted Deep Causal Learning (CoDEAL) framework that cohesively deals with the underlying heterogeneity and nonlinearity of both panel units and covariate effects. CoDEAL integrates nonlinear covariate effect components (parameterized by a feed-forward neural network) with nonlinear factor structures (modeled by a multi-output autoencoder) to form a heterogeneous causal panel model. The nonlinear covariate component flexibly captures complex covariate influences on outcomes, and the nonlinear factor decomposition enables CoDEAL to effectively capture both cross-sectional and temporal dependencies inherent in the data panel. This latent structural information is subsequently integrated into a customized matrix completion algorithm, thereby facilitating more accurate counterfactual imputation. Moreover, the use of a multi-output autoencoder explicitly accounts for heterogeneity across units and enhances the model interpretability of the latent factors. We establish theoretical guarantees on the convergence of the estimated counterfactuals and demonstrate the compelling performance of the proposed method using extensive simulation studies and real-world data applications.

stat.ML · cs.LG · econ.EM · stat.ME

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

新论文 · v1arXiv:2611.08798

Driver Takeovers and Longitudinal Responses Analysis from Naturalistic Driving

Yuhang Wang, Hao Zhou

原文摘要

As Level 2 advanced driver-assistance systems (ADAS) become more widely used, understanding driver-system interaction is increasingly important for traffic safety. However, limited real-world data make these interactions difficult to study. We present ADAS-TO, a naturalistic dataset of 16,446 takeover clips from 364 drivers across 2,585 different drives. It combines road video, vehicle kinematics, driver inputs, and ADAS status. To analyze takeover behavior, we retained 6,206 manually reviewed takeover events during continued lane keeping or car following. We excluded events in which the driver intentionally changed lanes, turned, or made a stop beyond the ADAS's capabilities (e.g., at a red light or stop sign) shortly after takeover. Drivers began intervening before ADAS disengaged in 65.6% of takeovers involving braking or steering. When the ego vehicle was still closing on a lead vehicle at disengagement, longitudinal safety margins often narrowed further after the transfer to manual control. Among 2,031 such events, 78.5% had a lower minimum time-to-collision (TTC) in the five seconds after disengagement than in the five seconds before it. For events involving braking, the mean TTC trajectory reached its minimum about 1.2 s after disengagement. We model the subsequent braking response using a Gazis-Herman-Rothery (GHR) car-following law. Its median five-second spacing root-mean-square error is 1.34 m with observed lead motion and 1.84 m with predicted lead motion. The fitted model expresses braking as a response to looming, with stronger responses at higher speeds and shorter gaps. Applied before takeover, it shows that greater looming than predicted by the human-response reference is associated with disengagement. These findings support continued assessment of longitudinal safety after ADAS disengagement, while the driver's braking response develops.

cs.HC

版本更新 · v4arXiv:2607.04364

RL Forgets! Towards Continual Policy Optimization

Mao-Lin Luo, Zhe-Xu Wang, Zi-Hao Zhou, Bo Ye, Jian Zhao, Min-Ling Zhang, Tong Wei

原文摘要

Continual post-training is becoming a central paradigm for adapting vision-language models to evolving tasks. Recent studies report that reinforcement learning is less prone to forgetting than supervised fine-tuning, motivating the view that RL is inherently resistant to forgetting. However, this view remains insufficiently validated, as existing evidence is largely drawn from outdated or homogeneous benchmarks. We revisit this assumption by introducing MRCL, a Multimodal Reasoning Continual Learning benchmark built from recent and diverse multimodal reasoning tasks. Experiments on MRCL show that standard reinforcement learning still suffers from catastrophic forgetting during continual post-training. We trace the failure to an objective mismatch. The KL regularization used in common policy optimization methods is evaluated on current-task data, whereas forgetting is caused by behavioral drift on prior-task distributions. To address this problem, we propose Continual Policy Optimization (CPO), a replay-free method grounded in a prior-task behavioral KL objective. CPO derives a local Fisher surrogate from the historical KL objective and uses parameter movement as a gradient-free proxy for Fisher sensitivity, enabling sparse regularization with negligible additional overhead. Experiments on three model scales and comparisons with multiple RL baselines show that CPO consistently reduces forgetting while maintaining effective adaptation and preserving broader pretrained capabilities. The implementation code is available at https://github.com/MaolinLuo/CPO.

cs.LG

版本更新 · v3arXiv:2610.13373

PartiGen: Part-Aware Representations for Language-Conditioned Humanoid Motion Generation

Chuxuan Huang, Zhanxiang Cao, Tianyue Zhan, Haoyang Li, Yang Zhang, Liyun Yan, Chenlin Ming, Keqi Zhu 等 17 位作者

原文摘要

Translating language into humanoid motion requires coordinating body parts, determining motion duration, and producing references suitable for robot execution. We introduce PartiGen, a part-aware latent diffusion framework that incorporates anatomical structure into a shared whole-body motion representation. Part-specific attention processes anatomically masked frame features, and its outputs are fused to combine local limb information with whole-body context. Conditioned on text and motion history, the model generates motion primitives autoregressively. Forward-kinematics supervision encourages kinematic consistency, while a learned end-of-sequence predictor selects a frame-level endpoint after generation. On HumanML3D retargeted to the Unitree G1, PartiGen achieves a segment-level FID of 3.165, a 16.8% reduction over TextOp, and improves R@1 by 1.4 percentage points. In the duration study with 16-frame primitives, endpoint prediction reduces mean absolute duration error from 12.471 to 3.080 frames compared with a fixed-length cutoff. We further evaluate robot execution using a pretrained, frozen GRIT tracker: 409 of 500 generated references (81.8%) pass the posture-based stability screen in MuJoCo. Following simulation screening and manual selection, 26 of 27 attempted motions are judged successful on the real G1.

cs.RO

新论文 · v1arXiv:2611.07512

RLGPA: A Reinforcement Learning-Guided Granularity Planning Attack for Decision-Based Sparse Adversarial Examples

Chao Zhou, Shenghua He, Jiaxin Mo, Qiangguo Yu, Fengchuang Xing

原文摘要

Decision-based sparse attacks must reduce perturbation support using only the victim's predicted label. The best restoration strategy varies as support contracts: coarse removal works early, while tail states need finer, history-aware tests. We propose RLGPA, an online reinforcement learning method that schedules support-reduction executors and their granularity under a hard query budget. A masked Dueling Double DQN selects among seven stable policy--scale actions; each action produces support-relative restoration groups that are rebuilt after every macro decision. A feasibility-preserving executor commits only adversarial restorations and feeds support gain and query cost back to the planner. Under the matched top-1-label oracle, RLGPA reaches 61\% targeted ASR at sparsity 0.01 on CIFAR-10 (vs. 25\% SparseEvo, 0\% Pointwise), and 75.5\%/73.0\% on ResNet50/ViT at sparsity 0.005 (vs. 29.0\%/15.5\%). A fixed-probe test reduces median \(L_0\) from 165 to 23 after 40 images without any update. State-blind and state-shuffled controls degrade significantly, confirming that the learned policy uses attack state; the main gains come from state-conditioned executor scheduling and dynamic repartition. The source code is publicly available at https://github.com/Acui001/RLGPA.git.

cs.LG · cs.CV

新论文 · v1arXiv:2611.06500

Tools Need Not Speak in Text: Latent Context Compression for Agents

Yuetong Liu, Zhehao Zhou, Yitong Zhang, Haorui Chen, Jia Li

原文摘要

Large language model (LLM) agents typically append raw tool outputs to their context. Over multi-step interactions, long and noisy observations incur substantial context overhead and dilute the agent's attention to task-relevant information. Existing token pruning and summarization methods remain constrained by discrete text representations, limiting the achievable compression ratios. In this work, we challenge the prevailing assumption that agents must consume tool observations as explicit text tokens. To this end, we propose Coca-Cola, a continuous latent context compression model for LLM agents. Coca-Cola compresses tool observations into latent tokens and embeds them into the input embedding space of the agent. We further introduce Action-Preserving Training, which aligns the agent's next-action distributions under full and compressed observations. This trains the compression model to learn action-sufficient latent tokens that retain decision-critical information. Experiments with web-search agents on four QA benchmarks and two model families show that Coca-Cola reduces the agent's token consumption by 70.01%-89.24% and end-to-end runtime by 24.45%-55.97%, while consistently improving task performance. These results suggest that Coca-Cola offers a promising approach for context compression in agents. Our code is available at https://github.com/THU-Agent/Coca-cola.

cs.AI

新论文 · v1arXiv:2611.06108

Learning When to Think Aloud in Latent Reasoning

Zhehao Zhou, Tongrui Su, Shengyu Zhu, Da Li, Zeyu Liu, Jun Zhu, Xueqi Cheng

原文摘要

Latent Chain-of-Thought (CoT) reasoning improves efficiency by shifting intermediate computation into continuous hidden states. However, fully latent methods often struggle on precision-critical tasks such as mathematical reasoning, while existing hybrid approaches retain substantial token-generation overhead. We introduce VITAL, an importance-guided hybrid reasoning framework that selectively verbalizes informative tokens as reasoning anchors while keeping most computation latent. A lightweight gating head dynamically selects between explicit token generation and direct hidden-state feedback. VITAL constructs hybrid trajectories from explicit CoT using token- importance estimation and trains the model through curriculum-based supervised training, followed by reinforcement learning with a reward that balances correctness and conciseness. Experiments show that VITAL consistently out- performs existing fully latent reasoning methods, achieving relative average accuracy gains of 9.6% on GPT-2 and 5.1% on Llama-3.2-1B at comparable reasoning lengths. Compared with hybrid baselines, VITAL achieves higher reasoning accuracy with substantially shorter reasoning trajectories on Qwen3-1.7B.

cs.LG

新论文 · v1arXiv:2611.05807

Near-Optimal Complexity of Finding Approximate Local Minima of Nonconvex Finite Sums

Qihao Zhou

原文摘要

We study the component-oracle complexity of finding approximate local minima of nonconvex finite sums under mean-squared averaged smoothness with parameter $L$ and a $ρ$-Lipschitz average Hessian. Each query returns the value, gradient, and one Hessian-vector product of a component. We show that the complexity in the high-accuracy regime $\varepsilon\le c_0L^2/(nρ)$ is $\tildeΘ(n^{3/4}L^{1/2}ρ^{1/4}Δ\varepsilon^{-7/4})$ for a sufficiently large initial gap $Δ$. We attain the upper bound by adapting the inverse solver and eigenvector routine of FastCubic to averaged smoothness. Our lower bound assigns the bridge edges of a nested chain to random components; a replicated spectral construction gives the same bound for unrestricted randomized algorithms. Under individual smoothness, a factor of $n^{1/4}$ remains for $\varepsilon\le cL^2/(n^2ρ)$, up to logarithmic factors. In the complementary low-accuracy regime, we propose PathVR, which uses $\tilde O(n+\sqrt{n}LΔ\varepsilon^{-2})$ queries and matches a lower bound from dense weak hiding.

math.OC · cs.DS

新论文 · v1arXiv:2611.04455

SourceFlow: Collaborative Source Coupling for Flow-Based Recommendation

Chenghao Wu, Yongqi Zhou, Jin Chen, Yifeng Zhou, Jinchang Zhu, Junwei Pan, Chao Zhou, Zhixiang Feng 等 10 位作者

原文摘要

Diffusion-based recommenders learn user preferences by denoising interaction histories, but the added noise can distort the original preference signals. Flow-based collaborative filtering (CF) instead learns a discrete path from a sampled source to the user's observed training interactions (the target history), enabling inference in a few steps. Existing flow-based CF methods sample sources using global item frequencies to reflect the sparsity and popularity of observed interactions. Each source is sampled independently of its target history, leaving the predictor without user-specific source cues for learning to reconstruct that history. We propose SourceFlow, which brings collaborative structure into the source distribution itself rather than adding further conditioning to the predictor. Like inference from observed histories, training uses collaborative evidence to predict missing interactions. Specifically, Neighborhood Coupling constructs displaced binary sources by replacing historical items with unobserved collaborative alternatives. Collaborative Consensus further refines replacement probabilities using evidence from other interactions of users who share the observed item. Stretched Restoration retains these replacements at late flow times during training, providing more opportunities to recover the original interactions. Experiments on five recommendation datasets show consistent improvements over competitive baselines, including a mean relative Recall@10 gain of 15.7% over the strongest flow-based baseline. Controlled experiments confirm that these gains depend on correctly pairing collaborative sources with their target histories, as reassigning the same source vectors across users reverses the gains. Code will be publicly released upon acceptance.

cs.IR

新论文 · v1arXiv:2611.04217

LENS: Reliability-Aware Stock Prediction via LLM-Extracted Priors and News-Driven Semantic Graphs

Hao Zhou, Tiejun Ma, Luis Felipe Costa Sperb

原文摘要

Predicting stock returns requires modeling persistent company relations and time-varying market signals. Graph Neural Network (GNN) approaches combine static priors with dynamic relational graphs, but treat every extracted edge as a trustworthy binary fact, ignoring heterogeneous reliability across relational sources. We propose LENS (LLM-Extracted priors and News-driven Semantics), a static--dynamic graph framework for stock return prediction and ranking that models relational reliability as a first-class signal across the pipeline. On the static side, we extract a multi-relational company graph from a Large Language Model and aggregate it over multiple runs with confidence weighting to downweight low-consistency edges. On the dynamic side, we build a news-driven semantic graph with exponential-decay temporal aggregation to capture changing market context under uneven coverage. A context-dependent gated fusion module rebalances the two graphs at the per-stock, per-day level. On S&P 500, LENS improves AR@5 by 16.4% and SR@5 by 22.6% over the strongest baseline, and on NASDAQ 100 it achieves comparable improvements (15.5% and 20.9% respectively). Ablations isolate each component's contribution, and a human-validation study of sampled relations supports that the aggregation is grounded, providing evidence that reliability-aware LLM relations and news-based semantic graphs carry complementary information for graph-based financial prediction.

cs.LG

新论文 · v1arXiv:2611.04147

AdSteer: Native Advertising in Large Language Model Generation

Shuhang Lin, Chuhao Zhou, Zhenyu Wang, Xiao Lin, Changsheng Wang, Saibo Geng, Dimitris N. Metaxas

原文摘要

Large language model (LLM) services face rapidly rising serving costs. To sustain free or affordable access for a broad user base, alternative monetization mechanisms are needed. Native advertising offers a promising approach, as it creates economic value by aligning user intent with merchant offerings. Yet how to integrate sponsored content naturally into LLM responses remains largely underexplored. Existing approaches primarily rely on prompt-level injection, multi-pass rewriting, or fine-tuning, which can compromise response quality or introduce additional computational costs. We propose AdSteer, a lightweight decoding-time advertising framework that adaptively adjusts token probabilities to integrate contextually appropriate advertisement into responses. AdSteer calibrates the strength and duration of advertising influence, making sponsored content a natural part of the response. Experiments on GEM-Bench across three application scenarios show that AdSteer achieves an average improvement of 14.1% in overall score over the strongest baselines and 22.5% fewer total tokens on average than rewrite-based methods. These results demonstrate that AdSteer provides an effective and practical solution for native advertising in LLMs.

cs.CL

新论文 · v1arXiv:2611.02810

TRIO: Task Refinement with Individual Optimization for Retrieval-Augmented Generation

Yingtao Ren, Xiao Luo, Yiwei Fu, Jinzhao Zhou, Yu-Cheng Chang, Chin-Teng Lin

原文摘要

This paper studies retrieval-augmented generation (RAG), which leverages external knowledge to improve the performance of language models. Despite the remarkable progress, current RAG approaches are still far from satisfactory due to inadequate retrieval and potential hallucinations. Towards this end, we propose a novel approach named Task Refinement with Individual Optimization (TRIO) for RAG. The core idea of our TRIO is to equip three well-designed agents with an iterative refinement paradigm by aligning their individual optimization objectives. Specifically, we first expand ambiguous queries with a query extension agent and quantify the reward based on the improved answer quality, which can be utilized to refine our agent for higher expansion efficiency. To enhance the retrieval quality, we include a unanimity voting to annotate the expanded query as insufficient or sufficient, and their generative outcomes are utilized as ground truth to optimize the judge agent. To further improve evidence utilization and answer accuracy, an answer agent is optimized with dynamic matching-based rewards with curriculum learning for final outputs. Extensive experiments across multiple benchmark datasets validate the effectiveness of the proposed TRIO in comparison with state-of-the-art approaches. Our code is available at https://github.com/yingtaoren/TRIO.

cs.CL