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

+197新增论文
+151其中 AI 相关
+16已有论文修订
+95新增 AI 导读

arXiv 最近完成扫描:2026-11-21 12:19 · 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 2026-11-20 23:48 — 2026-11-21 23:48(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:2026-11-21 12:19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 80 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-21 12:17(北京时间)
新论文 · v1arXiv:2611.26103

UniVEP: Unifying Velocity and Endpoint Prediction for Robot Manipulation

Zhengtu Liang, Qiwei Liang, Tao Lin, Shihang Weng, Boyang Cai, Xiangyu Chen, Yikeng Chen, Jiaming Liang 等 11 位作者

原文摘要

Flow-matching robot policies usually use one prediction target throughout action generation, even though recovering actions from noise and polishing nearly clean actions bring different challenges. We systematically compare velocity prediction (V), endpoint prediction (X), and velocity-weighted endpoint prediction (X--V) across multiple robot policies, benchmarks, and inference budgets. On StarVLA and LiLa-WAM, X--V works best for few-step generation, while V gains more from iterative refinement. We further uncover their complementary strengths across noise levels: clean actions have concentrated covariance spectra, endpoint predictions stay more stable under high noise, and velocity predictions offer more accurate corrections near clean actions. Inspired by these findings, we introduce UniVEP, which learns both prediction targets together with consistency supervision and switches from endpoint recovery to velocity refinement as noise drops. Each step only needs one network run, and joint training also boosts single-step endpoint generation. Tests on simulated and real-world manipulation show better success rates and efficiency. On RoboTwin, UniVEP hits 61.36% success with one StarVLA run, beating the best single-target baseline at sixteen runs (59.96%). With LiLa-WAM, two runs outperform the best sixteen-step single-target baseline and cut inference latency by 77.1%.

cs.RO · cs.CV

新论文 · v1arXiv:2611.25412

ChainAgent: Automated Chainable Vulnerability Discovery in PHP Web Applications

Xinyi Wang, Yeting Li, Shizhe Cui, Jiaming Guo, Qin Mai, Yecheng Sun, Hengyu Yang, Yujie Sun 等 12 位作者

原文摘要

High-impact attacks on PHP web applications often chain limited-capability vulnerabilities with other flaws or intended behaviors. Discovering these chains requires identifying flaws and the dependencies enabling capability composition. Existing vulnerability discovery techniques analyze flaws in isolation, while attack planning assumes known components. This separation makes it difficult to discover previously unknown components whose security relevance becomes apparent only through their potential roles in an exploit chain. We present ChainAgent, a goal-directed LLM-agent framework that jointly discovers exploit-chain components and their capability dependencies in source code. Guided by an empirical study of 386 real-world web exploit chains, ChainAgent represents vulnerabilities and functional gadgets--intended program behaviors that can be repurposed in attacks--through preconditions and capabilities over security-relevant objects. Instead of discovering vulnerabilities first and constructing attack paths afterward, ChainAgent uses an evolving exploit graph to guide source-code inspection. It searches backward from unmet preconditions for capability producers and forward from discovered capabilities for functional gadgets that consume or amplify them. Object-centered chaining knowledge from our empirical study directs searches toward promising vulnerability classes, functional operations, and object accesses. We evaluate ChainAgent against Codex, a general-purpose coding agent, on 15 PHP applications across three shared LLM backends. ChainAgent achieves 42.02%--44.63% recall for goal-reaching components and recovers up to 4.4 times as many correct goal-reaching dependency edges as Codex. An additional evaluation of 30 real-world PHP applications identifies 20 vulnerabilities and 13 exploit chains, nine of which achieve remote code execution (RCE).

cs.CR · cs.AI

版本更新 · v2arXiv:2601.21922

Zero-Shot Video Restoration and Enhancement with Assistance of Video Diffusion Models

Cong Cao, Huanjing Yue, Shangbin Xie, Xin Liu, Jingyu Yang

原文摘要

Although diffusion-based zero-shot image restoration and enhancement methods have achieved great success, applying them to video restoration or enhancement will lead to severe temporal flickering. In this paper, we propose to systematically utilize both homologous and heterogeneous video diffusion models to assist the image-based method in maintaining more temporal consistency for zero-shot video restoration and enhancement. We propose homologous latents fusion, heterogenous latents fusion, and a CoQ fusion ratio strategy to utilize both homologous and heterogenous text-to-video diffusion models to complement the image method. Moreover, we propose temporal-strengthening post-processing to utilize the image-to-video diffusion model to further improve temporal consistency. Our method is training-free and can be applied to any diffusion-based image restoration and enhancement methods. Experimental results demonstrate the superiority of the proposed method.

cs.CV

新论文 · v1arXiv:2611.24877

仅通过查询用大语言模型审计黑盒临床预测模型:一项植入缺陷的双盲测试

Auditing black-box clinical prediction models with a large language model through queries alone: a blinded test with planted flaws

Zhiyu Liu, Xinyu Yang

AI 速读 基于摘要

在仅能查询模型预测值的条件下,GPT-6 Astra 能较忠实地描述黑盒临床预测模型并发现大多数植入缺陷,但其报告的问题和发现需进一步核查。

cs.LG · cs.AI

查看原文摘要

Large language models (LLMs) are used to explain clinical prediction models, on the promise that they can say what a model computes, find its faults and even reveal new knowledge in it. We tested the three promises where the answers could be checked. From the International Stroke Trial we trained four kinds of model (logistic regression, explainable boosting machine, gradient-boosted trees, neural network) for two outcomes on patients randomised earlier, planted one flaw in each of 24 copies (an under-predicted subgroup, a reversed risk factor or an implausible step) and mixed them with the 8 clean models. GPT-6 Astra audited each model three times, blind, through a tool that only returned the model's predictions; the judging rules were committed before any run and applied by program. Its surrogate models, with a median of 128 terms, reproduced the audited models' log-odds with a mean $R^2$ of 0.976 (0.959 for an additive surrogate of 42 terms fitted by an analyst). It found the planted flaw in 69 of 72 runs (96%; 95% CI 80% to 99%); a script written for the purpose found all 24. It also reported many more problems: 60% of 1,089 checkable reports failed the pre-specified check against the model's average behaviour; post hoc, most of these were real but small steps, and 15% of the checkable reports were not found in the model. Of 601 unexpected relationships it read out of the clean models, 11% held in patients randomised later (random pairs 6%; a regression scan's shorter list of its strongest candidates, 28%); after a check on the training data, 33% against 30%. With query access alone, an LLM can describe a black-box model faithfully and find nearly every planted flaw, as a purpose-written script also did; its reports of problems must be checked on the model and its discoveries on data.

版本更新 · v2arXiv:2611.22815

Visual Harness Scales General VLMs to Medical Images

Shaowen Wan, Hanqi Jiang, Zihao Wu, Junhao Chen, Weihang You, Ruiyu Yan, Bowen Chen, Tianming Liu 等 9 位作者

原文摘要

We show that an appropriate visual harness can substantially improve the performance of general vision-language models (VLMs) across diverse medical imaging tasks. We introduce VERA, a medical visual harness that equips general VLMs with interactive visual tools and systematic diagnostic evidence management. With VERA, general VLMs interactively explore medical images and progressively acquire diagnostic evidence, which is preserved in a lossless memory for subsequent retrieval and use. After submitting an initial answer, the VLM receives an assessment of potential omissions and the reliability of identified findings. This assessment guides further image inspection and measurement, followed by answer revision in an iterative agentic loop until sufficient evidence is obtained. Across 11 tasks and four imaging modalities, VERA improves performance on all tasks with Qwen3.8-27B, with notable gains in spleen measurement (63.3% to 98.3%), renal search (57.5% to 71.2%), and pulmonary nodule detection (0.0% to 28.2%). High-capability API-based VLMs achieve even higher performance with VERA. For example, GPT-6.1 Sol improves pulmonary nodule detection from 10.8% to 69.2% with VERA, demonstrating the complementary benefits of stronger model capabilities and an effective medical visual harness. Our results highlight the potential of visual harnesses as a new paradigm for scaling general VLMs to medical imaging tasks.

cs.CV

新论文 · v1arXiv:2611.23419

LIC-Audit: How Comparable Are Reported Gains in Learned Image Compression?

Haisheng Fu, Jie Liang, Runyu Yang, Feng Ding, Xin Dong, Zixiao Jin, Jingning Han

原文摘要

Learned image compression (LIC) papers often report BD-rate improvements of only a few percent. They are measured against VTM reference software whose version keeps changing: the claims we audit name 7 versions, 5 in 2025 papers alone. But how comparable are these numbers across papers, and what evidence should future papers give for such small gains? We introduce LIC-Audit, an analysis of 353 released rate-distortion curves from 36 repositories, and a controlled re-evaluation of eight public codec releases with 28,193 encode-decode records. We identify three problems. First, different VTM reference runs change BD-rates by up to 3.56 percentage points, and on CLIC Pro published numbers order 10 of 55 method pairs differently from a common computation; comparing codecs directly over a fixed quality range removes this dependence. Second, releases use different and mostly undocumented conventions for counting bits, computing PSNR, and padding images. Under consistent measurement, the GLIC method's 1.00% lead over the HPCM method on Tecnick becomes a 1.43% deficit, changing only the padding reverses the comparison of HPCM and CMIC, and most gaps narrow when MS-SSIM replaces PSNR. Third, average curves hide how much results vary from image to image, so whether a small gain is statistically significant depends on the assumed variation. An optimistic assumption calls 12.0% of comparisons between equally good codecs significant on test sets as small as Kodak, instead of 5%; a cautious one leaves 18 of 45 differences between recent codecs undecided, yet per-image results show 12 of them to be significant. Beyond auditing past results, LIC-Audit provides a versioned evaluation protocol, a public leaderboard website with a scoring tool, source-linked benchmark data, per-image measurements, and reporting guidelines, to help future LIC papers make comparable and verifiable claims of progress.

eess.IV · cs.CV · stat.AP

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

版本更新 · v2arXiv:2605.23241

RelPrism: Multi-Faceted Self-Supervised Learning on Relational Databases

Jinyu Yang, Cheng Yang, Junze Chen, Zedi Liu, Muhan Zhang, Hanyang Peng, Chuan Shi

原文摘要

Relational databases (RDBs) remain the backbone of modern data systems and support a broad spectrum of predictive tasks that require multi-faceted information from different perspectives and granularities. For example, user churn prediction is often formulated as a binary classification task that relies more on user interaction patterns reflecting activity levels, whereas consumption value estimation is a fine-grained regression task that may require composite evidence from both user attributes and user--item interaction behaviors. Therefore, a central challenge is to learn representations with comprehensive coverage of the information underlying RDB tasks. A natural solution is to leverage self-supervised learning (SSL) for pre-training. However, existing SSL methods typically derive supervision from a single facet, such as node-level intrinsic attributes or subgraph-level relational structures. Consequently, their pre-training objectives provide limited support for adaptation. To this end, we propose RelPrism, a multi-faceted self-supervised learning framework for RDBs. Concretely, RelPrism first constructs intrinsic, relational, and hybrid attributes from distinct perspectives. It then applies multi-granularity clustering to each attribute perspective to form corresponding pseudo-task pools. Pre-training over these task pools exposes representations to comprehensive attribute perspectives and granularity levels, providing a stronger basis for downstream adaptation. Extensive experiments on 14 tasks across 5 real-world datasets show that RelPrism improves ROC-AUC by 4.15% on classification tasks and reduces MAE by 10.75% on regression tasks over state-of-the-art baselines. Our code is available at https://github.com/BUPT-GAMMA/RelPrism.

cs.LG

版本更新 · v2arXiv:2611.18822

LongCat-Video-Avatar 1.6 Technical Report

Meituan LongCat Team, Xunliang Cai, Yiqi Chen, Feng Gao, Xiaoyu Kong, Le Li, Hongyu Liu, Xiaoming Wei 等 11 位作者

原文摘要

Recent advances in audio-driven avatar video generation have enabled increasingly realistic synthesis, yet achieving precise lip-audio synchronization, natural, human-like motion, and visual consistency over long sequences remains challenging. We present LongCat-Video-Avatar 1.6, which builds on LongCat-Video-Avatar 1.5 to improve expressive naturalness and reduce error accumulation during extended generation, e.g., exaggerated lip movements and overly red, temporally unstable lip coloration, enhance the naturalness of facial expressions and coordinated head and body movements. These improvements are driven by a refined post-training pipeline that integrates reinforcement learning, improved classifier-free guidance strategies for DMD-based few-step distillation, long-video rollouts, and on-policy distillation. Together, these refinements improve expressive realism and enable the generation of videos exceeding 10 minutes while maintaining visual quality and temporal consistency. Arena evaluations show that LongCat-Video-Avatar 1.6 outperforms its predecessor and competing commercial audio-driven avatar models, demonstrating the effectiveness of the improved post-training pipeline.

cs.CV

新论文 · v1arXiv:2611.21706

Video recordings and play behaviour annotations of group-housed dairy calves on two Dutch farms

Haiyu Yang, Heidi Lesscher, Enhong Liu, Miel Hostens

原文摘要

Play is used as an indicator of positive welfare in dairy calves, but openly available video of group-housed calves with individual behaviour annotations is scarce. We describe video from four camera deployments of about one week each in group pens of dairy calves on two farms in the Netherlands: a research and teaching dairy farm (2024 and 2025) and a commercial dairy farm (2024). The recordings comprise 1,173 video files spanning 651 h. For eight observation days, trained observers coded calf behaviour continuously in Noldus The Observer XT with an 18-item ethogram of play and other behaviours, covering 104 h of video, 90 h of which have every calf in the pen coded. The release also contains 1.1 million decoded frames from seven annotated sessions, a per-frame timestamp read by optical character recognition from the camera clock burned into each frame, per-calf segmentation tracks and per-calf frame-level play labels. The data support studies of calf behaviour and welfare and the development and evaluation of automated behaviour recognition.

cs.CV · cs.LG

版本更新 · v3arXiv:2607.11505

Proxy OPD: On-Policy Distillation with Transferable Relative Proxy Update for Large Language Models

Daocheng Fu, Rong Wu, Yu Yang, Jianbiao Mei, Licheng Wen, Xuemeng Yang, Yong Liu, Botian Shi 等 10 位作者

原文摘要

Reward-based reinforcement learning (RL) improves large language models but incurs substantial costs when repeated across targets. On-policy distillation (OPD) reuses experts by matching their distributions on target-generated trajectories, yet differing base policies can confound reward-induced updates with pre-existing policy differences, potentially distorting transferred update directions. We propose Proxy OPD (P-OPD), a post-training method that transfers reward-induced relative policy updates using the target's frozen base policy as a reference. A proxy undergoes reward-guided exploration, yielding token-level log-probability changes between its initial and optimized policies. These signals guide learning on target-generated trajectories, with calibration controlling signal absorption, enabling reuse of reward-induced improvements across targets. Experiments on Qwen3-family targets in mathematical reasoning, code generation, and instruction following show that P-OPD improves targets and outperforms conventional OPD in most settings. For 1.7B-to-8B transfer, average Math Mean@16 and Code Mean@8 scores exceed OPD by 8.3 and 3.4 points, respectively. Mechanism analyses show more faithful reward-induced supervision and controllable adaptation. Cross-scale and cross-generation experiments confirm signal transferability and reusability, while multi-domain distillation reveals synergistic gains and cross-domain interference. In the measured 4B-to-8B setting, target adaptation after proxy exploration takes approximately 15\% of direct target RL time; repeated signal reuse amortizes the one-time exploration cost across compatible models. These findings support relative policy updates as effective, transferable, and composable supervision for an ``explore once, transfer multiple times'' post-training paradigm.

cs.LG · cs.AI

版本更新 · v3arXiv:2510.23587

A Survey of Data Agents: Emerging Paradigm or Overstated Hype?

Yizhang Zhu, Liangwei Wang, Chenyu Yang, Xiaotian Lin, Boyan Li, Wei Zhou, Xinyu Liu, Zhangyang Peng 等 25 位作者

原文摘要

The rapid advancement of large language models (LLMs) has spurred the emergence of data agents, autonomous systems designed to orchestrate Data + AI ecosystems for tackling complex data-related tasks. However, the term "data agent" currently suffers from terminological ambiguity and inconsistent adoption, conflating simple query responders with sophisticated autonomous architectures. This terminological ambiguity fosters mismatched user expectations, accountability challenges, and barriers to industry growth. Inspired by the SAE J3016 standard for driving automation, this survey introduces the first systematic hierarchical taxonomy for data agents, comprising six levels that delineate and trace progressive shifts in autonomy, from manual operations (L0) to a vision of generative, fully autonomous data agents (L5), thereby clarifying capability boundaries and responsibility allocation. Through this lens, we offer a structured review of existing research arranged by increasing autonomy, encompassing specialized data agents for data management, preparation, and analysis, alongside emerging efforts toward versatile, comprehensive systems with enhanced autonomy. We further analyze critical evolutionary leaps and technical gaps for advancing data agents, especially the ongoing L2-to-L3 transition, where data agents evolve from procedural execution to autonomous orchestration. Finally, we conclude with a forward-looking roadmap, envisioning proactive, generative data agents. A curated companion repository is available at https://github.com/HKUSTDial/awesome-data-agents.

cs.DB · cs.AI

新论文 · v1arXiv:2611.20703

Efficient Multi-View Generation with Iterative Global-Local Proxy Attention

Wei Tan, Kunming Luo, Hongyu Yan, Yu Zhang, Zihao Zhang, Xiatian Zhu, Lei Xie

原文摘要

Generating consistent multi-view RGB images and normal maps from a single input image provides complementary appearance and geometric cues for 3D reconstruction. However, maintaining cross-view consistency requires information exchange across viewpoints, and dense cross-view attention becomes computationally expensive as the number of views and spatial resolution increase. In this paper, we propose Global-Local Proxy Attention (GLPA) to reduce cross-view communication costs while preserving fine-grained within-view processing. Specifically, GLPA retains full-resolution interactions within each view and uses compact global proxies for cross-view communication. To further leverage the exchanged information, GLPA incorporates iterative proxy refinement, which rebuilds the proxies from updated features and reuses the same attention parameters for subsequent interactions within a single denoising step. We evaluate GLPA on two structurally different diffusion backbones, FLUX and Stable Diffusion. Experiments on FLUX show that GLPA achieves a $2.65\times$ speedup in attention computation per denoising step over dense attention, while improving reconstruction IoU from 0.6849 to 0.7019 and reducing NVS LPIPS from 0.086 to 0.076. Results on Stable Diffusion further demonstrate the effectiveness of GLPA, with a $1.80\times$ attention speedup and improvements across all five quality metrics.

cs.CV

新论文 · v1arXiv:2611.19765

M-CROSS: A Multisensor Simulation Dataset for SLAM across Water--Land Transitions

Yan Dong, Tianyi Wu, Junyu Yang, Shaoqiang Qiu, Zefeng Yan, Tao Zhang, Bin Han

原文摘要

Water--land cross-domain robots require continuous localization across land, transition and underwater phases, where sensor characteristics and availability change abruptly. Existing datasets and conventional metrics are not designed to capture transition-induced degradation and failures. We present \textbf{M-CROSS}, to the best of our knowledge, the first multisensor simulation dataset and benchmark for SLAM across continuous water--land transitions. It provides synchronized LiDAR, sonar, stereo camera, IMU, DVL, and depth measurements; 6DoF pose ground truth; sensor-wise medium-state annotations; and medium-dependent sensor degradation models. We establish a transition-aware protocol comprising the Trajectory Completion Rate (TCR), Piecewise Absolute Pose Error (PW-APE), Transition End Error (TEE), and Transition Survival Period (TSP), which measure trajectory completion, single-domain accuracy, transition-induced error, and localization survival under prolonged partial immersion, respectively. Experiments with 6 representative SLAM systems show that existing methods fail to maintain both localization accuracy and trajectory continuity across the full set of water--land transitions, exhibiting transition-induced drift, trajectory discontinuities, and tracking failures. M-CROSS is publicly available https://anonymous.4open.science/r/MCross-Dataset

cs.RO

新论文 · v1arXiv:2611.19593

Learning Spatially Aware Audio-Visual Features from Videos with Mono Audio

Mengyu Yang, You Zhang, Vishnu Raj, Olha Townsend, James Hays, Andrea Fanelli, Gautam Bhattacharya

原文摘要

Comprehensive audio-visual perception requires both semantic and spatial reasoning. Existing spatial models suffer from poor generalization due to data scarcity, while semantic-only models fail to capture spatial characteristics completely. We introduce a model capable of jointly reasoning over binaural audio and vision on semantic and spatial tasks with improved generalization. To overcome the shortage in real-world data, we develop an automatic pipeline that localizes the sound source in a video, estimates its relative 3D trajectory, and renders binaural audio. We then use this to spatialize VGGSound, allowing us to train at a much larger scale. We demonstrate improved performance and generalization on spatial reasoning tasks while still remaining competitive on semantic tasks compared to semantic-only models.

cs.CV

版本更新 · v3arXiv:2611.13223

Deletion Sensitivity Is a Property of the Model: A Three-Condition Measurement over 72 Valid Experimental Cells

Yiran Li, Hanzhang Jia, Liheng Zeng, Zhiyu Yang, Yi Gao

原文摘要

Reasoning models write a trace at every turn of a multi-turn tool session, and later turns read it. Upstream providers hold different retention constraints, so a request forwarded across issuers arrives with its history deleted, and its task cost remains unmeasured. This paper reports a direct, blind, multi-seed measurement of full history deletion in multi-turn tool calling, through three rendering conditions, a calibrated set of 72 valid experimental cells, a multi-seed protocol, and the official checker. The same deletion separates the models by direction and by magnitude, one class losing tens of points, another gaining, and a third unchanged, with the endpoint ordering reproduced across seeds and task subsets modulating the magnitude and, near zero, the sign. A re-dosed model preserves its success across the full deletion range, so the reading belongs to the model rather than the dose. Deletion sensitivity is a model-level property under an operational definition, measured under a fixed task family, scorer, and protocol, and a retrained model is a new model that a two-cell screen, one retention run and one deletion run, re-reads for the cost of two runs. Deletion sensitivity is thus a measurable property of the model, and the reading must enter routing as prior information rather than persist as an invisible default cost.

cs.CL · cs.AI · cs.SE

新论文 · v1arXiv:2611.16419

I See What You Want: Decoding Hierarchical Operator Intent from Visual Teleoperation History

Xiangyi Jia, Kaixian Qu, Shengzhi Wang, Chenyu Yang, Robert Katzschmann, Marco Hutter

原文摘要

Vision-language models (VLMs) have become a powerful foundation for robotic scene understanding, task planning, and language-conditioned control. A natural question follows: can these models also decode what a human operator intends while teleoperating a robot, without any explicit instruction? We formulate this as hierarchical intent prediction, jointly inferring the ongoing atomic action and the broader mission it serves from a short visual teleoperation history. To study this, we introduce VI AMO (Vision Intention Action and Mission Ongoing), a dataset of 6,600 episodes from eleven robot sources with 13,653 temporally aligned action annotations and 9,702 mission annotations. Large proprietary models struggle with this problem: on held-out episodes, GPT-4o reaches Sentence-BERT similarities of only 0.563 and 0.470 for action and mission, and GPT-5.6 Luna achieves only 0.581 and 0.554. Fine-tuning a VLM on VI AMO yields our Vision-Intention Model (VIM), which raises these scores to 0.825 and 0.821 and still reaches 0.726 and 0.717 on the 35.4% of test actions with both labels absent from training. Finally, as a downstream application, VIM's predicted mission enables a vision-language-action (VLA) policy to take over from the operator mid-task in a real-world environment unseen during VIM fine-tuning, reducing human teleoperation time by 34.6% relative to GPT-4o and 39.8% relative to GPT-5.6 Luna, while cutting intent-prediction latency by roughly 70% on average.

cs.RO · cs.CV

新论文 · v1arXiv:2611.14908

Hy ASR 3.0 Technical Report

Aoxiong Yin, Auden Li, Chao Huang, Chuanyang Hu, Eitan Wang, Ethan Zou, Fangming Feng, Guangyu Chen 等 63 位作者

原文摘要

We present Hy ASR 3.0, a large language model (LLM)-based automatic speech recognition (ASR) system that delivers strong recognition accuracy, supports flexible contextual conditioning, and maintains robust recognition performance across diverse speech conditions. Hy ASR 3.0 supports Mandarin Chinese, English and 13 Chinese dialect groups, including Cantonese. Among the evaluated systems, it achieves the lowest aggregate error rates on public Mandarin Chinese, English, and Cantonese benchmarks and the lowest error rates on the corresponding internal test sets, alongside first-tier dialect recognition performance. Beyond audio-only transcription, Hy ASR 3.0 supports multiple forms of external context, including hotword lists, question--answer dialogues, and summaries, enabling the use of task-relevant information during recognition. The model also leverages intra-utterance context to disambiguate homophonic and phonetically similar keywords using information from other parts of the same utterance, without requiring a separate contextual input. Evaluations demonstrate strong contextual recognition in both external-context and intra-utterance settings, as well as robust recognition of long-form speech, children's and older adults' speech, low-volume speech, and speech in noisy environments. This report describes the model architecture and training methodology and presents evaluations across recognition accuracy, context utilization, and robustness.

cs.CL · eess.AS

版本更新 · v3arXiv:2604.26963

MARS: Towards High Goodput and Low KV Thrashing in Agent Serving under GPU Memory Constraints

Yifei Wang, Tsun-yu Yang, Hancheng Ye, Yechen Xu, Cong Guo, Chiyue Wei, Qinsi Wang, Dongting Li 等 12 位作者

原文摘要

Self-hosted LLM agents offer greater control over sensitive data and model customization while avoiding per-request API fees. However, serving concurrent, multi-turn workflows within limited GPU memory makes it difficult to achieve high workflow-level goodput. In particular, as workflows accumulate context, their reusable key-value (KV) caches can easily outgrow GPU capacity, triggering repeated eviction and recovery, known as KV cache thrashing. This process consumes resources and delays workflow completion. Although existing approaches propose various methods, our motivation study shows that the evaluated baselines still incur substantial thrashing overhead or fail to address the workflow-level goodput issue. We present MARS, an agent serving system that coordinates workflow admission and in-engine scheduling to achieve high workflow-level goodput on memory-constrained devices while avoiding KV cache thrashing. Specifically, outside the engine, an admission controller selects root workflows using initial prefix footprint estimates and live KV availability, adapting admissions to memory pressure. Inside, an agent-centric scheduler prioritizes turn completion and coordinates prefill allocation with KV reclamation to reduce disruptive evictions. Across two models and three GPU configurations, MARS achieves 1.59x-7.56x mean end-to-end latency speedups over the fastest baseline. Integrated as the serving backend for OpenCode, Codex, and OpenHands, MARS further improves mean workflow completion time by 1.17x-1.87x. Our source code is publicly available at https://github.com/Afterglow231/MARS_preview .

cs.OS · cs.DC · cs.LG · cs.MA

版本更新 · v2arXiv:2611.10693

Machine Hearing: Can Audio LLMs Generalize Beyond Human Auditory Perception?

Liwei Liu, Jun Tao, Xingyuan Li, Xuenan Xu, Chen Zhang, Junyi Wang, Boya Zhang, Xiaoyu Yang 等 11 位作者

原文摘要

Multimodal LLMs have made remarkable progress in perceiving the physical world, while their perceptual scope remains largely human-centric, focusing on what humans can directly see or hear. This progress raises the prospect of perception beyond human limits, such as extending hearing to sounds that are inaudible to humans. More broadly, the physical world is full of waves, vibrations, and oscillations, only a small fraction of which are directly audible to humans. This invites the extension of multimodal LLMs toward a broader form of machine hearing, which remains largely underexplored. To investigate this direction, we introduce the Machine Hearing Benchmark (MHB), comprising 6,128 instances across 13 tasks and seven domains. MHB spans highly heterogeneous input regimes, with sampling rates from approximately $10^{-5}$ to $10^6$ Hz, sequence lengths from $10^1$ to $10^6$ samples, and both single- and multi-channel inputs. Evaluations of current open-source and proprietary Audio LLMs (ALLMs) reveal limited zero-shot transfer to machine hearing. Supervised adaptation on machine-hearing data alone does not close this gap, suggesting that the challenge extends beyond data exposure to a systematic mismatch between existing audio front ends and machine-hearing inputs. To address this mismatch, we introduce MachEar, a lightweight encoder extension that complements the pretrained Audio LLM for machine-hearing inputs. The results show that MachEar equips a pretrained Audio LLM with stronger machine-hearing capabilities while largely preserving its existing audio understanding performance.

cs.SD · cs.CL

版本更新 · v2arXiv:2511.22928

Predicting Risks Before They Happen: Vision-Language Reasoning for Autonomous Driving

Jiaxin Liu, Xiangyu Yan, Liang Peng, Lei Yang, Yuechen Luo, Lingjun Zhang, Hangjun Ye, Guang Chen 等 15 位作者

原文摘要

% Waiting until a driving hazard becomes directly visible can leave an autonomous vehicle little time to respond. Observable precursors, such as another vehicle's unexpected braking, can provide evidence of a hidden hazard and an opportunity for earlier risk mitigation. However, existing driving datasets and language reasoning formulations provide limited supervision for connecting these precursors to potential risks and appropriate responses. We introduce PotentialRiskQA, an ego-view driving dataset that marks precursor and risk appearance times and provides structured annotations linking scene evidence, potential risks, and mitigation actions. Building on this dataset, PR-Reasoner trains vision-language models to generate a precursor-centered reasoning chain through scene-level supervision and auxiliary tasks for scene understanding, precursor identification, risk inference, driving suggestions, and meta-actions. Experiments across multiple backbones show improved scene understanding, risk cognition, and action quality, with fewer unsupported risk claims on most models. Ablations show that supervising intermediate reasoning steps further reduces unsupported risk claims and improves action quality beyond scene-level training alone. On NAVSIM, the trained representations improve open-loop planning performance, demonstrating benefits beyond language-based evaluation.

cs.RO

版本更新 · v2arXiv:2605.15721

Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering

Jiachen Zhu, Zhuoying Ou, Congmin Zheng, Yuxiang Chen, Zeyu Zheng, Rong Shan, Lingyu Yang, Lionel Z. Wang 等 12 位作者

原文摘要

Large Language Models (LLMs) are highly sensitive to their input contexts, motivating the development of automated context engineering. However, existing methods predominantly treat this as a global search problem, seeking a single context strategy that maximizes average performance across a dataset. This restrictive assumption overlooks the fact that different inputs often require distinct guidance, leaving substantial instance-level performance gains untapped. In this paper, we propose a paradigm shift by formulating context engineering as a recommendation problem. We introduce \textbf{Neural Collaborative Context Engineering (NCCE)}, a framework that transitions optimization from a static global search to dynamic, instance-wise routing. NCCE first bootstraps a diverse catalog of anchor contexts and then employs a novel \textbf{Context-CF Co-Evolution} mechanism. This stage establishes a synergistic feedback loop: a lightweight Neural Collaborative Filtering (NCF) model learns instance-context preferences to guide the generation of specialized context variants, while the newly evaluated contexts continuously refine the NCF model's understanding of latent preferences. At inference time, the trained NCF model acts as a context router, dynamically assigning the most suitable context strategy to each unseen instance. Theoretical Proofs and comprehensive experiments demonstrate that by matching individual inputs with their optimal contexts, NCCE significantly improves task accuracy, highlighting the critical importance of personalization in LLM context engineering.

cs.CL

版本更新 · v3arXiv:2606.15874

LLM-as-Code: Agentic Programming for Agent Harness

Junjia Qi, Zichuan Fu, Jingtong Gao, Wenlin Zhang, Hanyu Yan, Xian Wu, Xiangyu Zhao

原文摘要

Every major LLM agent framework gives the LLM the role of orchestrator; the model decides what to do next, when to call tools, and when to stop. We argue that token explosion, control-flow hallucination, and unreliable completion are not implementation bugs but architectural consequences of assigning the deterministic work of looping, branching, and sequencing to a probabilistic system. A better prompt or a stronger model cannot guarantee the reliability of the LLM agent. We therefore propose Agentic Programming, in which the program governs all control flow, and the LLM is itself part of it, an adaptive component we call LLM-as-Code and invoke only where a task calls for reasoning or generation. Within each call the model keeps full flexibility, but it cannot alter the program's execution path. With control in the program, the LLM's context is built from the execution history's call tree and forms a directed acyclic graph (DAG). Each call's context length is then determined by its call depth rather than by accumulation over steps. A case study of computer-use agents shows that the design is practical, not just a theoretical stance, substantially improving the stability of long visual operation sequences.Code is available at https://github.com/FuzzyKuji/OpenProgram.

cs.AI · cs.SE

版本更新 · v3arXiv:2611.03412

DeliverBench: Benchmarking AI Agents on Delivering Realistic Multi-Stage Professional Projects

Yumou Liu, Mingju Chen, Zhoufutu Wen, Qianyu Yang, Zijie Wang, Sihan Chen, Yeqian Liu, Chenghao Yang 等 24 位作者

原文摘要

LLM agents are judged by what they deliver, and in professional work what gets delivered is a project, not a task. A project pays off only if the whole package holds together, and one weak part can limit the value of the rest. Yet existing benchmarks mostly test agents on one task at a time, leaving a gap between the capability we measure and the outcome that makes agents useful. To address this gap, we introduce DeliverBench, which tests whether agents can carry a project from brief to final delivery. Reconstructed from real materials with 13 domain experts, its 11 projects span settings such as financial due diligence, legal contract drafting, and drug safety reporting. They comprise 150 subtasks, with 2-15 subsequent releases of new materials and client feedback per project. Later subtasks build on the agent's own earlier deliverables, so unresolved errors can carry into downstream work. Expert rubrics assess each subtask submission and the final delivery package. Across seven model-harness systems, the best scores 65.0/100 on final delivery and passes 50.0% of subtasks at a 90-point threshold. Together, these results suggest that task-level capability does not simply compose into delivery; delivery also depends on keeping the work coherent as it evolves.

cs.AI

新论文 · v1arXiv:2611.12382

AutoVLA-D: Learn a Trajectory-Geometric Condition from Reasoning for Autonomous Driving VLA

Yuguang Yang, Zhewen Tan, Canyu Chen, Linlin Yang, Cheng Chi, Chunyang Liu, Kehua Sheng, Jinyu Yang 等 12 位作者

原文摘要

Autoregressive VLA planning usually predicts continuous trajectories as the final output, but driving instructions often describe actions rather than ego states, which weakens direct conditioning on the final continuous trajectory. We address this gap with TrajCond, which introduces a discrete trajectory-geometric condition for VLA planning. Specifically, we represent TrajCond as a 1D-Brohan differential action trajectory and learn it with a two-stage training framework before final continuous trajectory prediction. With the simultaneous autoregressive generation of discrete and numeric trajectories, we name our method AutoVLA-D (Double). Experiments on NAVSIM navtest, nuScenes, and NeuroNCAP show that discrete trajectories are weaker as direct outputs but more effective as TrajCond, consistently improving final continuous trajectory prediction across closed-loop and open-loop driving benchmarks. Code is available at https://github.com/ShivaTeam/AutoVLA-D.

cs.RO · cs.CV

版本更新 · v3arXiv:2606.15912

On-Policy Distillation with Curriculum Turn-level Guidance for Multi-turn Agents

Gengsheng Li, Mao Zheng, Mingyang Song, Ruiqi Liu, Tianyu Yang, Jie Sun, Qiyong Zhong, Haiyun Guo 等 11 位作者

原文摘要

Multi-turn agents that plan, invoke tools, and interact with environments offer a promising paradigm for solving complex tasks, yet their capabilities typically rely on very large models whose inference cost is prohibitive in practice. On-Policy Distillation (OPD) is a natural recipe for transferring such capabilities to smaller students, but we find that it suffers a characteristic failure mode in this setting: small student errors compound across turns and push the trajectory out of the teacher's familiar state distribution, so the teacher's supervision becomes least reliable precisely where the student needs it most. We propose Guided On-Policy Distillation (Guided-OPD), a simple yet effective algorithm that mixes teacher- and student-generated turns within each rollout and schedules the teacher's intervention probability along a curriculum that decays to zero. Strong guidance keeps early trajectories close to the teacher distribution and is then gradually withdrawn to recover the purely on-policy regime used at inference. On ALFWorld, ScienceWorld, and WebShop, distilling Qwen3 students from a Qwen3-30B-A3B teacher, Guided-OPD yields average relative gains of 21.1\% in Score and 25.5\% in Success Rate over vanilla OPD, with larger gains on smaller students.

cs.LG · cs.AI

版本更新 · v3arXiv:2512.14329

Wearable-informed generative digital avatars predict task-conditioned post-stroke locomotion

Yanning Dai, Chenyu Tang, Ruizhi Zhang, Wenyu Yang, Yilan Zhang, Yuhui Wang, Junliang Chen, Xuhang Chen 等 19 位作者

原文摘要

Dynamic prediction of locomotor capacity after stroke could enable more individualized rehabilitation, yet current assessments largely provide static impairment scores and do not indicate whether patients can perform specific tasks such as slope walking or stair climbing. Here, we present a wearable-informed data-physics hybrid generative framework that reconstructs a stroke survivor's locomotor control from wearable inertial sensing and predicts task-conditioned post-stroke locomotion in new environments. From a single 20 m level-ground walking trial recorded by five IMUs, the framework personalizes a physics-based digital avatar using a healthy-motion prior and hybrid imitation learning, generating dynamically feasible, patient-specific movements for inclined walking and stair negotiation. Across 11 stroke inpatients, predicted postures achieved approximately 95% of the practically attainable accuracy for slope ascent and 80% for stair climbing, respectively, demonstrating reliable task-specific gait prediction. In a multicenter randomized pilot feasibility study (n = 21; 28 days), access to scenario-specific locomotion predictions to support task selection and difficulty titration was associated with larger gains in Fugl-Meyer lower-extremity scores than the control group (mean change 6.0 vs 3.7 points; p < 0.05). These results suggest that wearable-informed generative digital avatars may augment individualized gait rehabilitation planning and provide a pathway toward dynamically personalized post-stroke motor recovery strategies.

cs.CE · cs.AI

版本更新 · v2arXiv:2605.21699

X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation

Sharath Turuvekere Sreenivas, Adithyakrishna Venkatesh Hanasoge, Mingyu Yang, Ali Taghibakhshi, Saurav Muralidharan, Ashwath Aithal, Pavlo Molchanov

原文摘要

Cross-tokenizer knowledge distillation allows a student to learn from teachers with incompatible vocabularies while preserving its tokenizer and inference architecture. Existing logit-based methods either supervise only the observed token or match full distributions through strict token partitions and heuristic ranking. We identify two limitations: an uncommon-token failure, where task-critical tokens outside the shared vocabulary are suppressed, and over-conservative matching, where exact string equality discards useful correspondences. We propose X-Token, which addresses both through a sparse projection initialized from tokenizer-level string rules and optionally refined during distillation. P-KL removes the partition and projects the student distribution into the teacher vocabulary; H-KL retains the hybrid loss while relaxing matching through the projection. A token-coverage audit guides the choice between them, and both extend naturally to heterogeneous teachers. Across Llama, OLMo, and Gemma students, X-Token achieves the highest average accuracy in all four teacher-student settings among all evaluated cross-tokenizer methods. Complementary teachers provide a further 1.30-point gain, and both variants are faster than the evaluated cross-tokenizer baselines in matched profiling.

cs.LG · cs.CL

新论文 · v1arXiv:2611.10356

SepLRM: A Foundation Model Paradigm for Recommendation

Di Chen, Xijun Xiao, Qin Ren, Weijiang Lai, Zhijian Pan, Zhentao Pan, Pengfei Nie, Cheng Yuan 等 26 位作者

原文摘要

Large recommendation models (LRMs) improve recommendation performance by scaling behavior sequence length, model capacity, and training compute. However, the return on investment (ROI) of continued scaling deteriorates as marginal gains diminish and long-sequence encoding costs rise, especially when this computation is repeatedly executed by distinct models for diverse recommendation stages and business scenarios. To address this issue, we propose SepLRM, a recommendation foundation model (RFM) paradigm that identifies reusable sequence encoding and reorganizes multiple end-to-end (E2E) LRMs into one RFM and multiple independently optimized vertical models (VMs). The RFM adopts an encoder-decoder architecture and exports its final-layer encoder state as the shared key-value (KV) cache that is independent of downstream task-offered candidates. Unlike candidate-specific logits or aggregated user embeddings, the KV cache preserves fine-grained behavioral information. Separation at this native KV interface also allows each VM to construct candidate-conditioned queries while retaining the same query-KV interaction as its E2E counterpart, enabling high-fidelity capability transfer. To ensure both transfer effectiveness and system efficiency, we co-design cache compression, the training and serving workflows, and LG-Store, a distributed storage system for KV caches. Experiments on three large-scale datasets show that SepLRM achieves state-of-the-art offline performance with a transfer rate of approximately 100%. It also demonstrates strong transferability across model iterations, recommendation stages, and business scenarios. Deployment in two large-scale industrial scenarios substantially improves the ROI of sequence scaling and delivers consistent gains in online A/B tests at ByteDance.

cs.IR

版本更新 · v3arXiv:2601.09920

SyncTwin: Fast Digital Twin Construction and Synchronization for Safe Robotic Manipulation

Ruopeng Huang, Boyu Yang, Wenlong Gui, Jeremy Morgan, Erdem Biyik, Jiachen Li

原文摘要

Accurate and safe robotic manipulation under dynamic and visually occluded conditions remains a core challenge in real-world deployment. We introduce SyncTwin, a novel digital twin framework that unifies fast 3D scene reconstruction and real-to-sim synchronization for robust and safety-aware robotic manipulation in such environments. In the offline stage, we employ VGGT to rapidly reconstruct object-level 3D assets from RGB images, forming a reusable geometry library. During execution, SyncTwin continuously synchronizes the digital twin by tracking real-world object states and uses stored assets to complete partially observed geometry. The synchronized twin enables motion planners to compute collision-aware robot trajectories in simulation, with execution on the real robot closing the real-to-sim-to-real loop. Experiments in dynamic and occluded scenes show that SyncTwin improves manipulation performance and motion safety, demonstrating the effectiveness of digital twin synchronization for real-world robotic execution.

cs.RO