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

+1112新增论文
+875其中 AI 相关
+133已有论文修订
+97新增 AI 导读

arXiv 最近完成扫描:2026-11-20 01:33 · 全站最近入库:2026-11-19 19:09各信源进度 →

统计口径与数据新鲜度

统计 2026-11-19 01:45 — 2026-11-20 01:45(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:2026-11-20 01:33最近发现新增版本:2026-11-19 19:09库内论文最新更新时间:2026-11-19 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。

27,982 已收录论文23,249 AI 相关8,559 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 38 篇论文 · 按版本更新时间排序上轮扫描起点 2026-11-20 01:31(北京时间)
版本更新 · v2arXiv:2610.35385

EmbodiedLab: Beyond Manipulation, Benchmarking Embodied Agents That Act to Know

Hongcheng Gao, Zelin Zheng, Alex Zhou, Jay Zhu, Shijia Ge, Yazhe Wang, Xiping Li, Jianshu Zeng 等 21 位作者

原文摘要

Physical action not only changes the state of an environment but is also the way to know its hidden properties: what cannot be seen must be inferred from the feedback to the change. As embodied agents advance from executing procedures to pursuing goals, success depends on properties neither given nor visible, so they must act to know. Existing benchmarks separate changing from knowing: manipulation benchmarks give the target state, so nothing has to be found out, whereas exploration and discovery benchmarks let the agent find out by looking or querying, so nothing physical has to be changed. Quantitative science experiments offer a natural testbed: the properties sought are new in every instance, appear only in instrument readings under conditions the agent sets up, and can be checked exactly. We introduce EmbodiedLab, a simulated laboratory of 35 such experiments. Given only a goal, the agent must decide what to measure, operate the apparatus with a robot arm, read instruments through cameras and judge when its readings suffice. Its 30 determination tasks specify what to find out, whereas its 5 optimization tasks ask only for the best result the apparatus allows. With native control, the strongest of seven frontier agents succeeds on 41.4% of the tasks. Ablations reveal two bottlenecks: contact-rich manipulation, where ground-truth depth and motion planning change the success rate by at most 10 points, whereas executing every operation for the agent on five of the tasks raises it from at most 20% to at least 70%, so what an agent can know is bounded by how reliably it acts; and closed-loop experimental rigor, where with manipulation supplied, agents fail to gather sufficient readings or read instruments accurately, and most optimization runs stop at one design. Beyond evaluation, EmbodiedLab offers a resamplable environment with verifiable rewards for training embodied agents.

cs.RO

新论文 · v1arXiv:2611.23674

Learning What to Degrade: A Recoverability-Aware Curriculum for Reliable Smart-Glasses Super-Resolution

Yaopeng Wang, Qingliang Wang, Yilun Jin, Xiujin Liu, Han Yue, Chen Xia, Renjie Zhu, Chuang Sheng

原文摘要

Degradations in smart-glasses images obscure small text and fine-grained structures needed by vision-language models (VLMs) for visual assistance. We introduce an high-resolution (HR)-referenced semantic evaluation protocol that compares VLM outputs on restored images with those on corresponding HR references. Our evaluation reveals two failure modes: generative SR can synthesize misleading details, whereas restoration-oriented SR can leave critical evidence blurred or ambiguous. These findings motivate improving faithful detail recovery in restoration-oriented SR, where a key training challenge is to provide sufficiently difficult inputs while retaining recoverable visual information. We propose ReDiC (Recoverability-Difficulty Curriculum), which combines a model-independent recoverability proxy with model-relative restoration difficulty to adapt training degradation severity. ReDiC increases severity when inputs are recoverable and restoration is easy, maintains challenging but recoverable conditions, and reduces severity when estimated recoverability is low. It modifies only training degradation generation, leaving the SR architecture and reconstruction objective unchanged. Across NAFNet, SwinIR, and MambaIR, ReDiC improves average PSNR by approximately 2.5 dB and HR-referenced semantic scores by about 3 points over the corresponding baselines on synthetic benchmarks, with further gains confirmed by LLM-based and human evaluations on 200 real smart-glasses captures.

cs.CV

新论文 · v1arXiv:2611.23476

GUARD: Stabilizing Recursive Self-Improvement with Regret Guidance

Minghe Zhang, Xuetao Kang, Yifei Ming, Yanfei Chen, Han Yu, Yufan Zhuang, Chen-Yu Lee

原文摘要

Autonomous AI agents pair a frozen base model with an editable harness of prompts, skills, tool rules, and memory. Recursive self-improvement (RSI) adapts this harness from experience without weight updates, yet self-editing without external graders often backfires: reflection and scalar scores conflate what an edit newly broke with what remains unsolved, causing local regressions, skill forgetting, and memory bloat. We introduce GUARD (Grader-free Unsupervised Environment Design [UED] with Adaptive Rule Distillation), a closed-loop framework for reference-free continual harness evolution. Our key insight is to decompose each task into pre-execution self-checks and guide harness updates via directional regret. Each round grades trajectories against these checks, pinning mastered rules while prioritizing newly broken behaviors, and selects among parallel candidate edits by critic-free group-relative fitness. A Soft-HURT gate then promotes an edit only when gains outweigh regressions, scoping specialized fixes to prevent over-triggering and guaranteeing non-regression on its gated buffer. At test time, one frozen harness runs in a single pass. Across benchmarks on memory, skill evolution, continual task streams, and domain reasoning, GUARD consistently improves performance without catastrophic forgetting or memory pollution while substantially cutting deployment token usage.

cs.AI · cs.LG

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 · v3arXiv:2508.03162

An open dataset of gas adsorption in deformable metal-organic frameworks for direct air capture

Anuroop Sriram, Logan M. Brabson, Xiaohan Yu, Sihoon Choi, Kareem Abdelmaqsoud, Elias Moubarak, Pim de Haan, Sindy Löwe 等 16 位作者

原文摘要

Engineering economical and scalable processes for direct air capture (DAC) from humid air relies on atomistic modeling to search and identify promising sorbent materials from a vast chemical space. Machine learning has emerged as a powerful tool for predicting material properties in an efficient yet accurate manner, but these models require large sets of carefully curated training data. We present the Open DAC 2025 (ODAC25) dataset comprising nearly 60 million DFT single-point calculations for CO2, H2O, N2, and O2 adsorption in ~15,000 MOFs. ODAC25 introduces functionalized MOFs, high-energy adsorbate placements, and synthetically generated frameworks to maximize the versatility of models trained on the dataset. ODAC25 improves upon the accuracy of DFT calculations in previous works and applies engineering intuition from recent work regarding the treatment of adsorbate-induced MOF flexibility. We release state-of-the-art machine-learned interatomic potentials trained on ODAC25 and demonstrate their utility via Henry's coefficient predictions. ODAC25 enables MOF screening for DAC at a resolution previously unattainable.

cond-mat.mtrl-sci · cs.LG · physics.chem-ph

新论文 · v1arXiv:2611.22200

MIRAGE: Motion Identity Reduction via Autoregressive Generative Encoding for Privacy-Preserving Skeleton-based Motion Data

Thomas Carr, Xujun Che, Depeng Xu, Shuhan Yuan, Aidong Lu

原文摘要

Skeleton motion identifies people through body proportions and movement style, and skeleton streams are increasingly passed to third-party analytics that run action classifiers trained on raw data. A prior adversarial anonymizer adds a per-frame residual in the raw coordinate space but sees one frame at a time; motion retargeting needs a target skeleton and complete sequences, which rules out online use. We present MIRAGE, a target-free, causal anonymizer that adds an identity-reducing residual to each incoming frame in the raw coordinate space, computed by attention over past frames. One causal, optionally windowed mask governs every attention in a rotary-position encoder-decoder, and key/value caches let the trained function run frame by frame; on all 56,578 NTU 60 sequences, batched and streaming outputs differ by at most 7.2e-6 m. Reported results use an unbounded window, so per-stream state grows with stream length. We evaluate against a passive adversary that applies raw-trained identity models and an adaptive adversary that trains on the anonymizer's output, treating the adaptive adversary as the headline, on NTU RGB+D 60 over five generator seeds, alongside the per-frame residual anonymizer of Moon et al. trained identically. When consumers retrain on the released data, MIRAGE keeps 83.9% action recognition (raw 89.1%; Moon et al. 88.7%) while a retrained identity classifier reaches 43.4% re-identification (RI) over 40 subjects, against 69.4% for Moon et al. and 75.4% on raw data. The strongest adaptive attacker still reaches 49.3% (chance 2.5%), so MIRAGE reduces identity leakage; it does not anonymize. Against raw-trained (frozen) classifiers, MIRAGE lowers RI below the strongest retargeting baseline (10.36% vs. 22.09%), but frozen action recognition falls to 37.04% (vs. 75.82%), so at full residual scale it is not a drop-in replacement for raw input to existing frozen models.

cs.CV

版本更新 · v2arXiv:2603.27460

Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development

Zhongying Deng, Cheng Tang, Ziyan Huang, Jiashi Lin, Ying Chen, Junzhi Ning, Chenglong Ma, Jiyao Liu 等 126 位作者

原文摘要

Foundation models have demonstrated remarkable success across diverse domains and tasks, primarily due to the thrive of large-scale, diverse, and high-quality datasets. However, in the field of medical imaging, the curation and assembling of such medical datasets are highly challenging due to the reliance on clinical expertise and strict ethical and privacy constraints, resulting in a scarcity of large-scale unified medical datasets and hindering the development of powerful medical foundation models. In this work, we present the largest survey to date of medical image datasets, covering over 1,000 open-access datasets with a systematic catalog of their modalities, tasks, anatomies, annotations, limitations, and potential for integration. Our analysis exposes a landscape that is modest in scale, fragmented across narrowly scoped tasks, and unevenly distributed across organs and modalities, which in turn limits the utility of existing medical image datasets for developing versatile and robust medical foundation models. To turn fragmentation into scale, we propose a metadata-driven fusion paradigm (MDFP) that integrates public datasets with shared modalities or tasks, thereby transforming multiple small data silos into larger, more coherent resources. Building on MDFP, we release an interactive discovery portal that enables end-to-end, automated medical image dataset integration, and compile all surveyed datasets into a unified, structured table that clearly summarizes their key characteristics and provides reference links, offering the community an accessible and comprehensive repository. By charting the current terrain and offering a principled path to dataset consolidation, our survey provides a practical roadmap for scaling medical imaging corpora, supporting faster data discovery, more principled dataset creation, and more capable medical foundation models.

cs.CV · cs.AI

新论文 · v1arXiv:2611.20771

Nemotron 3.5 Bolt E4B 4GB: An Open and Efficient Small Language Model for Fast Conversational Agents

NVIDIA, :, Adi Margolin, Aditya Malte, Aishwarya Chhabra, Alex Hodson, Ameya Sunil Mahabaleshwarkar, Ambrish Dantrey 等 113 位作者

原文摘要

We introduce Nemotron 3.5 Bolt E4B 4GB, an open and efficient small language model further post-trained from Gemma-4-E4B-it and optimized for speed and intelligence per GB of memory used for fast conversational agents. The model carries forward Gemma's strong conversational capabilities and further improves multi-turn tool use, instruction following, and input grounding for fast, local voice/device assistants, interactive personas, and embedded/Edge interfaces. The model combines natural conversation with multi-turn agentic capabilities to power voice/device assistants, interactive characters and robotic/IoT interfaces running on GeForce RTX, Jetson, and RTX/DGX Spark. Experiments on 21 benchmarks show that Nemotron 3.5 Bolt E4B 4GB achieves the highest average accuracy while generating the fewest output tokens in both reasoning and non-reasoning modes, compared with Gemma-4-E4B-it and Qwen3.5-4B. The model is released with a DFlash drafter. With DFlash, Bolt E4B achieves $2.74\times$ the per-user decode speed of inference without speculative decoding at concurrency~1, and $1.21\times$ the generation throughput of Gemma-4-E4B-it with MTP at batch size 1.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2611.20688

VIVID: A Visual Harness for Agentic Video Editing

Wenhan Yu, Zhaoxi Zhang, Zhilong Tan, Weikang Li, Lei Sha

原文摘要

Video editing requires agents to make editing decisions grounded in audiovisual observations and precise temporal localization, and to evaluate their effects in rendered outputs. General-purpose coding agents possess strong comprehension, reasoning, and code execution capabilities, while media interaction and evidence management mechanisms tailored to video tasks can further unlock their editing potential. We introduce VIVID, a visual harness that supports multiple native coding agents in video post-production without additional model training. VIVID provides tools for on-demand video inspection, audio analysis, and transcription, and preserves observations alongside their corresponding media versions and temporal coordinates. Agents can actively retrieve these observations as they reason, perform edits using their native coding and shell tools, and inspect rendered outputs to guide subsequent revisions. On AgenticVBench, comprising 100 tasks across Assembly, Repair, Sequencing, and Repurpose, Codex with VIVID achieves an average score of 58.6%, an improvement of 20.2 percentage points over native Codex. The same harness also integrates with Claude Code and OpenCode, achieving average scores of 55.1% and 37.1%, respectively, both substantially exceeding their native baselines. These results highlight VIVID's potential as a reusable visual harness for extending the capabilities of general-purpose coding agents to video editing.

cs.AI · cs.CV · cs.MM

新论文 · v1arXiv:2611.21690

EgoLink: Egocentric Language-Vision Interactive Network Knowledge Challenge Summary

Renhe Sun, Yueying Feng, Bohan Yu, Tong Niu, Yunqi Liu, Zitong Wang, Haolin He, Kexin Shi 等 15 位作者

原文摘要

The EgoLink Challenge at ACM Multimedia 2026 benchmarks egocentric multimodal intelligence linking first-person perception, social reasoning, and interactive action. Unlike benchmarks centered on visible objects and activities, EgoLink evaluates whether models can interpret emotional and social cues, resolve visually grounded references, and convert user requests into verified tool-mediated actions. Its two tracks cover social reasoning in egocentric video and interactive agents that complete service tasks through dialogue, tool use, and closed-loop execution. Together, they test whether perception, reasoning, and decision-making remain coupled under both offline question answering and state-changing interaction. We highlight a multi-stage Track 1 data pipeline for multiple-choice question (MCQ) generation, chain-of-thought generation, automatic quality grading, and video-contribution filtering. We summarize the task design, evaluation metrics, rules, leaderboards, and representative solutions. The benchmark combines objective answer scoring with process- and result-based evaluation, enabling analysis of both final correctness and execution quality. The best Track 1 system achieved 0.9263 accuracy, while the best Track 2 system achieved 0.844 joint success and 0.916 micro accuracy. Participant reports reveal a shared principle: strong systems make intermediate evidence explicit through candidate verification, option-robust reasoning, scenario-aware planning, tool canonicalization, and state-aware correction before answering or acting. These findings highlight the importance of process verification and evidence-grounded reasoning for reliable egocentric multimodal intelligence.

cs.CV · cs.AI

新论文 · v1arXiv:2611.20674

LEAF-OPD: Learning to Forget from Privileged Contexts via On-Policy Distillation

Zirui Pang, Zhijie Deng, Yuancheng Wang, Qihan Yu, Xin Li, Jiaheng Wei, Zixin Zhong

原文摘要

LLM unlearning aims to erase targeted knowledge from large language models while preserving their utility. However, many existing methods suppress target knowledge without explicitly teaching the model how to respond to queries about it. We propose LEAF-OPD (LEArning to Forget from Privileged Contexts via On-Policy Distillation), in which a frozen teacher provides token-level supervision on student-generated responses. On forget data, the teacher uses privileged contexts (instructions not to reveal knowledge about forget targets) to guide forgetting. On retain data, the teacher provides supervision without privileged context to preserve model utility. The student operates without privileged context in both cases, learning how to respond when encountering knowledge that should be forgotten. A key challenge is that the teacher often provides effective supervision only at the first few tokens of student trajectories. We introduce Supervision Signal (SS) to measure corrective supervision over a specified token interval, evaluating the entire trajectory (SS1) and its second half (SS0.5) to assess overall strength and late-stage persistence. When supervision is weak, lightweight SFT strengthens the teacher's context-conditioned refusal behavior, substantially increasing both scores. We evaluate LEAF-OPD on three widely used benchmarks: TOFU, RWKU, and MUSE-News. On TOFU, LEAF-OPD achieves the best Forget Quality, Model Utility, and Forget ROUGE-L while maintaining competitive retain performance. On RWKU, it outperforms the second-best method by 34% in Forget Quality while maintaining competitive Retain Quality. These results demonstrate the effectiveness of privileged-context supervision with on-policy token-level distillation for LLM unlearning.

cs.CL

版本更新 · v3arXiv:2511.15090

SciEGQA: A Dataset for Scientific Evidence-Grounded Question Answering and Reasoning

Wenhan Yu, Zhaoxi Zhang, Wang Chen, Guanqiang Qi, Weikang Li, Lei Sha, Deguo Xia, Jizhou Huang

原文摘要

Scientific documents contain complex multimodal structures, which makes evidence localization and scientific reasoning in Document Visual Question Answering particularly challenging. However, most existing benchmarks evaluate models only at the page level without explicitly annotating the evidence regions that support the answer, which limits both interpretability and the reliability of evaluation. To address this limitation, we introduce SciEGQA, a scientific document question answering and reasoning dataset with semantic evidence grounding, where supporting evidence is represented as semantically coherent document regions annotated with bounding boxes. SciEGQA consists of two components: a **human-annotated fine-grained benchmark** containing 1,623 high-quality question--answer pairs, and a **large-scale automatically constructed training set** with over 30K QA pairs generated through an automated data construction pipeline. Extensive experiments on a wide range of Vision-Language Models (VLMs) show that existing models still struggle with evidence localization and evidence-based question answering in scientific documents. Training on the proposed dataset significantly improves the scientific reasoning capabilities of VLMs. The project page is available at https://yuwenhan07.github.io/SciEGQA-project/.

cs.DB · cs.AI · cs.CV

版本更新 · v4arXiv:2511.07979

Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models

Wenhan Yu, Xinbo Lin, Lanxin Ni, Jinhua Cheng, Lei Sha

原文摘要

Large language models (LLMs) have demonstrated strong reasoning abilities across specialized domains, motivating research into their application to legal reasoning. However, existing legal benchmarks often conflate factual recall with genuine inference, fragment the reasoning process, and overlook the quality of reasoning. To address these limitations, we introduce MSLR, the first Chinese multi-step legal reasoning dataset grounded in real-world judicial decision making. MSLR adopts the IRAC framework (Issue, Rule, Application, Conclusion) to model structured expert reasoning from official legal documents. In addition, we design a scalable Human-LLM collaborative annotation pipeline that efficiently produces fine-grained step-level reasoning annotations and provides a reusable methodological framework for multi-step reasoning datasets. Evaluation of multiple LLMs on MSLR shows only moderate performance, highlighting the challenges of adapting to complex legal reasoning. Further experiments demonstrate that Self-Initiated Chain-of-Thought prompts generated by models autonomously improve reasoning coherence and quality, outperforming human-designed prompts. MSLR contributes to advancing LLM reasoning and Chain-of-Thought strategies and offers open resources for future research. The dataset and code are available at https://github.com/yuwenhan07/MSLR-Bench and https://law.sjtu.edu.cn/flszyjzx/index.html.

cs.AI

版本更新 · v9arXiv:2505.12620

BusterX: MLLM-Powered AI-Generated Video Forgery Detection and Explanation

Haiquan Wen, Yiwei He, Zhenglin Huang, Tianxiao Li, Zihan Yu, Xingru Huang, Lu Qi, Baoyuan Wu 等 10 位作者

原文摘要

As generative video models become increasingly realistic, detecting AI-generated videos requires systems that offer both accuracy and interpretability. However, applying Multimodal Large Language Models (MLLMs) to video forensics is currently limited by outdated datasets, simplistic evaluation protocols, and a reliance on black-box classification. To address these issues, we introduce a comprehensive dataset, benchmark, and baseline model for video forgery detection. First, we present \textbf{GenBuster-200K}, a fair dataset of over 200,000 high-quality videos sourced from state-of-the-art generators, featuring diverse real-world scenarios. Second, we propose \textbf{GenBuster-Bench}, a diagnostic benchmark spanning three progressive tracks (In-Domain, Out-of-Domain, and In-the-Wild) to evaluate models across \textit{domain shifts} and \textit{generational shifts}. Finally, we develop \textbf{BusterX}, a simple MLLM baseline with Reinforcement Learning (RL) training. Instead of direct binary classification, BusterX formulates detection as a visual reasoning task, where the generated reasoning chain serves as detector itself. Experimental results demonstrate that BusterX outperforms several leading MLLMs in both detection accuracy and rationale quality.

cs.CV

新论文 · v1arXiv:2611.16701

Sprint3D: Accelerating End-to-End 3D Asset Generation through Pipeline Optimization

Sho Kuno, Ruihan Yu, Yonghao Yu, Guixu Lin, Lian Fu, Muyao Niu, Yu-Ju Tsai, Zheng-Hui Huang 等 14 位作者

原文摘要

Image-to-3D generative models now produce asset-quality textured meshes, but at minutes per asset they remain slow to iterate with and costly to deploy. Prior work has mostly accelerated the sampling of the networks, and where it also optimizes the mesh processing, it trains its own generators. We instead start from a publicly released pipeline and ask how much of its end-to-end time can be saved. Profiling the public Pixal3D pipeline shows that its latency is dominated by what happens after the networks: the four rectified flows take 14% of the wall-clock time and mesh post-processing takes 85%, most of it in CPU-based UV unwrapping. We therefore first rebuild the mesh post-processing on the GPU and take it off the critical path, then cut the per-evaluation overhead of the flows and distill them from 76 to 8 network evaluations. The resulting pipeline, Sprint3D, reduces the median time per asset from 133 s to 4.05 s on one H200 GPU at the same export settings (33$\times$). At the same time, on 2,653 held-out Toys4K objects it improves every input-view normal metric of the Pixal3D protocol, with a slightly lower mean silhouette IoU, lower point-cloud alignment scores and less fine texture detail. The rebuilt post-processing alone also speeds up TRELLIS.2, which uses the same export code, by 6.7$\times$ without a detectable change in the evaluated metrics.

cs.CV · cs.GR

新论文 · v1arXiv:2611.16183

Data-Efficient LLM Safety Alignment Guided by Interpretable Features

Hongyu Li, Zhan Yu, Zhe Zhao, Kimmo Yan, Xiong Kuang, Renfen Hu

原文摘要

Existing large language models typically rely on massive fine-tuning datasets for safety alignment, which results in higher costs for safety alignment and often leads to the problem of over-refusal. We propose Less is Safer (LIS), a compact yet highly effective dataset for safety alignment, constructed through interpretable feature-guided selection and adversarial synthesis. Specifically, we leverage Sparse Autoencoder (SAE) activations to efficiently select prompts that cover diverse and interpretable safety features. Then, we employ a multi-agent adversarial synthesis framework to generate harmless prompts that nevertheless elicit unnecessary refusals. LIS contains only 2.4K samples, yet outperforms much larger datasets, e.g., TRIDENT-Core (26K), TRIDENT-Edge (19K) and WildJailbreak (262K), in overall performance on four safety and five over-refusal benchmarks. Through ablation experiments, we demonstrate that neither safety data nor over-refusal data alone can achieve optimal results. We also used safety features from SAE, annotated by an LLM, for data filtering, but the results were inferior to those obtained using the pipeline proposed in this paper.

cs.CL · cs.AI

版本更新 · v3arXiv:2506.15253

Specification-based Security Evaluation of Real-World Agents Tool-Calling under Long-Horizon Context Tasks

Yuchuan Fu, Minghe Wang, Xiaohan Yuan, Chenlin Zou, Kaitong Jia, Jinfeng Li, Dongxia Wang

原文摘要

As large language model (LLM) agents are increasingly deployed in long-horizon unattended scenarios, security evaluation of them before deployment becomes increasingly essential and challenging. Existing evaluation methods mainly follow the paradigms of LLM-as-a-Judge or Agent-as-a-Judge. However, such judges are themselves often vulnerable to hallucination and can even be affected by perturbations. Furthermore, because capturing full environment states at every step is often prohibitively expensive in open-ended environments, existing evaluations typically rely on textual logs and the final environment state. As a result, they may miss transient violations that are overwritten before the trajectory ends or never reflected in textual logs. We present RAS-Eval, a specification-based security evaluation framework for LLM agents. RAS-Eval uniformly expresses utility and security objectives as Linear Temporal Logic (LTL) specifications over tool-call trajectories and dynamic environment observations, and verifies them with an off-the-shelf model checker. This design addresses both limitations above. First, unlike LLM-as-a-Judge and Agent-as-a-Judge, RAS-Eval derives deterministic verdicts from formally defined properties, eliminating evaluator-side uncertainty and remaining reliable even for long-horizon trajectories. Second, RAS-Eval observes exactly the states on which the verdict depends, making it affordable to monitor the environment throughout execution and detect transient violations that leave little trace in the logs or final environment state. Moreover, we design a multi-agent-based dataset construction pipeline. Using it, we construct a benchmark (https://github.com/lanzer-tree/RAS-Eval) of 200 normal tasks and 800 attack tasks spanning four attack surfaces: indirect prompt injection, tool poisoning, skill code injection, and tool code injection.

cs.CR · cs.AI

新论文 · v1arXiv:2611.13204

Ground Reaction Force-Aware Model Predictive Control for Underactuated Upright Physical Assistance

Darren Biskup, Jeonghan Yu, Zibo Yu, Sunil K. Agrawal

原文摘要

Many rehabilitation robots execute prescribed motions using reactive tracking controllers that do not explicitly incorporate the user's instantaneous human-ground interaction. This paper presents Ground Reaction Force-Aware Model Predictive Control (GRF-MPC), a framework for upright physical assistance. By integrating live GRF and center of pressure (CoP) measurements directly into a human centroidal dynamics model, GRF-MPC formulates a real-time quadratic program (QP) that optimizes assistive forces and moments over a receding horizon. We deployed GRF-MPC on the Robotic Upright Stand Trainer (RobUST) in an underactuated 4-cable configuration and evaluated it against a fully actuated 8-cable Cartesian impedance baseline in nearly 300 trials across six healthy participants. Across tasks spanning impulsive perturbations, lunge trajectories, and voluntary limits of stability, GRF-MPC reduced peak planar center-of-mass (CoM) error by 19.6% during perturbations, lowered trajectory tracking error by 24.1%, required 28.7% less net mechanical work, and permitted a 45.9% greater normalized voluntary excursion area. The underlying QP solves in under 1 ms, comfortably enabling 100 Hz replanning and demonstrating that incorporating live human-ground interaction into predictive control yields stronger, more transparent physical assistance with half the actuators.

cs.RO · eess.SY

版本更新 · v2arXiv:2606.21023

Demystifying Numerical Instability in LLM Inference: Achieving Reproducible Inference for Mission-Critical Tasks with HEAL

Zhenting Zhu, Lucas Thai, Shan Yu, Yicheng Liu, Yifan Qiao, Chenxi Wang, Harry Xu, Junyi Shu

原文摘要

As Large Language Models (LLMs) deploy into mission-critical domains (e.g., finance, medicine, and law), output reproducibility has become a strict system requirement. While practitioners use greedy decoding to eliminate algorithmic stochasticity, empirical deployments with 16-bit precisions still exhibit catastrophic output divergence across heterogeneous GPUs. Through SASS-level profiling, we reveal that this inconsistency is fundamentally driven by truncation errors introduced during downcasting at kernel boundaries. However, achieving reproducibility via a global FP32 pipeline incurs prohibitive system penalties: bypassing 16-bit hardware accelerators hurts compute efficiency, while upcasting the KV cache doubles memory overhead. To bridge this gap, we propose Hybrid Error ALleviation (HEAL), a targeted intervention that approximates FP32 precision while resolving hardware constraints through two targeted mechanisms. First, recognizing that floating-point formats underutilize their bit-width for Q, K, V tensors, HEAL applies INT16 quantization that preserves numerical stability without expanding the KV cache footprint. Second, HEAL synthesizes high-precision matrix multiplications via an algebraic error compensation strategy, executing entirely on high-throughput 16-bit Tensor Cores. To evaluate our approach practically, we introduce MCR-Bench, a benchmark targeting reproducibility in mission-critical tasks. HEAL achieves the same level of reproducibility on downstream tasks as the FP32 baseline while reducing the performance overhead by up to 6.0$\times$.

cs.LG

新论文 · v1arXiv:2611.09091

TUGB: A Two-stage Uncertainty-aware Generative Auto-Bidding Framework

Luzhan Yuan, Chao Mi, Xiahao Shi, Yi Mao, Shengsheng Niu, Xin Zhu, Jie He, Zhangang Lin 等 9 位作者

原文摘要

Generative modeling, particularly Decision Transformers, shows promise in auto-bidding strategies. However, it struggles with limited exploration in static offline datasets, vulnerability to dynamic environmental shifts, and a reliance on heuristic return-to-go (RTG) specifications that may yield suboptimal performance on unseen traffic. To address these challenges, we propose the Two-stage Uncertainty-aware Generative Auto-Bidding (TUGB) framework. TUGB integrates generative sequence modeling with Reinforcement Learning (RL). It employs a two-stage pipeline where a pre-trained Generative Bidding Model is fine-tuned via an ensemble-based Uncertainty-aware Environment Model. This approach quantifies epistemic uncertainty to penalize high-risk trajectories and evolves the policy from RTG-conditioning to direct bidding optimization. Extensive experiments demonstrate that TUGB significantly outperforms SOTA baselines. Notably, full-scale deployment on JD Search Ad achieved a 2.32\% increase in cost and 3.57\% in target cost, validating its industrial efficacy, while its successful adaptation to subsequent mechanism upgrades and JD Food Delivery Ad further validates TUGB's superior generalization capability.

cs.LG

新论文 · v1arXiv:2611.05348

OpenBrain:面向全脑MRI分区、可审计的生成标签发布

OpenBrain: An Auditable Generated-Label Release for Whole-Brain MRI Parcellation

Qizhen Lan, Yu-Chun Hsu, Yuxiang Wei, Lijing Zhu, Zenan Sun, Liang He, Lishan Yu, Xiaoqian Jiang

AI 速读 基于摘要

作者提出并发布OpenBrain,一个带置信度与可审计证据的全脑MRI生成分区标签数据集,让用户能按风险筛选、加权或复核生成标签。

cs.CV

查看原文摘要

Automatic tools can now generate whole-brain MRI parcellations at cohort scale, but generated-label releases often provide little evidence about which cases are reliable enough to reuse. We introduce OpenBrain, a confidence-aware release of 35,838 provenance-verified OpenNeuro T1w cases from 607 source datasets. OpenBrain is organized as an auditable case-record release rather than a directory of standalone segmentation files: each record links a primary parcellation, two committee parcellations, source/license provenance, raw QC-7 measurements, percentile risks, a combined risk score R, and a confidence tier. QC-7 is a reference-free reliability panel over label geometry, image-label consistency, and committee disagreement, so users can filter, weight, audit, or re-threshold generated labels without rerunning inference. We evaluate this released evidence under a frozen protocol. Across external cohorts, lower QC-7 risk corresponds to higher generated-label quality; in fixed-budget training, lower-risk selections improve paired macro Dice over random selection by +3.2 to +3.7 percentage points. OpenBrain also exposes raw axes, committee outputs, provenance, and datasheet documentation, so confidence claims remain inspectable after download. It does not turn generated labels into manual annotations or clinical-grade segmentations. Its contribution is a large open generated-parcellation substrate, a reusable case-level risk-evidence layer, and an external validation protocol for release-time QC. Dataset: https://huggingface.co/datasets/lanqz7766/OpenBrain. Code: https://github.com/lanqz7766/openbrain.

版本更新 · v2arXiv:2611.02791

PGuard: A Native, Streaming, and Plug-in Guardrail for Multimodal Large Language Models

Junyu Lin, Mengjie Wu, Yonghao Dong, Yuchuan Fu, Jinfeng Li, Xiaodan Li, Xiaohan Yuan, Yicheng Liu 等 14 位作者

原文摘要

As streaming generation becomes the dominant serving paradigm for both text-only and multimodal large language models, ensuring safety throughout the generation process has become a critical challenge. We introduce PGuard, a native, streaming, and plug-in guardrail that transforms safety monitoring from an external serving dependency into an integrated capability of the backbone model. PGuard directly leverages the backbone's intermediate representations for token-level safety detection, without altering its original inference pathway or generation behavior. Specifically, dynamic layer gating selectively aggregates residual-stream representations across layers to extract safety-relevant signals during both prefill and autoregressive decoding. To balance detection accuracy and computational efficiency, PGuard supports multiple representation-modeling architectures, including a lightweight stateless variant and sequence-aware variants built on multi-scale causal EMA-attention and GRU-based recurrent modules. Its design also accounts for the execution characteristics of LLM serving frameworks, such as SGLang, optimizing computation and data access to minimize additional runtime and synchronization overhead. As a result, PGuard incurs only 0.82-2.26% end-to-end overhead on the hundred-billion-parameter backbone Qwen3.5-122B-A10B served by SGLang. Extensive evaluations across more than 30 benchmarks spanning text and multimodal safety, jailbreaks, cyber and CBRN risks, multilingual scenarios, and real-world traffic demonstrate state-of-the-art performance among native guardrails. On text queries with Qwen3.5-9B, PGuard achieves an average F1 score of 0.836, approaching dedicated external guardrails, while supporting deployment-time configuration of category-specific thresholds and enforcement actions.

cs.CL

新论文 · v1arXiv:2611.02468

To Coordinate or Not to Coordinate? Learning to Swim with Eight Soft Arms

Junkai Chen, Dehan Yuan, Yiyuan Zhang, Yu Duan, Fan Shi, Dixia Fan, Cecilia Laschi

原文摘要

Does effective swimming with multiple underactuated soft arms require explicit coordination between arms? We hypothesize that an eight-arm swimmer can control its swimming speed and direction by independently learning each arm's actuation amplitude under a shared rhythmic drive, without prescribed inter-arm phase coupling. To test this hypothesis, we compare three reinforcement learning-based control strategies using proximal policy optimization (PPO): (1) learning arm-specific actuation amplitudes without inter-arm phase coupling, (2) learning actuation amplitudes with prescribed inter-arm phase coupling, and (3) directly learning actuator commands through end-to-end PPO without an explicit rhythmic structure. Across 200 episodes with randomized three-dimensional velocity commands, the controller without phase coupling satisfies the tracking criterion in 169 episodes, compared with 117 for the phase-coupled controller and 28 for end-to-end PPO. Straight-line swimming and commanded direction-change trials further demonstrate more accurate velocity tracking without phase coupling. These findings suggest that effective eight-arm swimming does not require prescribed inter-arm phase coupling, but can instead be achieved through learned arm-specific amplitude modulation within a rhythmic control structure.

cs.RO

新论文 · v1arXiv:2611.01441

Renormalized Cellular Intelligence: When Does Model Reduction Preserve Collective Capability?

Xuening Wu, Yanlan Kang, Qianya Xu, Haode Yang, Shan Yu, Shenqin Yin

原文摘要

As multi-agent systems grow in size and complexity, understanding which features of their interactions support collective capability becomes increasingly difficult. Can a simpler description preserve both task performance and the measured contribution of interactions between agents? Preserving collective dynamics alone is insufficient: reduction can alter decision-relevant information or give a non-communicating baseline access to pooled observations, distorting the measured advantage of interaction. We introduce Renormalized Cellular Intelligence (RCI), a framework for specifying and auditing capability preservation across scales. RCI treats the task, interacting dynamics, matched baseline, decision interfaces, and resource budget as a joint object of reduction. It specifies dynamical closure, decision compatibility, and preservation of the intended baseline comparison, and bounds the resulting error in relative capability gain. An exact analytical construction demonstrates task-score preservation, while a counterexample shows how closed reduced dynamics can erase the measured interaction gain. Using cellular systems as models of locally interacting agents, we evaluate three reduction candidates on five frozen learned models without retraining. The final candidate reduces the evolving state from eight to five dimensions per cell (37.5%). Within-run uncertainty bounds support relative gain above a prespecified threshold for the fixed model collection, yet the candidate fails the closure and decision-preservation requirements for a complete RCI certificate. RCI provides explicit criteria for distinguishing positive interaction gains from

cs.MA

新论文 · v1arXiv:2610.40641

从极端天气到农业后果:基于智能体的AI

From extreme weather to agricultural consequences with agentic AI

Minghan Yu, Mengyu Dai, Yixin Wen, Haizhao Yang

AI 速读 基于摘要

提出WxCrop智能体,将可物理解释的天气指数与因果分析结合,预测历史与预报日期下作物损失。

physics.ao-ph · cs.AI

查看原文摘要

Extreme weather is forecast days ahead, yet its consequences for agriculture remain hard to predict: a forecast says where a storm will strike, not which crops will suffer or how much is at risk, and the records that could tell span many sources. We present WxCrop, the first agent that judges agricultural hazards from physically interpretable weather indices examined by causal analysis, and the first that combines weather and agricultural information to predict crop loss reliably for past and forecast dates. We demonstrate it in Florida on hurricanes, freezes and dry heat, with a loss model calibrated on insurance records for each, and the same procedure extends to other hazards and areas. Three checks show reliability: the hurricane index detects recorded cyclone days with an AUC of 0.98, recorded losses in held-out years are reproduced to within 2%, and independent production records confirm the county rankings (rank correlation 0.63). Users ask the agent for each crop group's loss as a fraction of expected season value, every number sourced, so that governments, growers and scientists respond to agricultural disasters quickly.

版本更新 · v2arXiv:2609.11234

NovGauge: A Fine-Grained Benchmark for Diagnosing LLMs' Capability in Paper Novelty Assessment

Guoqiang Zhang, Kexin Tan, Ming Zhang, Li Ju, Wenqing Jing, Zhonghan Yue, Jiayi Chen, Shiqiang Wu 等 15 位作者

原文摘要

Large language models (LLMs) are increasingly used in peer review at major AI conferences, yet novelty remains a persistent weak point. Existing benchmarks assess novelty as a single holistic score, making it difficult to diagnose which dimension a model misjudges or whether its evidence is faithful. We present NovGauge, a human-anchored benchmark for fine-grained novelty assessment diagnosis. The benchmark contains 619 paper pairs and 50 multi-paper sets, drawn from two expert sources: ICLR reviewer overlap claims and survey co-citations. Instances are independently labeled along three dimensions: task, problem, and method, capturing application goals, technical challenges, and solution approaches. We propose a cascading diagnostic pipeline that verifies per-dimension correctness, evidence grounding, and logical support. Evaluation of 18 LLMs shows hallucination rates ranging from 0% to 39% across dimensions, and among non-hallucinated correct-positive judgments, over 70% cite evidence fails to logically support the stated reason. The best-performing model, GPT-5.5, achieves 43-72% Verified F1 across dimensions, while most models retain less than half of their raw F1 after faithfulness verification. These results suggest that current LLMs remain far from reliable scientific novelty assessment, particularly when correctness is conditioned on faithful evidence grounding.

cs.AI

新论文 · v1arXiv:2610.38425HF 社区推荐

IntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved Generation

Shaohan Yu, Jie Qin, Wende Tan, Haiwen Diao, Limeng Qiao, Yueming Lyu, Chenyang Si

原文摘要

Humans routinely consume multimodal content, where textual and visual information is naturally interleaved. Although Unified Multimodal Models (UMMs) can jointly generate text and images, multimodal interleaved generation remains largely underexplored. Progress in this area is hindered by two key limitations: (1) the lack of well-defined interleaved generation tasks and corresponding training data, and (2) the absence of fine-grained evaluation protocols that can reliably diagnose model performance across different capability dimensions. To this end, we present IntReal, comprising two complementary components: IntReal-100K, a real-world dataset of multimodal interleaved samples spanning four major categories, and the IntReal Evaluation Suite, which evaluates model performance across seven complementary dimensions using specialized expert models, enabling coarse-to-fine diagnosis. Extensive experiments validate our evaluation suite through low inter-metric redundancy (max pairwise absolute Spearman's $ρ\leq 0.42$ ), high agreement with human judgments (83.3% accuracy), and strong consistency across different expert evaluators (Spearman's $ρ> 0.9$ ), supporting the complementarity and reliability of our metrics. By benchmarking four families of UMMs, we show that IntReal Evaluation Suite reveals distinct strengths and weaknesses across models. Post-training experiments demonstrate the utility of IntReal-100K for improving interleaved generation and further show that training unimodal generation can also benefit interleaved generation. These findings suggest that interleaved generation can benefit from modality-specific optimization, rather than requiring joint text-image training at every stage.

cs.CV

新论文 · v1arXiv:2610.38095

Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI

NVIDIA, :, Aastha Jhunjhunwala, Aayushi Ashokkumar Srivastava, Abhibha Gupta, Abhinav Garg, Abhinav Khattar, Achsah Wildish 等 559 位作者

原文摘要

We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic workloads. Super is a 120B-parameter, 12B-active multimodal model, while Lightning is a smaller 30B-parameter, 3B-active text model; both designed for efficient deployment. Both models combine large-scale distillation, long-context training, and native speculative decoding, while Super further incorporates Indic continued pretraining and agentic software-engineering mid-training. We develop a comprehensive post-training pipeline spanning supervised fine-tuning and reinforcement learning (RLVR and RLHF), complemented in Super by specialized teacher training and multi- teacher on-policy distillation (MOPD). This transforms Super from a text-only base model into a multimodal agent capable of reasoning over text, images, video, and interactive tool environments. We further explore test-time scaling through parallel agent execution and self-verification. Across training and deployment, we jointly optimize capability and efficiency. Indic continued pretraining improves Indian-language benchmarks by up to 9.82 percentage points, while agentic mid-training strengthens software-engineering capabilities and robustness across agent harnesses. The post-trained Super model achieves 51.78% on SWE-bench Pro, surpassing Nemotron 3 Ultra despite using approximately 4.6x fewer active parameters. Post-training MTP boosting improves speculative- decoding acceptance length by up to 21.8% under probabilistic draft sampling, while NVFP4 quantization achieves 99.62% median accuracy recovery relative to BF16. Inference optimizations enable up to 4,856 output tokens/s/GPU on GB200 while sustaining at least 50 tokens/s/user.

cs.CL · cs.AI · cs.LG

新论文 · v1arXiv:2610.35727

TRACE: Memory-Efficient Time Series Class-Incremental Learning via Temporal-Spectral Reconstruction

Junhui Mao, Junru Zhang, Liming Ye, Cheng Peng, Haoran Shi, Xiaoli Tang, Baokun Wang, Bin Dou 等 10 位作者

原文摘要

Web-connected sensing applications continuously generate multivariate time series with evolving behavioral categories, making Time Series Class-Incremental Learning (TSCIL) essential for adapting to new classes without forgetting previously acquired knowledge. However, preserving diverse and evolving class distributions under strict privacy and memory constraints remains a fundamental challenge. Existing approaches often face a trade-off between retaining sufficient historical knowledge for accurate recognition and minimizing the memory required for continual adaptation. To address these limitations, we propose TRACE, a memory-efficient, replay-free framework that preserves class-specific knowledge through generative modeling rather than sample rehearsal. TRACE employs a compact, frozen temporal-spectral representation and lightweight class-specific autoencoders to capture complex intra-class variations. By independently preserving each class model, TRACE avoids recursive generation and catastrophic forgetting, while enabling direct classification through reconstruction-based scoring without retaining historical samples or large statistical matrices. Extensive experiments across five TSCIL benchmarks demonstrate that TRACE achieves competitive classification accuracy while reducing mean retained memory by approximately 98.26% compared with TS-ACL, the strongest evaluated analytical baseline, and achieving an approximately 33.43% relative improvement in accuracy on GrabMyo.

cs.LG

版本更新 · v3arXiv:2605.12122

Disentangled Sparse Representations for Concept-Separated Diffusion Unlearning

Hyeonjin Kim, Hangyeol Jung, Heechan Yun, Sungjun Yun, Dong-Jun Han

原文摘要

Unlearning specific concepts in text-to-image diffusion models has become increasingly important for preventing undesirable content generation. Among prior approaches, sparse autoencoder (SAE)-based methods have attracted attention due to their ability to suppress target concepts through lightweight manipulation of latent features, without modifying model parameters. However, SAEs trained primarily for sparse reconstruction do not explicitly enforce concept-wise separation, allowing semantically related concepts to share latent features. To address this, we propose SAEParate, which explicitly separates semantically overlapping concepts in the SAE latent space through concept-aware contrastive learning, supported by cross-attention-guided spatial aggregation that emphasizes concept-relevant regions. In addition, we enhance the encoder with a nonlinear transformation to increase its expressive capacity under this separation objective, enabling more concept-discriminative latent representations. Experiments on UnlearnCanvas demonstrate state-of-the-art performance, with particularly strong gains in joint style-object unlearning, a challenging setting where existing methods suffer from severe interference between target and non-target concepts.

cs.LG · cs.AI · cs.CV