arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

University of Chinese Academy of Sciences(中国科学院大学)

共收录 1952
2606.23759 2026-06-24 cs.AR cs.AI cs.SE 新提交

VeriPilot: An LLM-Powered Verilog Debugging Framework

VeriPilot:一个基于LLM的Verilog调试框架

Yihan Wang, Cheng Liu, Jiazheng Zhang, Lei Zhang, Long Cheng, Xiaowei Li, Huawei Li

机构 * State Key Lab of Processors, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所国家专用集成电路设计实验室) University of Chinese Academy of Sciences(中国科学院大学) North China Electric Power University(华北电力大学)

AI总结 提出VeriPilot框架,利用黄金参考模型和LLM实现细粒度Verilog调试,通过内部变量语义对齐和CDFG信号追踪定位并修复错误,在CVDP基准上将GPT-4o修复成功率从54.3%提升至85.71%。

Comments 13 pages, 6 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.22984 2026-06-24 cond-mat.dis-nn cond-mat.stat-mech cs.LG 新提交

Scalable Physics-Inspired Transformers for Spin Glasses

可扩展的物理启发式Transformer用于自旋玻璃

Lu Zhong, Wenli Duan, Jing Liu, Pan Zhang, Ying Tang

机构 * Institute of Fundamental and Frontier Sciences, University of Electronic Science and Technology of China(基础与前沿科学研究院,电子科技大学) School of Physical Science and Technology, Beijing University of Posts and Telecommunications(物理科学与技术学院,北京邮电大学) Institute of Theoretical Physics, Chinese Academy of Sciences(理论物理研究所,中国科学院) School of Fundamental Physics and Mathematical Sciences, Hangzhou Institute for Advanced Study, UCAS(基础物理与数学科学学院,杭州先进研究院,UCAS) School of Physics, University of Electronic Science and Technology of China(物理学院,电子科技大学) Key Laboratory of Quantum Physics and Photonic Quantum Information, Ministry of Education, University of Electronic Science and Technology of China(量子物理与光量子信息重点实验室,教育部,电子科技大学) Non-classical Information Science Basic Discipline Research Center of Sichuan Province, University of Electronic Science and Technology of China(四川省非经典信息科学基础学科研究中心,电子科技大学)

AI总结 针对受阻自旋玻璃中玻尔兹曼分布采样效率低的问题,提出一种具有可解释稀疏注意力和自旋定制位置嵌入的物理启发式Transformer,利用FlashAttention实现并行祖先采样,在单GPU上实现前所未有的系统规模模拟,并解决现有方法在特定温度下的局限性。

详情

展开后加载摘要…

URL PDF HTML 收藏
2604.17473 2026-06-24 cs.CV cs.AI 版本更新

Dual-Anchoring: Addressing State Drift in Vision-Language Navigation

双锚定:解决视觉语言导航中的状态漂移问题

Kangyi Wu, Pengna Li, Kailin Lyu, Xi Lin, Lin Zhao, Qingrong He, Jinjun Wang, Jianyi Liu

机构 * National Key Laboratory of Human-Machine Hybrid Augmented Intelligence(人机混合增强智能国家重点实验室) National Engineering Research Center for Visual Information and Applications(视觉信息与应用国家工程研究中心) Institute of Artificial Intelligence and Robotics(人工智能与机器人研究院) Xi’an Jiaotong University(西安交通大学) Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) Johns Hopkins University(约翰霍普金斯大学) Joy Future Academy, JD(京东探索研究院)

AI总结 提出双锚定框架,通过指令进度锚定和记忆地标锚定分别解决进度漂移和记忆漂移,显著提升长场景导航成功率。

Comments Accepted by ECCV26

详情

展开后加载摘要…

URL PDF HTML 收藏
2412.10795 2026-06-24 cs.CV q-bio.QM

Reliable and superior elliptic Fourier descriptor normalization and its application software ElliShape with efficient image processing

可靠且优越的椭圆傅里叶描述符规范化及其应用软件ElliShape与高效的图像处理

Hui Wu, Jia-Jie Yang, Chao-Qun Li, Jin-Hua Ran, Ren-Hua Peng, Xiao-Quan Wang

机构 * Big Data and AI Biodiversity Conservation Research Center, Institute of Botany, Chinese Academy of Sciences(大数据与人工智能生物多样性保护研究中心,植物研究所,中国科学院) State Key Laboratory of Plant Diversity and Specialty Crops and Key Laboratory of Systematic and Evolutionary Botany, Institute of Botany, Chinese Academy of Sciences(植物多样性与特色作物国家重点实验室和系统与进化植物学重点实验室,植物研究所,中国科学院) Plant Science Data Center, Chinese Academy of Sciences(植物科学数据中心,中国科学院) China National Botanical Garden(中国国家植物园) School of Life Sciences, Qilu Normal University(生命科学学院,青岛师范学院) University of Chinese Academy of Sciences(中国科学院大学) Key Laboratory of Noise and Vibration Control, Institute of Acoustics, Chinese Academy of Sciences(噪声与振动控制重点实验室,声学研究所,中国科学院)

AI总结 本文提出改进的椭圆傅里叶描述符规范化方法,开发了ElliShape软件,提升了轮廓分析的效率和稳定性,适用于复杂图像的处理及生物多样性研究。

Journal ref Methods in Ecology and Evolution, 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.23404 2026-06-23 cs.CL cs.AI 新提交

ReasoningLens: Hierarchical Visualization and Diagnostic Auditing for Large Reasoning Models

ReasoningLens:大型推理模型的分层可视化与诊断审计

Jun Zhang, Jiasheng Zheng, Boxi Cao, Yaojie Lu, Hongyu Lin, Jia Zheng, Xianpei Han, Le Sun

机构 * Chinese Information Processing Laboratory(中国信息处理实验室) Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所) University of Chinese Academy of Sciences(中国科学院大学)

AI总结 提出ReasoningLens框架,通过分层结构、智能审计和系统分析,将长思维链转化为可操作洞察,用于解释、调试和优化大型推理模型。

Comments Our project is available at https://github.com/icip-cas/ReasoningLens

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.22627 2026-06-23 cs.CL cs.AI 新提交

Orthogonal Representation Editing: Decoupling Semantic Entanglement in Batch Knowledge Editing of LLMs

正交表示编辑:解耦大型语言模型批量知识编辑中的语义纠缠

Wenhao Yu, Zhicong Lu, Bo Lv, Fangyin Ma, Kaiwen Wei, Shihao Yang, Nayu Liu

机构 * School of Computer Science and Technology, Tianjin University(天津大学计算机科学与技术学院) Kexin Technology(可心科技) University of Chinese Academy of Sciences(中国科学院大学) Tencent Hunyuan(腾讯混元) College of Computer Science, Chongqing University(重庆大学计算机学院)

AI总结 针对批量知识编辑中语义表示纠缠导致性能下降的问题,提出正交表示编辑(ORE),通过构建通用语义子空间并对编辑向量施加正交约束来解耦纠缠,并引入门控非线性表示头自适应学习编辑位置,实验表明ORE在跨语言场景中表现优异。

Comments Accepted to Findings of ACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.22565 2026-06-23 cs.CL cs.AI cs.CV 新提交

Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do

轻看,重思:多模态思维链推理能做什么和不能做什么

Zhuoran Jin, Kejian Zhu, Hongbang Yuan, Yupu Hao, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao

机构 * The Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所复杂系统认知与决策智能实验室) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)

AI总结 本文系统探究多模态思维链推理在12个感知与推理任务上的表现,发现CoT对感知任务有副作用,但对数学、科学等多图像推理有效,且现有开源多模态推理模型提升有限,视觉推理仍是瓶颈。

Comments ACL 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.22486 2026-06-23 cs.CV cs.AI cs.HC 新提交

Human and AI collaboration for pulmonary nodule segmentation

人类与AI协作进行肺结节分割

Hongqiao Dong, Wenhao Chi, Ruobing Liang, Xiaokui Yang, Wenhua Liang, Peng Hou, Wenjun Pu, Yipeng Zhao, Ping Chen, Haiping Liu, Jianxing He, Bo Liu

机构 * State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences(数学科学国家重点实验室,数学与系统科学研究院,中国科学院) PET/CT Center, The First Affiliated Hospital of Guangzhou Medical University(广州医科大学第一附属医院PET/CT中心) Department of Thoracic Surgery and Oncology, The First Affiliated Hospital of Guangzhou Medical University(广州医科大学第一附属医院胸外科与肿瘤科) Department of Mathematical Science, Tsinghua University(清华大学数学科学系) Yau Mathematical Sciences Center, Tsinghua University(清华大学尤金数学科学中心) China State Key Laboratory of Respiratory Disease & National Clinical Research Centre for Respiratory Disease, Guangzhou, China(中国呼吸疾病国家重点实验室及呼吸疾病临床研究中心,广州,中国) School of Mathematical Sciences, University of Chinese Academy of Sciences(中国科学院大学数学科学学院) National Center for Respiratory Medicine, National Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University(呼吸医学国家中心、呼吸疾病临床研究中心、广州呼吸健康研究院、广州医科大学第一附属医院)

AI总结 提出Hi-Seg框架,基于SAM通过人类迭代优化提示实现肺结节分割,在12中心1179例CT上平均Dice达85%,优于多种深度学习模型,并降低标注时间。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.22462 2026-06-23 cs.LG 新提交

Adaptive Recurrent Message Passing for Test Time Computing on Graphs

自适应递归消息传递用于图上的测试时计算

Junshu Sun, Wanxing Chang, Qingming Huang, Shuhui Wang

机构 * State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所人工智能安全国家重点实验室) University of Chinese Academy of Sciences(中国科学院大学) DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)

AI总结 针对图数据与固定架构不匹配的问题,提出自适应递归图模型AdaR,通过理论推导步依赖作为自适应收敛的充要条件,并利用归一化步信息和梯度监督实现灵活测试时计算,在归纳和直推设置中优于强基线。

Comments Accepted by ICML 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.22429 2026-06-23 cs.LG 新提交

Enhancing LLMs for Graph Tasks via Graph-aware LoRA Generation

通过图感知的LoRA生成增强LLMs的图任务能力

Junshu Sun, Wanxing Chang, Qingming Huang, Shuhui Wang

机构 * State Key Lab. of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所人工智能安全国家重点实验室) University of Chinese Academy of Sciences(中国科学院大学) DAMO Academy, Alibaba Group(阿里巴巴集团达摩院)

AI总结 提出GaRA模型,通过生成任务特定的低秩权重更新注入全图信息,避免信息损失,在零样本图学习任务上优于基线方法。

Comments Accepted by ICML 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21949 2026-06-23 cs.CV cs.CL 新提交

CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales

CapRiCorn-1K:面向视频字幕和时间尺度上主体指代一致性的综合基准

Xinlong Chen, Jiafu Tang, Yue Ding, Yizhuo Jia, Bozhou Li, Bohan Zeng, Yang Shi, Shihao Li, Yiyan Ji, Qiang Liu, Weihong Lin, Yuanxing Zhang, Pengfei Wan, Liang Wang, Tieniu Tan

机构 * NLPR, CASIA(中国科学院自动化研究所模式识别国家重点实验室) UCAS(中国科学院大学) Kling Team(Kling团队) NJU(南京大学) FDU(复旦大学) PKU(北京大学)

AI总结 提出CapRiCorn-1K基准,评估视频字幕质量和主体指代一致性,发现现有模型在长视频中表现下降,且指标与下游任务性能强相关。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21048 2026-06-23 cs.CL 新提交

Event Ontology Expansion via LLM-Based Conceptualization

基于LLM概念化的事件本体扩展

Weicheng Ren, Zixuan Li, Long Bai, Xiaolong Jin, Jiafeng Guo, Xueqi Cheng

机构 * State Key Laboratory of AI Safety(人工智能安全国家重点实验室) Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所) School of Computer Science and Technology, University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院)

AI总结 提出ConceptE框架,利用LLM从句子和触发词中提取概念级语义,增强事件聚类和层次扩展,在ACE、ERE和MAVEN上显著优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.21023 2026-06-23 cs.LG 新提交

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

揭秘LLM推理中的数值不稳定性:使用HEAL实现关键任务的可复现推理

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

机构 * UCLA(加州大学洛杉矶分校) UC Berkeley(加州大学伯克利分校) University of Chinese Academy of Sciences(中国科学院大学)

AI总结 针对LLM在关键任务中因16位精度导致输出不一致的问题,提出HEAL方法,通过INT16量化和代数误差补偿,在保持FP32精度的同时减少性能开销。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.19120 2026-06-23 cs.LG cs.CV 新提交

Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation

先看后思:解耦感知与推理以实现抗捷径的多模态在策略自蒸馏

Sihan Wang, Xiyao Liu, Lianqing Liu, Zhi Han

机构 * State Key Laboratory of Robotics and Intelligent Systems, Shenyang Institute of Automation, Chinese Academy of Sciences(机器人与智能系统国家重点实验室,沈阳自动化研究所,中国科学院) University of Chinese Academy of Sciences(中国科学院大学)

AI总结 提出ViGOS框架,通过解耦感知和推理,在MLLM后训练中避免文本捷径,提升图像依赖行为。

Comments 29 pages, 5 figures, 8 tables; Project page: https://oedosoldier.github.io/ViGOS/

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.13007 2026-06-23 cs.LG cs.AI 新提交

scLLM-DSC: LLM-Knowledge Enhanced Cross-Modal Deep Structural Clustering for Single-Cell RNA Sequencing

scLLM-DSC:基于LLM知识增强的跨模态深度结构聚类用于单细胞RNA测序

Ping Xu, Pengjiang Li, Tian Du, Zaitian Wang, Jiawei Gu, Zhiyuan Ning, Ziyue Qiao, Pengfei Wang, Yuanchun Zhou

机构 * Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心) University of Chinese Academy of Sciences(中国科学院大学) Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences(中国科学院大学杭州高等研究院) School of Computing and Information Technology, Great Bay University(大湾区大学计算机科学与技术学院) School of Engineering, Westlake University(西湖大学工学院)

AI总结 提出scLLM-DSC框架,通过知识驱动语义视图与结构感知拓扑视图的跨模态对比对齐,利用LLM增强单细胞RNA测序数据的聚类性能,显著优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.29245 2026-06-23 cs.CR cs.CL cs.LG 版本更新

Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated Content

LLM的隐式身份技术:跨数据集、模型和生成内容的指纹识别与水印

Bing Liu, Shunping Wang, Yufan Zhu, Xinyi Yu, Jing Huang, Linkang Du, Hongbin Pei, Wei Luo

机构 * School of Cyber Science and Engineering, Xi’an Jiaotong University, Xi’an, China(西安交通大学计算机科学与工程学院) State Grid Henan Marketing Service Center, Henan, China(国网河南营销服务中心) Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China(中国科学院信息工程研究所) School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China(中国科学院大学网络安全学院) School of Information Technology, Deakin University, Geelong, Australia(迪金大学信息技术学院)

AI总结 本文综述了LLM指纹识别和水印技术,提出隐式身份统一抽象,并基于生命周期分类法组织数据集、模型和生成内容的技术,建立评估框架。

Comments Accepted by IJCAI-ECAI 2026. 11 pages, 1 figure. Survey and taxonomy of LLM fingerprinting and watermarking for identity, provenance, generated-content attribution, and asset protection

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.15098 2026-06-23 cs.CV 版本更新

A Comprehensive Study on Visual Token Redundancy for Discrete Diffusion-based Multimodal Large Language Models

基于离散扩散的多模态大语言模型中视觉标记冗余的综合研究

Duo Li, Zuhao Yang, Xiaoqin Zhang, Ling Shao, Shijian Lu

机构 * CCDS, NTU, Singapore(南洋理工大学新加坡分校) CCST, ZJUT, China(浙江工业大学中国分校) Terminus AI Lab, UCAS, China(中国科学院大学人工智能实验室)

AI总结 本研究系统分析了离散扩散多模态大语言模型中视觉标记冗余的演化规律,发现其仅出现在从头训练的模型处理长答案任务时,并验证了视觉标记剪枝会导致信息损失,而层跳过和渐进剪枝分别适用于不同架构的加速。

Comments Accepted by CVPR 2026

Journal ref Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Findings, 2026, pp. 2823-2833

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.08262 2026-06-23 cs.RO cs.AI cs.CV 版本更新

CLAR: Learning 3D Representations for Robotic Manipulation by Fusing Masked Reconstruction with Multi-Level Contrastive Alignment

CLAR: 通过融合掩码重建与多层级对比对齐学习用于机器人操作的3D表示

Wenbo Cui, Chengyang Zhao, Yuhui Chen, Haoran Li, Zhizheng Zhang, Dongbin Zhao, He Wang

机构 * SKL-MAIS, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所SKL-MAIS) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) Carnegie Mellon University(卡内基梅隆大学) Galbot CFCS, School of Computer Science, Peking University(北京大学计算机科学与技术学院CFCS)

AI总结 提出CLAR框架,融合掩码自编码与全局跨模态对比学习,并引入基于可变形注意力的局部自适应对齐机制,解决3D预训练中空间几何与语义细节的权衡问题,在视觉运动策略学习中达到最优性能。

详情

展开后加载摘要…

URL PDF HTML 收藏
2411.18276 2026-06-23 cs.RO cs.AI 版本更新

GAPartManip: A Large-scale Part-centric Dataset for Material-Agnostic Articulated Object Manipulation

GAPartManip:面向材料无关铰接物体操作的大规模部件中心数据集

Wenbo Cui, Chengyang Zhao, Songlin Wei, Jiazhao Zhang, Haoran Geng, Yaran Chen, Haoran Li, He Wang

机构 * Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所) School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院) CFCS, School of Computer Science, Peking University(北京大学计算机科学系) Carnegie Mellon University(卡内基梅隆大学) University of California, Berkeley(加州大学伯克利分校) Xi’an Jiaotong-Liverpool University(西安交通大学利物浦大学) Galbot

AI总结 提出大规模部件中心数据集GAPartManip,结合照片级材质随机化和部件级交互姿态标注,通过模块化框架提升深度估计与交互姿态预测,在仿真和真实场景中实现鲁棒的铰接物体操作。

Comments Accepted by ICRA 2025. Project page: https://pku-epic.github.io/GAPartManip/

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.19733 2026-06-19 cs.CV cs.AI 新提交

QueryGaussian: Scalable and Training-Free Open-Vocabulary 3D Instance Retrieval

QueryGaussian: 可扩展且无需训练的开词汇3D实例检索

Xiuyuan Zhu, Ke Lu, Zijie Yang, Chao Yue, Jian Xue, Dongming Zhang

机构 * University of Chinese Academy of Sciences(中国科学院大学) State Key Laboratory of Communication Content Cognition(通信内容认知国家重点实验室) Peng Cheng Laboratory(鹏城实验室)

AI总结 提出QueryGaussian,一种无需训练的开词汇3D实例检索框架,通过实例级查询机制解耦语义与几何,结合2D视觉模型和时序融合模块,在保持精度的同时降低70%以上GPU内存并加速180倍,支持城市级场景。

Comments 8 pages, 4 figures, 6 tables. Accepted to the 2026 IEEE International Conference on Systems, Man, and Cybernetics (SMC 2026)

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.19215 2026-06-18 cs.CV 新提交

GUMP-Net: An interpretable model-data-driven intelligent algorithm for multi-class pelvic segmentation

GUMP-Net: 一种用于多类盆腔分割的可解释模型-数据驱动智能算法

Liheng Wang, Yinghui Zhang, Licheng Zhang, Hailin Xu, Qiyong Cao, Chong Chen

机构 * State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences(数学科学国家重点实验室,数学与系统科学研究院,中国科学院) University of Chinese Academy of Sciences(中国科学院大学) Department of Orthopedics, The Fourth Medical Center of Chinese PLA General Hospital(中国人民解放军第四医学中心骨科部) National Clinical Research Center for Orthopedics, Sports Medicine and Rehabilitation(骨科、运动医学与康复临床研究中心) Department of Trauma and Orthopedics, People’s Hospital Peking University(北京大学人民医院创伤与骨科部) Department of Orthopedics and Traumatology, Beijing Jishuitan Hospital, Capital Medical University(首都医科大学北京积水潭医院骨科与创伤科)

AI总结 提出GUMP-Net,结合改进测地线活动轮廓模型与深度神经网络,实现多类盆腔分割,在小训练数据下表现更优,并提供可解释几何视角。

Comments 26 pages, 8 figures, 3 tables

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.18886 2026-06-18 cs.CV 新提交

DINO-Med3D: Bridging Dimension and Domain Gaps in Volumetric Segmentation via Progressive Adaptation

DINO-Med3D:通过渐进式适应弥合体分割中的维度与领域差距

Haoyu Hu, Xiyao Ma, Shiqi Liu, Linsen Zhang, Xiaoliang Xie, Xiaohu Zhou, Zeng-Guang Hou

机构 * University of Chinese Academy of Sciences(中国科学院大学) Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)

AI总结 提出两阶段渐进框架DINO-Med3D,通过多切片嵌入模块、3D适配器和并行细节恢复流,将DINOv3适配到3D医学分割,在五个数据集上超越现有方法。

Comments Accepted at MICCAI 2026. The camera-ready version and link will be made publicly available upon publication

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.18781 2026-06-18 cs.CL 新提交

Lost in a Single Vector: Improving Long-Document Retrieval with Chunk Evidence Aggregation

迷失在单一向量中:通过分块证据聚合改进长文档检索

Shanshan Lyu, Yiwei Wang, Yujun Cai, Jiafeng Guo, Shenghua Liu

机构 * Chongqing University(重庆大学) State Key Laboratory of AI Safety(人工智能安全国家重点实验室) Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所) University of California, Merced(加州大学默塞德分校) University of Queensland(昆士兰大学) University of Chinese Academy of Sciences(中国科学院大学)

AI总结 针对长文档检索中单向量编码削弱关键片段证据的问题,提出无训练的分块证据聚合策略DICE,通过独立编码分块并聚合为单一向量,在保持标准接口的同时显著提升检索性能。

Comments Code is available at https://github.com/PunchlineAAAA/DICE

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.18650 2026-06-18 cs.LG 新提交

BLADE: Scalable Bi-level Adaptive Data Selection for LLM Training

BLADE: 面向LLM训练的可扩展双层自适应数据选择

Jiaxing Wang, Deping Xiang, Jin Xu, Zirui Liu, Zicheng Zhang, Guoqiang Gong, Jun Fang, Chao Liu, Pengzhang Liu, Tongxuan Liu, Ke Zhang, Qixia Jiang

机构 * University of Oxford(牛津大学) Renmin University of China(中国人民大学) University of Chinese Academy of Sciences(中国科学院大学)

AI总结 提出BLADE框架,通过拉格朗日乘子将双层优化转化为单层惩罚目标,避免逆Hessian计算,实现动态参考模型,理论保证一阶收敛,实验优于现有方法。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.18599 2026-06-18 cs.CR cs.AI 新提交

MIDS: Detecting Stealthy Masquerade and Tampering Attacks on CAN Bus via Bidirectional Mamba

MIDS:通过双向Mamba检测CAN总线上的隐蔽伪装和篡改攻击

Qiqi Liu, Runhan Song, Lei Cui, Heng Zhang, Yuyan Sun, Limin Sun

机构 * Institute of Information Engineering, Chinese Academy of Sciences(信息工程研究所,中国科学院) School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院) Zhongguancun Laboratory(中关村实验室)

AI总结 针对CAN总线缺乏加密认证易受攻击的问题,提出MIDS双流框架,利用双向状态空间模型并行处理标识符和载荷,在特斯拉Model 3数据集上F1达96.94%,优于基线8个百分点以上。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.17453 2026-06-18 cs.AI 新提交

MapSatisfyBench: Benchmarking Satisfaction-Aware Map Agents through Behavior-Grounded Implicit Decision Factors

MapSatisfyBench: 通过行为隐含决策因素基准测试满意度感知的地图智能体

Lubin Bai, Mengyu Cao, Sixue Wang, Zhongwei Wan, Yue Pan, Jiale Hou, Xiang Li, Xiuyuan Zhang

机构 * University of Chinese Academy of Sciences(中国科学院大学) Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所)

AI总结 提出MapSatisfyBench基准,通过恢复用户行为链中的隐含决策因素来评估地图智能体的满意度感知能力,实验表明现有智能体在显式任务完成上表现良好,但在满足隐含需求方面仍有局限。

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.15088 2026-06-18 cs.SD cs.CL eess.AS 新提交

When the Same Musical Knowledge Forgets Differently: A Clean Probe of Pathway-Dependent Forgetting

当相同的音乐知识以不同方式遗忘:路径依赖遗忘的干净探测

Yu Liu, Zhiwei Yang, Wenxiao Zhang, Cong Cao, Fangfang Yuan, Kun Peng, Haimei Qin, Lei Jiang, Jin B. Hong, Hao Peng, Yanbing Liu

机构 * Institute of Information Engineering, CAS(中国科学院信息工程研究所) School of Cyber Security, UCAS(中国科学院大学网络空间安全学院) The University of Western Australia(西澳大利亚大学) Beihang University(北京航空航天大学)

AI总结 提出配对路径控制协议(PPCP),发现多模态模型中通过文本路径获取的知识比音频路径更易遗忘,且该效应不受架构深度影响,主要源于输入表示差异。

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.14288 2026-06-18 astro-ph.CO cs.AI cs.CE gr-qc hep-th 版本更新

DeepInflation: an AI agent for research and model discovery of inflation

DeepInflation:用于暴胀研究与模型发现的AI智能体

Ze-Yu Peng, Hao-Shi Yuan, Qi Lai, Jun-Qian Jiang, Gen Ye, Jun Zhang, Yun-Song Piao

机构 * School of Physical Sciences, University of Chinese Academy of Sciences, Beijing 100049, China International Centre for Theoretical Physics Asia-Pacific, University of Chinese Academy of Sciences, 100190 Beijing, China Taiji Laboratory for Gravitational Wave Universe, University of Chinese Academy of Sciences, 100049 Beijing, China School of Fundamental Physics Mathematical Sciences, Hangzhou Institute for Advanced Study, UCAS, Hangzhou 310024, China Institute of Theoretical Physics, Chinese Academy of Sciences, P.O. Box 2735, Beijing 100190, China D\' e partement de Physique Th\' e orique, Universit\' e de Gen\` e ve, 24 quai Ernest-Ansermet, CH-1211 Gen\` e ve 4, Switzerland

AI总结 提出基于多智能体架构的AI智能体DeepInflation,集成大语言模型、符号回归引擎和检索增强生成知识库,自动发现与最新观测一致的单场慢滚暴胀势,并解释理论背景。

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.13562 2026-06-18 physics.med-ph cs.CV cs.NA math.NA

An efficient approach with theoretical guarantees to simultaneously reconstruct activity and attenuation sinogram for TOF-PET

一种具有理论保证的高效方法用于同时重建TOF-PET的活动和衰减正弦图

Liyang Hu, Chong Chen

机构 * State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing 100190, China(数学科学国家重点实验室,数学与系统科学研究院,中国科学院,北京100190,中国) University of Chinese Academy of Sciences, Beijing 100190, China(中国科学院大学,北京100190,中国)

AI总结 本文提出一种基于最大似然估计的新方法,用于同时重建TOF-PET的活动和衰减正弦图,通过利用指数形式的衰减校正因子和活动总量约束,证明了方法的可解性,并通过实验验证了其在精度和效率上的优越性。

Comments 32 pages, 11 figures, 4 tables

Journal ref IEEE Transactions on Computational Imaging 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2606.18198 2026-06-17 cs.CR cs.CV 新提交

Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners

看见不等于筛查:针对智能体技能扫描仪的多模态隐藏指令攻击

Xiaojun Jia, Jie Liao, Simeng Qin, Ke Ma, Wenbo Guo, Yebo Feng, Aishan Liu, Yang Liu

机构 * Nanyang Technological University, Singapore(南洋理工大学,新加坡) Chongqing University, China(重庆大学) Northeastern University, China(东北大学) University of Chinese Academy of Sciences, China(中国科学院大学) Beihang University, China(北航大学)

AI总结 针对现有技能扫描仪忽视图像中恶意指令的盲点,提出SkillCamo多模态攻击将指令隐藏于图像,并设计ExecScan执行级扫描模块,通过意图提取、行为重建等检测隐藏指令,实验证明其有效性。

详情

展开后加载摘要…

URL PDF HTML 收藏