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)

2026-06-18 至 2026-06-18 共收录 9
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