arXivDaily arXiv每日学术速递 周一至周五更新

高校专区

The Hong Kong University of Science and Technology(香港科技大学)

2026-05-19 至 2026-05-19 共收录 35
2601.13992 2026-05-19 cs.CL cs.AI

"The Whole Is Greater Than the Sum of Its Parts": A Compatibility-Aware Multi-Teacher CoT Distillation Framework

整体大于部分之和:一种兼容性感知的多教师CoT蒸馏框架

Jin Cui, Jiaqi Guo, Ruixuan Yang, Jiayi Lu, Jiepeng Zhou, Jiajun Xu, Jiangcheng Song, Boran Zhao, Pengju Ren

机构 * State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University(人机混合增强智能国家重点实验室,人工智能与机器人研究院,西安交通大学) Nankai University(南开大学) The Hong Kong University of Science and Technology(Guangzhou)(香港科技大学(广州)) School of Software Engineering, State Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Institute of Artificial Intelligence and Robotics, Xi’an Jiaotong University(软件学院,人机混合增强智能国家重点实验室,人工智能与机器人研究院,西安交通大学)

AI总结 本文提出COMPACT框架,通过动态加权不同教师的梯度,结合多维指标提升学生模型的推理能力,有效整合多样化推理能力并减少灾难性遗忘。

Comments 11pages, 9figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16572 2026-05-19 cs.CV

TriALS: Triphasic-Aided Liver Lesion Segmentation Benchmark in Non-Contrast CT

TriALS: 三相辅助非增强CT肝脏病变分割基准

Marawan Elbatel, Mohamed Ghonim, Jiaji Mao, Zhuosheng Lin, Katharina Eckstein, Andrés Martínez Mora, Jonathan Deissler, Maximilian Rokuss, Constantin Ulrich, Zdravko Marinov, Wenhui Deng, Baoxun Li, Huijun Hu, Jun Shen, Mohanad Ghonim, Khadiga Omar Nassar, Mariam Elbakry, Menna Dyab, Amr Muhammad Abdo Salem, Nouran Elghitany, Noha Elghitany, Yi Qin, Xuanqi Huang, Haonan Wang, Shao-Woo Yen, Ahmed Elghamry Saba, Salma Ahmad, Xinyan Fang, Jiahao Zhang, Xiaodi Wang, Xinghua Ma, Gongning Luo, Jessica C. Delmoral, João Manuel R. S. Tavares, Ankan Deria, Adinath Dukre, Yutong Xie, Imran Razzak, Dongwook Kim, Matthew Choi, Hanxiao Zhang, Minghui Zhang, Xin You, Abdul Qayyum, Steven A. Niederer, Moona Mazher, Rachika E. Hamadache, Ricardo Montoya-del-Angel, Robert Martí, Xavier Lladó, Toufiq Musah, Livingstone Eli Ayivor, Enrique Almar-Munoz, Agnes Mayr, Kaouther Mouheb, Esther E. Bron, Stefan Klein, Ahmed Abouelhoda, Amira Adel, Susan Adil Ali, Rainer Stiefelhagen, Klaus H. Maier-Hein, Fabian Isensee, Aya Yassin, Xiaomeng Li

机构 * Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology(香港理工大学电子与计算机工程系) AI Center of Excellence, Ain Shams University(爱思明大学人工智能中心) Department of Radiology, Ain Shams University(爱思明大学放射科) Department of Radiology, Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University(广东省恶性肿瘤表观遗传与基因调控重点实验室,中山大学孙逸仙纪念医院放射科) Nanfang Hospital, Southern Medical University(南方医科大学南华医院) Division of Medical Image Computing, German Cancer Research Center (DKFZ), Heidelberg, Germany(德国癌症研究中心(DKFZ)医学影像计算部,海德堡,德国) Medical Faculty Heidelberg, Heidelberg University(海德堡大学医学院) Faculty of Mathematics and Computer Science, Heidelberg University(海德堡大学数学与计算机科学学院) Karlsruhe Institute of Technology(卡尔斯鲁厄理工学院)

AI总结 本文提出TriALS挑战,通过多中心150例数据评估自动肝脏病变分割算法,在非增强CT条件下取得人类水平性能,但表现受训练数据规模和预训练策略影响显著。

Comments TriALS challenge paper across MICCAI 2024 and 2025; data and code at https://github.com/xmed-lab/TriALS

详情

展开后加载摘要…

URL PDF HTML 收藏
2605.16272 2026-05-19 cs.HC cs.AI

Beyond Compliance: How AI Could Help Creative Writers by Refusing Them

超越合规:AI如何通过拒绝帮助创意作家

Hua Xuan Qin, Guangzhi Zhu, Mingming Fan, Pan Hui

机构 * The Hong Kong University of Science and Technology(香港科技大学) The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)) Computational Media and Arts (Guangzhou)(计算媒体与艺术(广州)) Hong Kong, China(香港,中国)

AI总结 本文探讨AI通过拒绝请求引入反思的可能性,通过22名创意作家的质性研究,发现不同情境、认知和关系维度下的偏好差异影响反思效果,提出摩擦性AI设计的策略。

Comments conditionally accepted to Creativity & Cognition 2026

详情

展开后加载摘要…

URL PDF HTML 收藏
2601.21941 2026-05-19 cs.LG cs.AI

Robust Multimodal Representation Learning in Healthcare

医疗领域鲁棒多模态表征学习

Xiaoguang Zhu, Linxiao Gong, Lianlong Sun, Yang Liu, Haoyu Wang, Jing Liu

机构 * University of California, Davis(加州大学戴维斯分校) HKUST (GZ)(香港科技大学) University of Rochester(罗切斯特大学) Tongji University(同济大学) Georgia Institute of Technology(佐治亚理工学院) Fudan University(复旦大学) The University of British Columbia(不列颠哥伦比亚大学)

AI总结 本文提出双流特征去相关框架,通过结构因果分析处理医疗多模态数据中的系统性偏差,提升模型泛化能力,实验验证在MIMIC-IV、eICU和ADNI数据集上的性能提升。

详情

展开后加载摘要…

URL PDF HTML 收藏
2306.12282 2026-05-19 cs.DS cs.LG math.OC

Online Resource Allocation with Convex-set Machine-Learned Advice

在线资源分配与凸集机器学习建议

Negin Golrezaei, Patrick Jaillet, Zijie Zhou

机构 * Sloan School of Management, Massachusetts Institute of Technology(麻省理工学院斯隆管理学院) Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology(麻省理工学院电气工程与计算机科学系) Department of Industrial Engineering and Decision Analytics, Hong Kong University of Science and Technology(香港科学与技术大学工业工程与决策分析系)

AI总结 本文提出一种在线资源分配框架,结合凸集机器学习建议,平衡一致性与鲁棒性,通过动态保护水平提升在不确定环境下的性能。

Comments 77 pages, 8 figures

详情

展开后加载摘要…

URL PDF HTML 收藏