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)

2025-11-21 至 2025-11-21 共收录 4
2511.16668 2025-11-21 cs.CV

V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models

V-ReasonBench:面向视频生成模型的统一推理基准套件

Yang Luo, Xuanlei Zhao, Baijiong Lin, Lingting Zhu, Liyao Tang, Yuqi Liu, Ying-Cong Chen, Shengju Qian, Xin Wang, Yang You

机构 * NUS(新加坡国立大学) HKUST(GZ)(香港科技大学(广州)) HKU(香港大学) USYD(澳大利亚悉尼大学) CUHK(香港中文大学) LIGHTSPEED Project(LIGHTSPEED项目)

AI总结 V-ReasonBench通过四个维度评估视频生成模型的推理能力,提供可验证任务以衡量结构化问题解决、空间认知、模式推理和物理动态,促进更可靠的推理模型发展。

Comments Project Page: https://oahzxl.github.io/VReasonBench

详情

展开后加载摘要…

URL PDF HTML 收藏
2511.16278 2025-11-21 cs.CR cs.AI

"To Survive, I Must Defect": Jailbreaking LLMs via the Game-Theory Scenarios

为生存,我必须背叛:通过博弈论场景进行大语言模型的劫持攻击

Zhen Sun, Zongmin Zhang, Deqi Liang, Han Sun, Yule Liu, Yun Shen, Xiangshan Gao, Yilong Yang, Shuai Liu, Yutao Yue, Xinlei He

机构 * The Hong Kong University of Science and Technology (Guangzhou)(香港科学与技术大学(广州)) East China Normal University(华东师范大学) Flexera(Flexera公司) Zhejiang University(浙江大学) Xidian University(西安电子科技大学) Xi’an Jiaotong University(西安交通大学) Institute of Deep Perception Technology, JITRI(JITRI深度感知技术研究所)

AI总结 本文提出一种基于博弈论的可扩展黑盒劫持框架GTA,通过重塑LLM目标以提高攻击成功率,实现在多种场景下的高ASR表现。

Comments 20 pages

详情

展开后加载摘要…

URL PDF HTML 收藏
2510.27237 2025-11-21 cs.CV

Fusion of Multi-scale Heterogeneous Pathology Foundation Models for Whole Slide Image Analysis

多尺度异构病理基础模型融合用于全切片图像分析

Zhidong Yang, Xiuhui Shi, Wei Ba, Zhigang Song, Haijing Luan, Taiyuan Hu, Senlin Lin, Jiguang Wang, Shaohua Kevin Zhou, Rui Yan

机构 * School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China(中国科学技术大学生物医学工程学院) Division of Life Science, Department of Chemical and Biological Engineering, State Key Laboratory of Nervous System Disorders, The Hong Kong University of Science and Technology(香港科技大学生命科学系) SIAT-HKUST Joint Laboratory of Cell Evolution and Digital Health, HKUST Shenzhen-Hong Kong Collaborative Innovation Research Institute(深圳-香港联合创新研究院细胞进化与数字健康联合实验室) Department of Hepatobiliary Surgery, The First Affiliated Hospital of USTC, Division of Life Sciences and Medicine, University of Science and Technology of China(中国科学技术大学附属第一医院肝胆外科) Center for Medical Imaging, Robotics, Analytic Computing & Learning (MIRACLE), Suzhou Institute for Advanced Research, USTC, Suzhou, Jiangsu, China(中国科学技术大学苏州先进研究所) Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心) Institute of Computing Technology, Chinese Academy of Sciences(中国科学院计算技术研究所) Jiangsu Provincial Key Laboratory of Multimodal Digital Twin Technology, Suzhou, Jiangsu, China(江苏省多模态数字孪生技术重点实验室) Key Laboratory of Precision and Intelligent Chemistry, USTC, Hefei, Anhui, China(中国科学技术大学精准与智能化学重点实验室) Department of Pathology, Chinese PLA General Hospital, Beijing, China(中国人民解放军总医院病理科)

AI总结 本文提出FuseCPath框架,通过多尺度异构病理基础模型融合提升全切片图像分析性能。

Comments 22 pages, 9 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2501.15638 2025-11-21 cs.LG cs.AI

A Comprehensive Survey on Self-Interpretable Neural Networks

对自解释神经网络的全面综述

Yang Ji, Ying Sun, Yuting Zhang, Zhigaoyuan Wang, Yuanxin Zhuang, Zheng Gong, Dazhong Shen, Chuan Qin, Hengshu Zhu, Hui Xiong

机构 * Artificial Intelligence Thrust, The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州)人工智能方向) Computer Network Information Center, Chinese Academy of Sciences(中国科学院计算机网络信息中心)

AI总结 本文综述了自解释神经网络的现有方法,从五个关键视角总结了其方法,并提供了可视化示例和评估指标,旨在推动该领域的发展。

Journal ref Proceedings of the IEEE, 2025

详情

展开后加载摘要…

URL PDF HTML 收藏