# Yike GUO 郭毅可 Chair Professor ![Yike GUO](../portraits/yikeguo.jpg) [官方档案](https://cse.hkust.edu.hk/admin/people/faculty/profile/yikeguo) · [个人主页](https://hkustprovost.hkust.edu.hk/) · [HTML](../../index.html#faculty-yikeguo) 1962 年生。 ## 学术指标 | 指标 | 数值 | | --- | ---: | | [累计引用](https://openalex.org/A5045081171) | 21,913 | | h-index | 70 | | i10-index | 300 | | 2024–2026 收录论文 | 217 | | 在组成员 | 65 | | 产业合作机构 | 10 | 数据日期：2026-10-17。[指标定义与分位标准](../../index.html#standards)。 ### 网络关注 - [Wikipedia 人物条目](https://en.wikipedia.org/wiki/Guo_Yike)：2025-10-01 至 2026-09-30，3,154 次浏览。 ## 教育与履历 ### 教育 - 1985 · [Tsinghua University](https://hkustprovost.hkust.edu.hk/) · Bachelor, Computing Science - 1994 · [Imperial College London](https://hkustprovost.hkust.edu.hk/) · PhD, Computing · 导师 John Darlington ### 任职与研究经历 - 2002– · [Imperial College London](https://hkustprovost.hkust.edu.hk/) · Professor of Computing - 2009 年售出 · [InforSense (Imperial College spin-out)](https://hkustprovost.hkust.edu.hk/) · Founder - 2014– · [Imperial College London](https://hkustprovost.hkust.edu.hk/) · Founding Director, Data Science Institute - 2015–2020 · [Shanghai University](https://hkustprovost.hkust.edu.hk/) · Non-Executive Dean, Computer Engineering and Science - 2020–2022 · [Hong Kong Baptist University](https://hkustprovost.hkust.edu.hk/) · Vice-President (Research and Development); Graduate School Dean - 2022-12– · [HKUST](https://hkustprovost.hkust.edu.hk/) · Provost; Chair Professor, CSE [1962 年出生于上海；凤凰网《君品谈》2024-03-07 人物访谈所载。](https://i.ifeng.com/c/8XkzTByaCvY) [2024 年《君品谈》访谈将人和机器互相理解、技术释放创造性工作的空间作为其 AI 研究愿景。](https://i.ifeng.com/c/8XkzTByaCvY) [博士导师为 John Darlington。](https://en.wikipedia.org/wiki/Guo_Yike) [2020 年本人访谈将真实、大规模产业问题与跨学科大数据研究相联系，列举铁路安全与污染等应用。](https://aecardiffknowledgehub.wales/2020/01/24/my-research-career-in-big-data-analysis-by-yike-guo-imperial-college-london/) ## 研究方向 ### [数据科学与科学应用](https://cse.hkust.edu.hk/admin/people/faculty/profile/yikeguo) 数据挖掘、机器学习、分布式数据与大规模 scientific applications。 ### [音乐与多模态生成](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) 语言音乐表征、长歌曲生成、音频视频条件统一。 ### [AI for Science 与金融](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) 分子表示、生命科学以及金融 AI 等跨领域应用；岗位含 DXM joint lab director。 长期科学数据挖掘与机器学习是官方稳定方向，近期合作明显包含科学表示学习和创意 AI。2024 分子知识增强学习、2025 YuE、2026 AudioX 展示跨领域模型研究；它们反映团队合作版图，无法据此断定本人日常主导的具体课题和学生任务。 ### 跨领域研究平台与大型合作 官方科学应用覆盖面广，近期工作中有大规模数据、模型与开源发布；直接监督机制需要本人和学生补充。 ## 实验室与成员 [Yike Guo 研究组](https://hkustprovost.hkust.edu.hk/) HKUST CSE Clear Water Bay, Hong Kong 数据科学与科学应用；音乐与多模态生成；AI for Science 与金融 ### 在组成员（65） | 成员与公开档案 | 身份与时间 | 教育背景 | 研究与经历 | 量化记录 | | --- | --- | --- | --- | --- | | [CHEN, Jialiang](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [CHEN, Long](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [CHEN, Pengyu](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [CHEN, Wenqi](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, CSE | | | — | | [DU, Mengfei](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [FAN, Liaoyuan](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, Arts and Machine Creativity | | 共同指导 | — | | [HUANG, Yidan](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [LIAO, Xinyao](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [LIN, Zikang](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [WANG, Dengyuxing](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, CSE | | | — | | [WANG, Dongyu](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, Arts and Machine Creativity | | 共同指导 | — | | [XU, Hua](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, ECE | | | — | | [YANG, Jian](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [YANG, Zhiqin](https://visitworld123.github.io/) · [Google Scholar](https://scholar.google.com/citations?user=DSjGPu0AAAAJ) · [GitHub](https://github.com/visitworld123) · [LinkedIn](https://www.linkedin.com/in/zhiqin-y-50a209193) | PhD, IIP；2025– | [Nanjing University of Science and Technology](https://visitworld123.github.io/) · BS；2024 · [Beihang University](https://visitworld123.github.io/) · MS；2025– · [HKUST](https://visitworld123.github.io/) · PhD | LLM 推理与偏好对齐、智能体记忆、协同学习；2024-06–2024-09 · [GigaAI](https://visitworld123.github.io/) · Algorithm Intern；2025-11–2026-02 · [Tencent LightSpeed](https://visitworld123.github.io/) · Algorithm Intern；2025-08–2025-10 · [HKGAI](https://visitworld123.github.io/) · Algorithm Intern；共同导师 Yike Guo、Wei Xue | [GitHub 关注](https://github.com/visitworld123) 23；[Stars](https://github.com/visitworld123) 292 | | [ZHANG, Xiaojie](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [ZHANG, Zifu](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, Arts and Machine Creativity | | 共同指导 | — | | [ZHAO, Hengyue](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [ZHENG, Huajiang](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [ZHENG, Mingxuan](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, ECE | | | — | | [ZHOU, Wuyou](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [BIAN, Weizhen](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [CUI, Yakun](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [DENG, Ning](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [GU, Hao](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [GUO, Yijie](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [KOU, Zhizhuo](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [LI, Ruoxi](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [LIN, Sida](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [LU, Guoying](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [NING, Evan K](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, CSE | | | — | | [SHI, Xuanyu](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [SUN, Jiapeng](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [WANG, Duorong](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [WANG, Yuren](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, CSE | | | — | | [ZHANG, Jingyi](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [ZHANG, Yanting](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [ZHANG, Zhenyuan](https://liar-zzy.github.io/) · [GitHub](https://github.com/Liar-zzy) · [Google Scholar](https://scholar.google.com/citations?user=TckOPxUAAAAJ) | PhD, IIP；2025-02– | 2021 · [Nanjing University of Science and Technology](https://liar-zzy.github.io/) · BEng, Software Engineering；HKUST 入学前 · [Nanjing University of Science and Technology](https://liar-zzy.github.io/) · PhD study, direct entry；2025-02– · [HKUST](https://liar-zzy.github.io/) · PhD, Artificial Intelligence | 智能体记忆、动作生成、VLA 与具身智能；共同导师 Yike Guo、Wei Xue；此前在 NJUST 随 Jianfeng Lu 读直博。 | [GitHub 关注](https://github.com/Liar-zzy) 14；[Stars](https://github.com/Liar-zzy) 31 | | [ZHOU, Qinyi](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [ZHOU, Yujin](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [ZHU, Junqi](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [ZHU, Qiyuan](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [CAI, Yiyang](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [CAO, Chuxue](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [CHAN, Chi-min](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [CHEN, Baoyang](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [CHENG, Sitong](https://cmots.github.io/) · [GitHub](https://github.com/cmots) · [Google Scholar](https://scholar.google.com/citations?user=oNProlEAAAAJ) | PhD, IIP；2024-09– | 2017–2021 · [Beijing University of Posts and Telecommunications](https://cmots.github.io/) · BEng；2021–2022 · [CUHK](https://cmots.github.io/) · MSc, Computer Science；2024-09– · [HKUST](https://cmots.github.io/) · PhD | 音频理解与生成、表达性同步语音到语音翻译；2021-02–2021-05 · [Microsoft Research Asia](https://cmots.github.io/) · Industry experience；共同导师 Wei Xue、Yike Guo | [GitHub 关注](https://github.com/cmots) 19；[Stars](https://github.com/cmots) 74 | | [HAN, Sirui](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, CSE | | | — | | [JIA, Xianzhang](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [JIANG, Chunyang](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [JIN, Yizhu](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [JU, Chengyi](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, CSE | | | — | | [LI, Yan](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [LIU, Xinyu](https://liuxinyv.github.io/) · [GitHub](https://github.com/Liuxinyv) · [Google Scholar](https://scholar.google.com/citations?user=kgRjFN8AAAAJ) | PhD, IIP；2024-01– | [Xidian University](https://liuxinyv.github.io/) · BEng, Communication Engineering；[Xidian University](https://liuxinyv.github.io/) · MSc, Computer Science and Technology；2024-01– · [HKUST](https://liuxinyv.github.io/) · PhD, Artificial Intelligence | 可控视频生成和编辑、统一多模态理解生成、强化学习后训练；2022-04–2023-10 · [Tsinghua University AIR](https://liuxinyv.github.io/) · Research Intern；2025-05–2025-12 · [Alibaba Tongyi Wan](https://liuxinyv.github.io/) · Research Intern；2026-03–2026-07 · [Kuaishou Kling](https://liuxinyv.github.io/) · Research Intern；共同导师 Yike Guo、Wenhan Luo | [GitHub 关注](https://github.com/Liuxinyv) 11；[Stars](https://github.com/Liuxinyv) 121 | | [LIU, Yulong](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, CSE | | | — | | [LU, Yiwen](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [SIMA, Qie](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [WANG, Zhiqiang](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [XU, Yucheng](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, CSE | | | — | | [ZHU, Chuanbo](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [ZHU, Han](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | 共同指导 | — | | [LI, Mengfei](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [TIAN, Zeyue](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [YUAN, Ruibin](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [ZHOU, Ziya](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP | | | — | | [PENG, Siyu](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | MPhil, IIP | | 共同指导 | — | ### 校友与去向（8） | 成员与公开档案 | 身份与时间 | 教育背景 | 研究与经历 | 量化记录 | | --- | --- | --- | --- | --- | | [CHEN, Jianyi](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP；2026 | 2026 · [HKUST](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) · PhD, IIP | 共同指导 | — | | [CHI, Xiaowei](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP；2026 | 2026 · [HKUST](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) · PhD, IIP | | — | | [LI, Lujun](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP；2026 | 2026 · [HKUST](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) · PhD, IIP | | — | | [LI, Peng](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP；2026 | 2026 · [HKUST](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) · PhD, IIP | | — | | [QI, Xingqun](https://xingqunqi-lab.github.io/QXQPage/) · [Google Scholar](https://scholar.google.com/citations?user=3tO41a8AAAAJ) | PhD, IIP；2026 | [Beijing University of Posts and Telecommunications / Queen Mary University of London](https://xingqunqi-lab.github.io/QXQPage/) · Bachelor, joint program；2022 · [Beijing University of Posts and Telecommunications](https://xingqunqi-lab.github.io/QXQPage/) · Master；2026 · [HKUST](https://xingqunqi-lab.github.io/QXQPage/) · PhD, IIP | 三维人体运动建模、医学图像分析与生物特征识别；导师 Yike Guo；共同导师 Qifeng Liu | — | | [YE, Zhen](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, IIP；2026 | 2026 · [HKUST](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) · PhD, IIP | 共同指导 | — | | [ZENG, Min](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | PhD, ECE；2025 | 2025 · [HKUST](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) · PhD, ECE | | — | | [WEN, Pengcheng](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) | MPhil, IIP；2026 | 2026 · [HKUST](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) · MPhil, IIP | 共同指导 | — | ## 指导方式与组内生活 ### [博士毕业生去向](https://aecardiffknowledgehub.wales/2020/01/24/my-research-career-in-big-data-analysis-by-yike-guo-imperial-college-london/) 在 2020 年欧洲科学院访谈中，郭毅可表示其博士毕业生中有多人已在制药行业担任高级技术负责人。 ## 业界合作 GSK（research collaboration）；Pfizer（research collaboration）；Roche（research collaboration）；KPMG（research collaboration）；Huawei（research collaboration）；BBC（research collaboration） - **[GSK](https://cse.hkust.edu.hk/admin/people/faculty/profile/yikeguo) · 研究合作**。官方履历列出的产业研究与咨询合作 - **[Pfizer](https://cse.hkust.edu.hk/admin/people/faculty/profile/yikeguo) · 研究合作**。官方履历列出的产业研究与咨询合作 - **[Roche](https://cse.hkust.edu.hk/admin/people/faculty/profile/yikeguo) · 研究合作**。官方履历列出的产业研究与咨询合作 - **[KPMG](https://cse.hkust.edu.hk/admin/people/faculty/profile/yikeguo) · 研究合作**。官方履历列出的产业研究与咨询合作 - **[Huawei](https://cse.hkust.edu.hk/admin/people/faculty/profile/yikeguo) · 研究合作**。官方履历列出的产业研究与咨询合作 - **[BBC](https://cse.hkust.edu.hk/admin/people/faculty/profile/yikeguo) · 研究合作**。官方履历列出的产业研究与咨询合作 - **[Duxiaoman Technology (Beijing) Co., Ltd.](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) · 资助研究项目**。金融信贷慢思考大模型；负责人，合作成员 Sirui Han、Dong Lou；2024– - **[InforSense](https://aecardiffknowledgehub.wales/2020/01/24/my-research-career-in-big-data-analysis-by-yike-guo-imperial-college-london/) · 创办企业，历史记录**。2020 年本人访谈记述：创办 Imperial College 衍生企业 InforSense，技术用于制药业大数据处理；公司于 2009 年出售。 - **[Huawei](https://aecardiffknowledgehub.wales/2020/01/24/my-research-career-in-big-data-analysis-by-yike-guo-imperial-college-london/) · 历史产业合作**。2020 年欧洲科学院访谈中本人列举的中国企业合作对象，合作背景为计算与大数据研究。 - **[HNA](https://aecardiffknowledgehub.wales/2020/01/24/my-research-career-in-big-data-analysis-by-yike-guo-imperial-college-london/) · 历史产业合作**。2020 年欧洲科学院访谈中本人列举的中国企业合作对象，合作背景为计算与大数据研究。 - **[China Construction Bank](https://aecardiffknowledgehub.wales/2020/01/24/my-research-career-in-big-data-analysis-by-yike-guo-imperial-college-london/) · 历史产业合作**。2020 年欧洲科学院访谈中本人列举的中国企业合作对象，合作背景为计算与大数据研究。 ## 成员实习与产业经历 - **[CHENG, Sitong](https://cmots.github.io/) · Microsoft Research Asia**（2021-02–2021-05）。Industry experience；BUPT 本科阶段；Industry experience - **[LIU, Xinyu](https://liuxinyv.github.io/) · Tsinghua University AIR**（2022-04–2023-10）。Research Intern；HKUST 博士入学前；Research Intern - **[YANG, Zhiqin](https://visitworld123.github.io/) · GigaAI**（2024-06–2024-09）。Algorithm Intern；HKUST 博士入学前；Algorithm Intern - **[YANG, Zhiqin](https://visitworld123.github.io/) · Tencent LightSpeed**（2025-11–2026-02）。Algorithm Intern；HKUST 博士阶段；Algorithm Intern - **[YANG, Zhiqin](https://visitworld123.github.io/) · HKGAI**（2025-08–2025-10）。Algorithm Intern；博士入学当年的经历；Algorithm Intern - **[LIU, Xinyu](https://liuxinyv.github.io/) · Alibaba Tongyi Wan**（2025-05–2025-12）。Research Intern；HKUST 博士阶段；Research Intern - **[LIU, Xinyu](https://liuxinyv.github.io/) · Kuaishou Kling**（2026-03–2026-07）。Research Intern；HKUST 博士阶段；Research Intern ## 学术贡献与服务 资深数据科学研究者兼大学管理者，学术地位、组织职责与实际带生安排应分别确认。 - [HKUST Provost 自 2022-12-01；CSE 与 ECE Chair Professor，HKUST-DXM AI for Finance Joint Laboratory Director。](https://facultyprofiles.hkust.edu.hk/profiles.php?profile=yike-guo-yikeguo) - [Royal Academy of Engineering Fellow、Academia Europaea Member、Hong Kong Academy of Engineering Sciences Fellow、IEEE Fellow。](https://cse.hkust.edu.hk/admin/people/faculty/profile/yikeguo) - [Imperial Data Science Institute founding director。](https://cse.hkust.edu.hk/admin/people/faculty/profile/yikeguo) ## 论文分析 ### 2024 · [APK-MRL: An Adaptive Pre-training Framework with Knowledge-enhanced for Molecular Representation Learning](https://doi.org/10.1109/bibm62325.2024.10821780) IEEE BIBM 2024 - **问题**：分子对比学习受数据依赖与增强造成知识稀缺限制。 - **方法**：融合分层骨架与化学语义先验，形成知识增强自适应预训练。 - **结果**：作者报告 drug-target interaction 和分子属性预测上相较基线有竞争力，并公开代码。 - **实验条件**：仅有 computational experiments 摘要；不能推断新药有效性、实验室验证或临床结果。 - **研究线**：体现数据科学和领域知识整合的科学应用。 阅读：Abstract（完整摘要）。 ### 2025 · [YuE: Scaling Open Foundation Models for Long-Form Music Generation](https://arxiv.org/abs/2503.08638) arXiv 2025 - **问题**：长 lyrics-to-song 需要同时保持歌词对齐、段落结构和伴奏质量。 - **方法**：Track-decoupled next-token prediction、结构渐进条件、多任务多阶段训练，扩展音乐 in-context learning。 Introduction 区分长程依赖、多声部信号、歌唱音素与配对数据稀缺；CLAP-score 与人评未必对齐，需音乐专用指标。 - **结果**：摘要报告最多 5 分钟音乐、trillion-token 训练及 MARBLE 理解任务表现；v2 对比段指出仍落后于 Suno V4。 - **实验条件**：结论将声学保真、混音、和弦及配器知识、更深韵律情感控制和弱覆盖文化继续列为改进方向。 - **研究线**：从音乐符号理解推进到完整长音频基础模型。 阅读：Abstract（完整）；1 Introduction（完整）；13 Conclusion and Future Work（完整）；v2 第 6.1 节商业系统比较（搜索返回）。 ### 2026 · [AudioX: A Unified Framework for Anything-to-Audio Generation](https://arxiv.org/abs/2503.10522v3) ICLR 2026；所读 arXiv v3 - **问题**：音频生成需在同一框架中处理不同控制模态和大规模高质量监督。 - **方法**：Multimodal Adaptive Fusion 合并文本、视频、音频条件；IF-caps 含超过 7M 样本。 - **结果**：作者报告多任务优于所比方法，尤其文本到音频与音乐。 - **实验条件**：本档使用 v3 数据口径；任意模态组合和生产可控性需查完整实验。 - **研究线**：扩展为跨模态的声音生成平台。 阅读：Abstract（完整摘要）。 ### 2025 · [FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation](https://arxiv.org/abs/2505.24714) ACL 2025 - **问题**：通用多模态评测不足以反映高知识密度金融报告与图表分析的要求。 - **方法**：构建逾 1.1 万金融样本，覆盖 18 个领域、6 类资产、10 类主要图表与 21 个子类；20 名标注者参与验证。FinScore 纳入幻觉惩罚和领域归一化。 - **结果**：评测 6 个专有和 11 个开源模型；引言报告领先模型总体表现仅略高于 50%，不同提示下预测标准差低于 1%。 - **实验条件**：主要是选择题和计算题，无法完整刻画现实分析流程；复杂概念可能留下标注偏差。尚未覆盖音视频、实时数据和噪声输入。评测分数不代表真实投资回报或金融决策效用。 - **研究线**：为其金融数据科学方向提供具体证据，贡献是领域数据与诊断评测，和音乐生成、生命科学表示形成多应用并行。 阅读：Abstract（完整）；1 Introduction（完整）；6 Conclusion（完整）；Limitations（完整）。 ## 2024–2026 论文目录 ### 2026 - [A Control Theory of Predictability in Latent World Models](https://doi.org/10.48550/ARXIV.2607.10362)。[CoRR](https://dblp.org/rec/journals/corr/abs-2607-10362) - [A Physics-guided Fine-tuned LLM-based Framework for Customized Power Distribution System Feeder Generation](https://doi.org/10.48550/ARXIV.2607.07237)。[CoRR](https://dblp.org/rec/journals/corr/abs-2607-07237) - [A Theory of Reliable Self-Evolution for Agent Harnesses](https://doi.org/10.48550/ARXIV.2609.08175)。[CoRR](https://dblp.org/rec/journals/corr/abs-2609-08175) - [ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing](https://doi.org/10.18653/V1/2026.FINDINGS-ACL.1718)。[ACL (Findings)](https://dblp.org/rec/conf/acl/ChenXG26) - [Adaptive weighted disentangling variational autoencoder with fine-grained feedback](https://doi.org/10.1016/J.ENGAPPAI.2026.114623)。[Eng. Appl. Artif. Intell.](https://dblp.org/rec/journals/eaai/YuLLYGLW26) - [AI Alignment: A Contemporary Survey](https://doi.org/10.1145/3770749)。[ACM Comput. Surv.](https://dblp.org/rec/journals/csur/JiQCZZHLWDHVZZDPXONTFMW26) - [AM3Safety: Towards Data Efficient Alignment of Multi-modal Multi-turn Safety for MLLMs](https://doi.org/10.48550/ARXIV.2601.04736)。[CoRR](https://dblp.org/rec/journals/corr/abs-2601-04736) - [Attention Hijacking: Response Manipulation Across Queries in Vision-Language Models](https://doi.org/10.48550/ARXIV.2605.17310)。[CoRR](https://dblp.org/rec/journals/corr/abs-2605-17310) - [Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing](https://doi.org/10.1145/3799902.3811191)。[SIGGRAPH (Conference Paper Track)](https://dblp.org/rec/conf/siggraph/TianYLZYYCLLXG26) - [AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio Generation](https://doi.org/10.48550/ARXIV.2606.12555)。[CoRR](https://dblp.org/rec/journals/corr/abs-2606-12555) - [AudioX: A Unified Framework for Anything-to-Audio Generation](https://proceedings.iclr.cc/paper_files/paper/2026/hash/b36dc39b319ba6ba2a0fd7601951efb4-Abstract-Conference.html)。[ICLR](https://dblp.org/rec/conf/iclr/TianLJYXTCXG26) - [Benchmarking Fine-Grained Error Detection in Multimodal Reasoning](https://doi.org/10.18653/V1/2026.ACL-LONG.2068)。[ACL (1)](https://dblp.org/rec/conf/acl/ChanZJJDXHG26) - [Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs](https://doi.org/10.18653/V1/2026.ACL-LONG.1020)。[ACL (1)](https://dblp.org/rec/conf/acl/XuGLWLLZYLHG26) - [BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook](https://doi.org/10.18653/V1/2026.ACL-LONG.1066)。[ACL (1)](https://dblp.org/rec/conf/acl/GuLWWWLLZHG26) - [Can Coding Agents Solve Repository-Level Issues with Rendered Code? An Exploratory Study of Visual Representations](https://doi.org/10.48550/ARXIV.2608.09268)。[CoRR](https://dblp.org/rec/journals/corr/abs-2608-09268) - [CareerCraft: Supporting New Graduates on Job Hunting with LLM-Assisted Self-Construction of Career Profile](https://doi.org/10.1145/3772318.3791221)。[CHI](https://dblp.org/rec/conf/chi/QiLLKHG26) - [CaveAgent: Transforming LLMs into Stateful Runtime Operators](https://doi.org/10.48550/ARXIV.2601.01569)。[CoRR](https://dblp.org/rec/journals/corr/abs-2601-01569) - [ClawNet: Human-Symbiotic Agent Network for Cross-User Autonomous Cooperation](https://doi.org/10.48550/ARXIV.2604.19211)。[CoRR](https://dblp.org/rec/journals/corr/abs-2604-19211) - [CoBrush: A Hierarchical Planning Framework for Human-Robot Co-Painting](https://doi.org/10.48550/ARXIV.2609.35476)。[CoRR](https://dblp.org/rec/journals/corr/abs-2609-35476) - [CoCoGesture: Towards coherent co-speech 3D gesture generation in the wild](https://doi.org/10.1016/J.INFFUS.2025.103613)。[Inf. Fusion](https://dblp.org/rec/journals/inffus/QiZWPLSXZHLG26) - [CogniEdit: Dense Gradient Flow Optimization for Fine-Grained Image Editing](https://openaccess.thecvf.com/content/CVPR2026/html/Li_CogniEdit_Dense_Gradient_Flow_Optimization_for_Fine-Grained_Image_Editing_CVPR_2026_paper.html)。[CVPR](https://dblp.org/rec/conf/cvpr/LiLZXLGT26) - [Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models](https://doi.org/10.48550/ARXIV.2604.10219)。[CoRR](https://dblp.org/rec/journals/corr/abs-2604-10219) - [Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment](https://doi.org/10.48550/ARXIV.2605.20834)。[CoRR](https://dblp.org/rec/journals/corr/abs-2605-20834) - [Crisis-Bench: Benchmarking Strategic Ambiguity and Reputation Management in Large Language Models](https://doi.org/10.48550/ARXIV.2601.05570)。[CoRR](https://dblp.org/rec/journals/corr/abs-2601-05570) - [Data-Efficient Brushstroke Generation with Diffusion Models for Oil Painting](https://doi.org/10.1145/3822182)。[ACM Trans. Multim. Comput. Commun. Appl.](https://dblp.org/rec/journals/tomccap/QinBYZGW26) - [DC-W2S: Dual-Consensus Weak-to-Strong Training for Reliable Process Reward Modeling in Biological Reasoning](https://doi.org/10.48550/ARXIV.2603.08095)。[CoRR](https://dblp.org/rec/journals/corr/abs-2603-08095) - [Discovering physical laws with parallel symbolic enumeration](https://doi.org/10.1038/S43588-025-00904-8)。[Nat. Comput. Sci.](https://dblp.org/rec/journals/ncs/RuanXGLGWS26) - [DreamVideo-Omni: Omni-Motion Controlled Multi-Subject Video Customization with Latent Identity Reinforcement Learning](https://doi.org/10.48550/ARXIV.2603.12257)。[CoRR](https://dblp.org/rec/journals/corr/abs-2603-12257) - [Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement](https://doi.org/10.48550/ARXIV.2608.03733)。[CoRR](https://dblp.org/rec/journals/corr/abs-2608-03733) - [From Weights to Features: SAE-Guided Activation Regularization for LLM Continual Learning](https://doi.org/10.48550/ARXIV.2606.26629)。[CoRR](https://dblp.org/rec/journals/corr/abs-2606-26629) - [Glance-or-Gaze: Incentivizing LMMs to Adaptively Focus Search via Reinforcement Learning](https://doi.org/10.18653/V1/2026.FINDINGS-ACL.1700)。[ACL (Findings)](https://dblp.org/rec/conf/acl/BaiZWCWPHG26) - [HAGD: Hierarchical Anatomical-Guided Diffusion for Synthetic CT Generation from CBCT](https://doi.org/10.1109/ISBI61048.2026.11515500)。[ISBI](https://dblp.org/rec/conf/isbi/GuoLHZD26) - [HelixWorld: A Real-time Interactive Audio-Visual World Model](https://doi.org/10.48550/ARXIV.2609.38123)。[CoRR](https://dblp.org/rec/journals/corr/abs-2609-38123) - [HiPrompt: Tuning-free Higher-Resolution Generation with Hierarchical MLLM Prompts](https://doi.org/10.1007/S11263-026-02736-Z)。[Int. J. Comput. Vis.](https://dblp.org/rec/journals/ijcv/LiuHGLJLCXLLG26) - [HOMIE: Human-object Centric Video Personalization via Multimodal Intelligent Enhancement](https://doi.org/10.48550/ARXIV.2607.18217)。[CoRR](https://dblp.org/rec/journals/corr/abs-2607-18217) - [Improving Model Fusion by Training-Time Neuron Alignment With Fixed Neuron Anchors](https://doi.org/10.1109/TPAMI.2025.3624314)。[IEEE Trans. Pattern Anal. Mach. Intell.](https://dblp.org/rec/journals/pami/LiLLSXGLW26) - [IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference](https://doi.org/10.48550/ARXIV.2605.25475)。[CoRR](https://dblp.org/rec/journals/corr/abs-2605-25475) - [Inference-time Scaling for Diffusion-based Audio Super-resolution](https://doi.org/10.1609/AAAI.V40I17.38520)。[AAAI](https://dblp.org/rec/conf/aaai/JinYTLKGX26) - [InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents](https://doi.org/10.18653/V1/2026.FINDINGS-ACL.1729)。[ACL (Findings)](https://dblp.org/rec/conf/acl/ZhuSCLCCHG26) - [Learning While Staying Curious: Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models](https://doi.org/10.18653/V1/2026.ACL-LONG.617)。[ACL (1)](https://dblp.org/rec/conf/acl/WangGPGYYHGW26) - [LeCor: Learning to Be Corrected by Meta-Learned Test-Time Training for Interactive 3D Lung-Tumour Segmentation](https://doi.org/10.48550/ARXIV.2609.09477)。[CoRR](https://dblp.org/rec/journals/corr/abs-2609-09477) - [LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents](https://doi.org/10.48550/ARXIV.2609.09754)。[CoRR](https://dblp.org/rec/journals/corr/abs-2609-09754) - [Life Operators: a self-evolving framework for multiscale life modelling](https://doi.org/10.48550/ARXIV.2609.00068)。[CoRR](https://dblp.org/rec/journals/corr/abs-2609-00068) - [Lighthouse: A Self-Reconfiguring Sociotechnical Infrastructure for the Unforeseen Long-Tail of Urban Crisis](https://doi.org/10.1145/3772363.3798644)。[CHI Extended Abstracts](https://dblp.org/rec/conf/chi/DengZZXG26) - [LRAS: Advanced Legal Reasoning with Agentic Search](https://doi.org/10.48550/ARXIV.2601.07296)。[CoRR](https://dblp.org/rec/journals/corr/abs-2601-07296) - [LUNA: Learning Universal 3D Human Animation Beyond Skinning](https://doi.org/10.48550/ARXIV.2606.31981)。[CoRR](https://dblp.org/rec/journals/corr/abs-2606-31981) - [MD-VAE: Concepts embedded variational autoencoder with multiple decoders](https://doi.org/10.1007/S10489-026-07435-3)。[Appl. Intell.](https://dblp.org/rec/journals/apin/LiuLLWGLW26) - [MemFly: On-the-Fly Memory Optimization via Information Bottleneck](https://doi.org/10.48550/ARXIV.2602.07885)。[CoRR](https://dblp.org/rec/journals/corr/abs-2602-07885) - [Modeling the Brain's Grammar: ROI-Guided fMRI Pretraining for Transferable and Interpretable Vision Decoding](https://openaccess.thecvf.com/content/CVPR2026/html/Liu_Modeling_the_Brains_Grammar_ROI-Guided_fMRI_Pretraining_for_Transferable_and_CVPR_2026_paper.html)。[CVPR](https://dblp.org/rec/conf/cvpr/LiuXCJHG26) - [MOSS: Self-Evolution through Source-Level Rewriting in Autonomous Agent Systems](https://doi.org/10.48550/ARXIV.2605.22794)。[CoRR](https://dblp.org/rec/journals/corr/abs-2605-22794) - [NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation](https://doi.org/10.48550/ARXIV.2605.10813)。[CoRR](https://dblp.org/rec/journals/corr/abs-2605-10813) - [Not Just the Destination, But the Journey: Reasoning Traces Causally Shape Generalization Behaviors](https://doi.org/10.48550/ARXIV.2603.12397)。[CoRR](https://dblp.org/rec/journals/corr/abs-2603-12397) - [NVBench: A Benchmark for Speech Synthesis with Non-Verbal Vocalizations](https://doi.org/10.48550/ARXIV.2604.16211)。[CoRR](https://dblp.org/rec/journals/corr/abs-2604-16211) - [Omni-RewardBench: Toward a Comprehensive Evaluation of Generative Reward Models Across Modalities](https://doi.org/10.18653/V1/2026.ACL-LONG.636)。[ACL (1)](https://dblp.org/rec/conf/acl/ChanZWYJDXHG26) - [OMP-MoE: Efficient Expert Pruning for Mixture-of-Experts LLMs via Orthogonal Matching Pursuit](https://doi.org/10.48550/ARXIV.2609.31631)。[CoRR](https://dblp.org/rec/journals/corr/abs-2609-31631) - [On-device large language models: a survey of model compression and system optimization](https://doi.org/10.1007/S10462-026-11538-1)。[Artif. Intell. Rev.](https://dblp.org/rec/journals/air/ChenWZSJZWZZWLHWLHCLLML26) - [Operation-Mechanism Alignment for Reliable Clinical Reasoning over Electronic Health Records](https://doi.org/10.18653/V1/2026.BIONLP-1.48)。[BioNLP@ACL](https://dblp.org/rec/conf/bionlp/TaoWXTJSMCGGZGG26) - [Outlier Matters: Efficient Long-to-Short Reasoning via Outlier-Guided Model Merging](https://doi.org/10.1609/AAAI.V40I41.40828)。[AAAI](https://dblp.org/rec/conf/aaai/ZhuLLQLGXHG26) - [PASTABench: Proactive Assessment of Sequential Trajectories for Agent Safety](https://doi.org/10.48550/ARXIV.2609.28197)。[CoRR](https://dblp.org/rec/journals/corr/abs-2609-28197) - [Pixel-Perfect Puppetry: Precision-Guided Enhancement for Face Image and Video Editing](https://proceedings.iclr.cc/paper_files/paper/2026/hash/f54bd48aba0dff7acdac86123188f1b6-Abstract-Conference.html)。[ICLR](https://dblp.org/rec/conf/iclr/LiWLXLG26) - [Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification](https://doi.org/10.48550/ARXIV.2601.22642)。[CoRR](https://dblp.org/rec/journals/corr/abs-2601-22642) - [QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training-Inference Mismatch](https://doi.org/10.18653/V1/2026.FINDINGS-ACL.841)。[ACL (Findings)](https://dblp.org/rec/conf/acl/GuWLLZLXWYLHG26) - [ReBind: Multi-Reference Video Editing via Structured Instructions with Explicit Reference Relationships](https://doi.org/10.48550/ARXIV.2607.14681)。[CoRR](https://dblp.org/rec/journals/corr/abs-2607-14681) - [Reimagining Legal Fact Verification with GenAI: Toward Effective Human-AI Collaboration](https://doi.org/10.1145/3772318.3791088)。[CHI](https://dblp.org/rec/conf/chi/HanZHLLG26) - [Reinforcement Learning of Large Language Models for Interpretable Credit Card Fraud Detection](https://doi.org/10.48550/ARXIV.2601.05578)。[CoRR](https://dblp.org/rec/journals/corr/abs-2601-05578) - [RW-TTT: Batched Serving for Request-Owned Test-Time Training State](https://doi.org/10.48550/ARXIV.2605.28053)。[CoRR](https://dblp.org/rec/journals/corr/abs-2605-28053) - [SafeMT: Multi-turn Safety for Multimodal Language Models](https://doi.org/10.18653/V1/2026.ACL-LONG.1920)。[ACL (1)](https://dblp.org/rec/conf/acl/ZhuDJLCWCCYHG26) - [Scale-Aware Curriculum Learning for Data-Efficient Lung Nodule Detection with YOLOV11](https://doi.org/10.1109/ISBI61048.2026.11515949)。[ISBI](https://dblp.org/rec/conf/isbi/LuoGHZD26) - [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://doi.org/10.48550/ARXIV.2608.31075)。[CoRR](https://dblp.org/rec/journals/corr/abs-2608-31075) - [Scaling Multi-Hop Training Data via Graph-Constrained Path Selection](https://doi.org/10.48550/ARXIV.2605.31238)。[CoRR](https://dblp.org/rec/journals/corr/abs-2605-31238) - [Self-Evolving Deep Research via Joint Generation and Evaluation](https://doi.org/10.48550/ARXIV.2606.04507)。[CoRR](https://dblp.org/rec/journals/corr/abs-2606-04507) - [Semantic Voting: A Self-Evaluation-Free Approach for Efficient LLM Self-Improvement on Unverifiable Open-ended Tasks](https://proceedings.iclr.cc/paper_files/paper/2026/hash/3db3e1f192877e47bf48c93cae238e51-Abstract-Conference.html)。[ICLR](https://dblp.org/rec/conf/iclr/JiangZCCLCXG26) - [SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent](https://doi.org/10.48550/ARXIV.2608.07449)。[CoRR](https://dblp.org/rec/journals/corr/abs-2608-07449) - [Sparse Adapter Fusion for Continual Learning in NLP](https://doi.org/10.18653/V1/2026.EACL-LONG.37)。[EACL (Volume 1: Long Papers)](https://dblp.org/rec/conf/eacl/ZengCYG26) - [Spatiotemporal Graph Learning with Direct Volumetric Information Passing and Feature Enhancement](https://doi.org/10.1145/3770854.3780155)。[KDD (1)](https://dblp.org/rec/conf/kdd/MiWHGWLS26) - [SqueezeComposer: Temporal Speed-up is A Simple Trick for Long-form Music Composing](https://doi.org/10.48550/ARXIV.2603.21073)。[CoRR](https://dblp.org/rec/journals/corr/abs-2603-21073) - [Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging](https://doi.org/10.1609/AAAI.V40I27.39464)。[AAAI](https://dblp.org/rec/conf/aaai/LiZWQLGHG26) - [TTHE: Test-Time Harness Evolution](https://doi.org/10.48550/ARXIV.2607.08124)。[CoRR](https://dblp.org/rec/journals/corr/abs-2607-08124) - [UniSAE: Unified Speech Attribute Editing on Speaker, Emotion and Low-Level Content via Discrete Phonetic Posteriorgram Modelling](https://doi.org/10.48550/ARXIV.2606.31128)。[CoRR](https://dblp.org/rec/journals/corr/abs-2606-31128) - [UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass](https://openaccess.thecvf.com/content/CVPR2026/html/Li_UniSH_Unifying_Scene_and_Human_Reconstruction_in_a_Feed-Forward_Pass_CVPR_2026_paper.html)。[CVPR](https://dblp.org/rec/conf/cvpr/LiLZLZXLPZLLG26) - [UniSS: Unified Expressive Speech-to-Speech Translation with Your Voice](https://proceedings.iclr.cc/paper_files/paper/2026/hash/c29fc04c339cd91b89b70dfe4b6d0fc0-Abstract-Conference.html)。[ICLR](https://dblp.org/rec/conf/iclr/ChengBWYCYGX26) - [UniVerse: Benchmarking and Enhancing LALMs on Culturally Inclusive Low-Resource Music Understanding](https://doi.org/10.48550/ARXIV.2608.17852)。[CoRR](https://dblp.org/rec/journals/corr/abs-2608-17852) - [VizoMem: A Visual-Textual Memory Framework for Efficient Long-Horizon Reasoning](https://doi.org/10.18653/V1/2026.FINDINGS-ACL.365)。[ACL (Findings)](https://dblp.org/rec/conf/acl/LiangSCCHG26) - [When Slower Isn't Truer: Inverse Scaling Law of Truthfulness in Multimodal Reasoning](https://doi.org/10.18653/V1/2026.FINDINGS-ACL.63)。[ACL (Findings)](https://dblp.org/rec/conf/acl/FangCLWCHDGYJ26) - [When Text Hijacks Vision: Benchmarking and Mitigating Text Overlay-Induced Hallucination in Vision Language Models](https://doi.org/10.48550/ARXIV.2604.17375)。[CoRR](https://dblp.org/rec/journals/corr/abs-2604-17375) - [Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test](https://doi.org/10.48550/ARXIV.2601.04137)。[CoRR](https://dblp.org/rec/journals/corr/abs-2601-04137) - [YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality](https://doi.org/10.48550/ARXIV.2609.33757)。[CoRR](https://dblp.org/rec/journals/corr/abs-2609-33757) - [YuE: Scaling Open Foundation Models for Long-Form Music Generation](https://proceedings.iclr.cc/paper_files/paper/2026/hash/a6a21421022d1da16eadbba533980530-Abstract-Conference.html)。[ICLR](https://dblp.org/rec/conf/iclr/YuanLGZPZLLMDDY26) - [Zero2Skill: Bootstrapping Robot Skills through Autonomous Data Collection, Training, and Deployment](https://doi.org/10.48550/ARXIV.2607.14047)。[CoRR](https://dblp.org/rec/journals/corr/abs-2607-14047) ### 2025 - [$ \tt {zkFL}$zkFL: Zero-Knowledge Proof-Based Gradient Aggregation for Federated Learning](https://doi.org/10.1109/TBDATA.2024.3403370)。[IEEE Trans. Big Data](https://dblp.org/rec/journals/tbd/WangDSKG25) - [A Survey of Reasoning with Foundation Models: Concepts, Methodologies, and Outlook](https://doi.org/10.1145/3729218)。[ACM Comput. Surv.](https://dblp.org/rec/journals/csur/SunZXLCQXDLGWWCYRFHYLLL25) - [A Systematic Comparison of Horizontal Federated Learning Algorithm Based on Random Forests in a Medical Setting](https://doi.org/10.1007/S11633-023-1489-6)。[Int. J. Autom. Comput.](https://dblp.org/rec/journals/ijautcomp/ChengZSGG25) - [AI Deception: Risks, Dynamics, and Controls](https://doi.org/10.48550/ARXIV.2511.22619)。[CoRR](https://dblp.org/rec/journals/corr/abs-2511-22619) - [AIRA: Activation-Informed Low-Rank Adaptation for Large Models](https://doi.org/10.1109/ICCV51701.2025.00169)。[ICCV](https://dblp.org/rec/conf/iccv/LiLLLXHG25) - [AttnZero: Efficient Attention Discovery for Vision Transformers](https://doi.org/10.1007/978-3-031-72652-1_2)。[ECCV (5)](https://dblp.org/rec/conf/eccv/LiWDLXLG24) - [Audio-FLAN: A Preliminary Release](https://doi.org/10.48550/ARXIV.2502.16584)。[CoRR](https://dblp.org/rec/journals/corr/abs-2502-16584) - [AudioX: Diffusion Transformer for Anything-to-Audio Generation](https://doi.org/10.48550/ARXIV.2503.10522)。[CoRR](https://dblp.org/rec/journals/corr/abs-2503-10522) - [Auto-GAS: Automated Proxy Discovery for Training-Free Generative Architecture Search](https://doi.org/10.1007/978-3-031-72652-1_3)。[ECCV (5)](https://dblp.org/rec/conf/eccv/LiSLDLXLG24) - [Automate Strategy Finding with LLM in Quant Investment](https://doi.org/10.18653/V1/2025.FINDINGS-EMNLP.1005)。[EMNLP (Findings)](https://dblp.org/rec/conf/emnlp/KouYLPLLDCHG25) - [BayesKD: Bayesian Knowledge Distillation for Compact LLMs in Constrained Fine-tuning Scenarios](https://doi.org/10.18653/V1/2025.FINDINGS-ACL.7)。[ACL (Findings)](https://dblp.org/rec/conf/acl/Li0LSZXG25) - [Benchmarking Multi-National Value Alignment for Large Language Models](https://doi.org/10.18653/V1/2025.FINDINGS-ACL.1028)。[ACL (Findings)](https://dblp.org/rec/conf/acl/JuSLJZZ00HG25) - [Boosting Policy and Process Reward Models with Monte Carlo Tree Search in Open-Domain QA](https://doi.org/10.18653/V1/2025.FINDINGS-ACL.388)。[ACL (Findings)](https://dblp.org/rec/conf/acl/ChanXZJHWJY0XHG25) - [Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation](https://openreview.net/forum?id=qPx3i9sMxv)。[ICLR](https://dblp.org/rec/conf/iclr/SunCLYL0XG25) - [CMD: Controllable Multiview Diffusion for 3D Editing and Progressive Generation](https://doi.org/10.1145/3721238.3730722)。[SIGGRAPH (Conference Paper Track)](https://dblp.org/rec/conf/siggraph/LiMC000LS0G25) - [Co3Gesture: Towards Coherent Concurrent Co-speech 3D Gesture Generation with Interactive Diffusion](https://openreview.net/forum?id=VaowElpVzd)。[ICLR](https://dblp.org/rec/conf/iclr/QiWZPXZLLG25) - [CoDe-NeRF: Neural Rendering via Dynamic Coefficient Decomposition](https://doi.org/10.48550/ARXIV.2508.06632)。[CoRR](https://dblp.org/rec/journals/corr/abs-2508-06632) - [Codec Does Matter: Exploring the Semantic Shortcoming of Codec for Audio Language Model](https://doi.org/10.1609/AAAI.V39I24.34761)。[AAAI](https://dblp.org/rec/conf/aaai/YeSL00DKCPLGX25) - [Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction](https://doi.org/10.1145/3690624.3709244)。[KDD (1)](https://dblp.org/rec/conf/kdd/MiRX00GWSL25) - [Construction and Application of the "One Map" for Natural Resource Construction Land](https://doi.org/10.1145/3778265.3778267)。[BDSIC](https://dblp.org/rec/conf/bdsic/MengYLGZL25) - [Deep Learning Surrogate Models of JULES-INFERNO for Wildfire Prediction on a Global Scale](https://doi.org/10.1109/TETCI.2024.3445450)。[IEEE Trans. Emerg. Top. Comput. Intell.](https://dblp.org/rec/journals/tetci/ChengCKGA25) - [Delta Decompression for MoE-based LLMs Compression](https://proceedings.mlr.press/v267/gu25c.html)。[ICML](https://dblp.org/rec/conf/icml/GuL0ZLS0G25) - [Dynamic link prediction: Using language models and graph structures for temporal knowledge graph completion with emerging entities and relations](https://doi.org/10.1016/J.ESWA.2025.126648)。[Expert Syst. Appl.](https://dblp.org/rec/journals/eswa/OngSGS25) - [Efficient Fine-Tuning of Large Models Via Nested Low-Rank Adaptation](https://doi.org/10.1109/ICCV51701.2025.02066)。[ICCV](https://dblp.org/rec/conf/iccv/LiLLHLWZXHG25) - [Empowering World Models with Reflection for Embodied Video Prediction](https://proceedings.mlr.press/v267/chi25b.html)。[ICML](https://dblp.org/rec/conf/icml/ChiFZQZCC0LZG25) - [Every Angle is Worth a Second Glance: Mining Kinematic Skeletal Structures From Multi-View Joint Cloud](https://doi.org/10.1109/TVCG.2025.3542442)。[IEEE Trans. Vis. Comput. Graph.](https://dblp.org/rec/journals/tvcg/JiangCACXG25) - [FinMME: Benchmark Dataset for Financial Multi-Modal Reasoning Evaluation](https://doi.org/10.18653/V1/2025.ACL-LONG.1426)。[ACL (1)](https://dblp.org/rec/conf/acl/0002KY0H0PLJLHZ25) - [Fire-Image-DenseNet (FIDN) for predicting wildfire burnt area using remote sensing data](https://doi.org/10.1016/J.CAGEO.2024.105783)。[Comput. Geosci.](https://dblp.org/rec/journals/gandc/PangCHJGPHA25) - [Foundation Cures Personalization: Improving Personalized Models' Prompt Consistency via Hidden Foundation Knowledge](http://papers.nips.cc/paper_files/paper/2025/hash/12fa90b384f16f08738e4c6564008b07-Abstract-Conference.html)。[NeurIPS](https://dblp.org/rec/conf/nips/CaiJLJXGL25) - [From Perception to Cognition: A Survey of Vision-Language Interactive Reasoning in Multimodal Large Language Models](https://doi.org/10.48550/ARXIV.2509.25373)。[CoRR](https://dblp.org/rec/journals/corr/abs-2509-25373) - [Generalized Multi-agent Social Simulation Framework](https://doi.org/10.48550/ARXIV.2510.06225)。[CoRR](https://dblp.org/rec/journals/corr/abs-2510-06225) - [Generative RLHF-V: Learning Principles from Multi-modal Human Preference](http://papers.nips.cc/paper_files/paper/2025/hash/b76105b94a8c1286c860ad885ec588f1-Abstract-Conference.html)。[NeurIPS](https://dblp.org/rec/conf/nips/ZhouJCSCHHGY25) - [Graceful Forgetting in Generative Language Models](https://doi.org/10.18653/V1/2025.EMNLP-MAIN.666)。[EMNLP](https://dblp.org/rec/conf/emnlp/JiangCCLXG25) - [HKGAI-V1: Towards Regional Sovereign Large Language Model for Hong Kong](https://doi.org/10.48550/ARXIV.2507.11502)。[CoRR](https://dblp.org/rec/journals/corr/abs-2507-11502) - [Importance Weighting Can Help Large Language Models Self-Improve](https://doi.org/10.1609/AAAI.V39I23.34602)。[AAAI](https://dblp.org/rec/conf/aaai/JiangCXLG25) - [InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback](http://papers.nips.cc/paper_files/paper/2025/hash/8eb88844dafefa92a26aaec9f3acad93-Abstract-Datasets_and_Benchmarks_Track.html)。[NeurIPS](https://dblp.org/rec/conf/nips/ChenHJZDZWDWCZL25) - [Intuitively interpreting GANs latent space using semantic distribution](https://doi.org/10.1016/J.KNOSYS.2024.112894)。[Knowl. Based Syst.](https://dblp.org/rec/journals/kbs/WangWGLLG25) - [J1: Exploring Simple Test-Time Scaling for LLM-as-a-Judge](https://doi.org/10.48550/ARXIV.2505.11875)。[CoRR](https://dblp.org/rec/journals/corr/abs-2505-11875) - [Learning spatiotemporal dynamics from sparse data via a high-order physics-encoded network](https://doi.org/10.1016/J.CPC.2025.109582)。[Comput. Phys. Commun.](https://dblp.org/rec/journals/cphysics/RenSRWGSL25) - [Learning-based Artificial Intelligence Artwork: Methodology Taxonomy and Quality Evaluation](https://doi.org/10.1145/3698105)。[ACM Comput. Surv.](https://dblp.org/rec/journals/csur/WangDYGCKGW25) - [LegalReasoner: Step-wised Verification-Correction for Legal Judgment Reasoning](https://doi.org/10.18653/V1/2025.ACL-LONG.361)。[ACL (1)](https://dblp.org/rec/conf/acl/ShiZJ0ZZZXHG25) - [Llasa: Scaling Train-Time and Inference-Time Compute for Llama-based Speech Synthesis](https://doi.org/10.48550/ARXIV.2502.04128)。[CoRR](https://dblp.org/rec/journals/corr/abs-2502-04128) - [LLM-powered Document Analysis and Application in Natural Resources](https://doi.org/10.1145/3778265.3778275)。[BDSIC](https://dblp.org/rec/conf/bdsic/MengLYGX25) - [Machine learning for modelling unstructured grid data in computational physics: A review](https://doi.org/10.1016/J.INFFUS.2025.103255)。[Inf. Fusion](https://dblp.org/rec/journals/inffus/ChengBDFFFGJLLMPPCSWXXZ25) - [MDFCL: Multimodal data fusion-based graph contrastive learning framework for molecular property prediction](https://doi.org/10.1016/J.PATCOG.2025.111463)。[Pattern Recognit.](https://dblp.org/rec/journals/pr/GongLLGW25) - [Measuring Hong Kong Massive Multi-Task Language Understanding](https://doi.org/10.48550/ARXIV.2505.02177)。[CoRR](https://dblp.org/rec/journals/corr/abs-2505-02177) - [MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data](https://doi.org/10.48550/ARXIV.2512.13297)。[CoRR](https://dblp.org/rec/journals/corr/abs-2512-13297) - [MIFS: An adaptive multipath information fused self-supervised framework for drug discovery](https://doi.org/10.1016/J.NEUNET.2024.107088)。[Neural Networks](https://dblp.org/rec/journals/nn/GongLHGW25) - [MinD: Unified Visual Imagination and Control via Hierarchical World Models](https://doi.org/10.48550/ARXIV.2506.18897)。[CoRR](https://dblp.org/rec/journals/corr/abs-2506-18897) - [Mitigating Deceptive Alignment via Self-Monitoring](https://doi.org/10.48550/ARXIV.2505.18807)。[CoRR](https://dblp.org/rec/journals/corr/abs-2505-18807) - [MoE-SVD: Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition](https://proceedings.mlr.press/v267/li25az.html)。[ICML](https://dblp.org/rec/conf/icml/Li0GHLSXG25) - [Multi-View Large Reconstruction Model via Geometry-Aware Positional Encoding and Attention](https://doi.org/10.1109/TVCG.2025.3572341)。[IEEE Trans. Vis. Comput. Graph.](https://dblp.org/rec/journals/tvcg/LiLLLLLLWG25) - [MultiGranDTI: an explainable multi-granularity representation framework for drug-target interaction prediction](https://doi.org/10.1007/S10489-024-05936-7)。[Appl. Intell.](https://dblp.org/rec/journals/apin/GongLHGW25) - [Multimodal Slice Interaction Network Enhanced by Transfer Learning for Precise Segmentation of Internal Gross Tumor Volume in Lung Cancer PET/CT Imaging](https://doi.org/10.48550/ARXIV.2509.22841)。[CoRR](https://dblp.org/rec/journals/corr/abs-2509-22841) - [Outlier-Aware Model Merging for Efficient Multitask Inference](https://doi.org/10.1145/3746027.3754894)。[ACM Multimedia](https://dblp.org/rec/conf/mm/Zhu0LLCXHG25) - [OVST: online video stabilization with two-stage training transformer](https://doi.org/10.1007/S00521-025-11494-X)。[Neural Comput. Appl.](https://dblp.org/rec/journals/nca/WuZZSYZQG25) - [PanoLAM: Large Avatar Model for Gaussian Full-Head Synthesis from One-shot Unposed Image](https://doi.org/10.48550/ARXIV.2509.07552)。[CoRR](https://dblp.org/rec/journals/corr/abs-2509-07552) - [Perception, Understanding and Reasoning, A Multimodal Benchmark for Video Fake News Detection](https://doi.org/10.48550/ARXIV.2510.24816)。[CoRR](https://dblp.org/rec/journals/corr/abs-2510-24816) - [PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference](https://doi.org/10.18653/V1/2025.ACL-LONG.1544)。[ACL (1)](https://dblp.org/rec/conf/acl/JiHZ0DZQZWLHG025) - [PSHuman: Photorealistic Single-image 3D Human Reconstruction using Cross-Scale Multiview Diffusion and Explicit Remeshing](https://openaccess.thecvf.com/content/CVPR2025/html/Li_PSHuman_Photorealistic_Single-image_3D_Human_Reconstruction_using_Cross-Scale_Multiview_Diffusion_CVPR_2025_paper.html)。[CVPR](https://dblp.org/rec/conf/cvpr/LiZLY0QCXCXLG25) - [PT-VAE: Variational autoencoder with prior concept transformation](https://doi.org/10.1016/J.NEUCOM.2025.130129)。[Neurocomputing](https://dblp.org/rec/journals/ijon/LiuLYYFGLW25) - [ReViSE: Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning](https://doi.org/10.48550/ARXIV.2512.09924)。[CoRR](https://dblp.org/rec/journals/corr/abs-2512-09924) - [Safe RLHF-V: Safe Reinforcement Learning from Human Feedback in Multimodal Large Language Models](https://doi.org/10.48550/ARXIV.2503.17682)。[CoRR](https://dblp.org/rec/journals/corr/abs-2503-17682) - [Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback](http://papers.nips.cc/paper_files/paper/2025/hash/41c51513dac7b42dea755ea484955604-Abstract-Conference.html)。[NeurIPS](https://dblp.org/rec/conf/nips/JiCPZLHCZWDCHGY25) - [SafeLawBench: Towards Safe Alignment of Large Language Models](https://doi.org/10.18653/V1/2025.FINDINGS-ACL.721)。[ACL (Findings)](https://dblp.org/rec/conf/acl/CaoZJSZWD0HG25) - [Scale-Aware Curriculum Learning for Ddata-Efficient Lung Nodule Detection with YOLOv11](https://doi.org/10.48550/ARXIV.2510.26923)。[CoRR](https://dblp.org/rec/journals/corr/abs-2510-26923) - [Scaling Decentralized Learning with Flock](https://doi.org/10.1109/WI-IAT67162.2025.00131)。[WI-IAT](https://dblp.org/rec/conf/webi/ChengSSG25) - [Scenario, Role, and Persona: A Scoping Review of Design Strategies for Socially Intelligent AI Agents](https://doi.org/10.1145/3706599.3719762)。[CHI Extended Abstracts](https://dblp.org/rec/conf/chi/NiuHPCLHG25) - [Spark-TTS: An Efficient LLM-Based Text-to-Speech Model with Single-Stream Decoupled Speech Tokens](https://doi.org/10.48550/ARXIV.2503.01710)。[CoRR](https://dblp.org/rec/journals/corr/abs-2503-01710) - [STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs](https://openreview.net/forum?id=6XUSDvBFkV)。[ICLR](https://dblp.org/rec/conf/iclr/Dong0ZDFCT0XG025) - [Supporting Data from: Physically Constrained Mass Spectrometry Data Binning for Multi-Platform Untargeted Metabolomics Data Integration](https://doi.org/10.5281/ZENODO.15251976)。[](https://dblp.org/rec/data/11/NganZKCZGYWYC25) - [Supporting Data from: Physically Constrained Mass Spectrometry Data Binning on Multi-Platform Untargeted Metabolomics Data Reveals Generic Biomarkers for Hepatocellular Carcinoma](https://doi.org/10.5281/ZENODO.14962746)。[](https://dblp.org/rec/data/11/NGANZKCZGYWYC25) - [Supporting Data from: Resolution-Adaptive Binning Enhances Machine Learning Modeling by Interbatch and Multiplatform Orbitrap-Based Shotgun Mass Spectrometry Data Integration](https://doi.org/10.5281/ZENODO.17170776)。[](https://dblp.org/rec/data/12/NganZKCZGYWYC25) - [Supporting Data from: Resolution-Adaptive Orbitrap Mass Spectrometry Data Binning for Multi-Platform Untargeted Metabolomics Data Integration](https://doi.org/10.5281/ZENODO.17076922)。[](https://dblp.org/rec/data/11/NganZKCZGYWYC25b) - [T3D: Advancing 3D Medical Vision-Language Pre-Training by Learning Multi-View Visual Consistency](https://doi.org/10.1109/ICCVW69036.2025.00698)。[ICCVW](https://dblp.org/rec/conf/iccv/LiuOCCMFGSBA25) - [Task-wrapped Continual Learning in Task-Oriented Dialogue Systems](https://doi.org/10.18653/V1/2025.FINDINGS-NAACL.174)。[NAACL (Findings)](https://dblp.org/rec/conf/naacl/ZengYCG25) - [The Mirage of Multimodality: Where Truth is Tested and Honesty Unravels](https://doi.org/10.48550/ARXIV.2505.20214)。[CoRR](https://dblp.org/rec/journals/corr/abs-2505-20214) - [ThinkPatterns-21k: A Systematic Study on the Impact of Thinking Patterns in LLMs](https://doi.org/10.48550/ARXIV.2503.12918)。[CoRR](https://dblp.org/rec/journals/corr/abs-2503-12918) - [Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving](https://doi.org/10.18653/V1/2025.EMNLP-MAIN.628)。[EMNLP](https://dblp.org/rec/conf/emnlp/CaoLDYZZSLHG25) - [VFX Creator: Animated Visual Effect Generation with Controllable Diffusion Transformer](https://doi.org/10.48550/ARXIV.2502.05979)。[CoRR](https://dblp.org/rec/journals/corr/abs-2502-05979) - [VidMuse: A Simple Video-to-Music Generation Framework with Long-Short-Term Modeling](https://openaccess.thecvf.com/content/CVPR2025/html/Tian_VidMuse_A_Simple_Video-to-Music_Generation_Framework_with_Long-Short-Term_Modeling_CVPR_2025_paper.html)。[CVPR](https://dblp.org/rec/conf/cvpr/Tian0YPL0CXG25) - [WoW: Towards a World omniscient World model Through Embodied Interaction](https://doi.org/10.48550/ARXIV.2509.22642)。[CoRR](https://dblp.org/rec/journals/corr/abs-2509-22642) ### 2024 - [AgentMonitor: A Plug-and-Play Framework for Predictive and Secure Multi-Agent Systems](https://doi.org/10.48550/ARXIV.2408.14972)。[CoRR](https://dblp.org/rec/journals/corr/abs-2408-14972) - [APK-MRL: An Adaptive Pre-training Framework with Knowledge-enhanced for Molecular Representation Learning](https://doi.org/10.1109/BIBM62325.2024.10821780)。[BIBM](https://dblp.org/rec/conf/bibm/GongLH0G024) - [Bayesian at heart: Towards autonomic outflow estimation via generative state-space modelling of heart rate dynamics](https://doi.org/10.1016/J.COMPBIOMED.2023.107857)。[Comput. Biol. Medicine](https://dblp.org/rec/journals/cbm/RosasCLGM24) - [Can LLMs "Reason" in Music? an Evaluation of LLMs' Capability of Music Understanding and Generation](https://doi.org/10.5281/ZENODO.14877281)。[ISMIR](https://dblp.org/rec/conf/ismir/ZhouWWZYMWBXG24) - [Causal inference in the medical domain: a survey](https://doi.org/10.1007/S10489-024-05338-9)。[Appl. Intell.](https://dblp.org/rec/journals/apin/WuPLZSLQLG24) - [ChatMusician: Understanding and Generating Music Intrinsically with LLM](https://doi.org/10.48550/ARXIV.2402.16153)。[CoRR](https://dblp.org/rec/journals/corr/abs-2402-16153) - [Combined Global and Local Information Diffusion of Neural Processes](https://doi.org/10.1007/978-3-031-72332-2_24)。[ICANN (1)](https://dblp.org/rec/conf/icann/TaiG24) - [COMOSVC: Consistency Model-Based Singing Voice Conversion](https://doi.org/10.1109/ISCSLP63861.2024.10800419)。[ISCSLP](https://dblp.org/rec/conf/iscslp/LuYX0LG24) - [ComposerX: Multi-Agent Symbolic Music Composition With LLMs](https://doi.org/10.5281/ZENODO.14877425)。[ISMIR](https://dblp.org/rec/conf/ismir/DengYYH0LTPZLLM24) - [DEA: Data-efficient augmentation for interpretable medical image segmentation](https://doi.org/10.1016/J.BSPC.2023.105748)。[Biomed. Signal Process. Control.](https://dblp.org/rec/journals/bspc/WuLTHCYZSLLG24) - [Design of Improved Artificial Intelligence Generative Dialogue Algorithm and Dialogue System Model Based on Knowledge Graph](https://doi.org/10.1109/ACCESS.2024.3430902)。[IEEE Access](https://dblp.org/rec/journals/access/Guo24a) - [DetKDS: Knowledge Distillation Search for Object Detectors](https://proceedings.mlr.press/v235/li24c.html)。[ICML](https://dblp.org/rec/conf/icml/LiBDYLLLXG24) - [Dirichlet Continual Learning: Tackling Catastrophic Forgetting in NLP](https://proceedings.mlr.press/v244/zeng24a.html)。[UAI](https://dblp.org/rec/conf/uai/ZengYXLG24) - [Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models](http://papers.nips.cc/paper_files/paper/2024/hash/ff997469ac66cf893c4183efeb22212a-Abstract-Conference.html)。[NeurIPS](https://dblp.org/rec/conf/nips/LiDTLWLXLCG24) - [Discovering symbolic expressions with parallelized tree search](https://doi.org/10.48550/ARXIV.2407.04405)。[CoRR](https://dblp.org/rec/journals/corr/abs-2407-04405) - [EDM: Synthetic Data from Exemplar Diffusion Model Improves Non-Communicable Diseases Detection](https://doi.org/10.1109/ICASSP48485.2024.10447799)。[ICASSP](https://dblp.org/rec/conf/icassp/WuLYQZSG24) - [Efficient deep data assimilation with sparse observations and time-varying sensors](https://doi.org/10.1016/J.JCP.2023.112581)。[J. Comput. Phys.](https://dblp.org/rec/journals/jcphy/ChengLGA24) - [Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention](http://papers.nips.cc/paper_files/paper/2024/hash/65a723bf7d8dad838c09178270d30e80-Abstract-Conference.html)。[NeurIPS](https://dblp.org/rec/conf/nips/LiLLZLLQZXLTWLG24) - [EVA: An Embodied World Model for Future Video Anticipation](https://doi.org/10.48550/ARXIV.2410.15461)。[CoRR](https://dblp.org/rec/journals/corr/abs-2410-15461) - [FastSAG: Towards Fast Non-Autoregressive Singing Accompaniment Generation](https://www.ijcai.org/proceedings/2024/843)。[IJCAI](https://dblp.org/rec/conf/ijcai/ChenX0YLG24) - [FedEL: Federated ensemble learning for non-iid data](https://doi.org/10.1016/J.ESWA.2023.121390)。[Expert Syst. Appl.](https://dblp.org/rec/journals/eswa/WuPHCYLQG24) - [FlashSpeech: Efficient Zero-Shot Speech Synthesis](https://doi.org/10.1145/3664647.3681044)。[ACM Multimedia](https://dblp.org/rec/conf/mm/YeJL0CLSPBHXLG24) - [Foundation Cures Personalization: Recovering Facial Personalized Models' Prompt Consistency](https://doi.org/10.48550/ARXIV.2411.15277)。[CoRR](https://dblp.org/rec/journals/corr/abs-2411-15277) - [Freeze the Backbones: a Parameter-Efficient Contrastive Approach to Robust Medical Vision-Language Pre-Training](https://doi.org/10.1109/ICASSP48485.2024.10447326)。[ICASSP](https://dblp.org/rec/conf/icassp/QinLCGA24) - [GNN-MgrPool: Enhanced graph neural networks with multi-granularity pooling for graph classification](https://doi.org/10.1016/J.INS.2024.120965)。[Inf. Sci.](https://dblp.org/rec/journals/isci/SunWLG24) - [Hierarchical Linear Symbolized Tree-Structured Neural Processes](https://doi.org/10.1145/3637528.3671861)。[KDD](https://dblp.org/rec/conf/kdd/TaiG24) - [Honest Computing: Achieving demonstrable data lineage and provenance for driving data and process-sensitive policies](https://doi.org/10.48550/ARXIV.2407.14390)。[CoRR](https://dblp.org/rec/journals/corr/abs-2407-14390) - [Improving disentanglement in variational auto-encoders via feature imbalance-informed dimension weighting](https://doi.org/10.1016/J.KNOSYS.2024.111818)。[Knowl. Based Syst.](https://dblp.org/rec/journals/kbs/LiuYLYYLGLW24) - [Labelling with dynamics: A data-efficient learning paradigm for medical image segmentation](https://doi.org/10.1016/J.MEDIA.2024.103196)。[Medical Image Anal.](https://dblp.org/rec/journals/mia/MoLYWZWPMHG24) - [LLMs Meet Multimodal Generation and Editing: A Survey](https://doi.org/10.48550/ARXIV.2405.19334)。[CoRR](https://dblp.org/rec/journals/corr/abs-2405-19334) - [M-LRM: Multi-view Large Reconstruction Model](https://doi.org/10.48550/ARXIV.2406.07648)。[CoRR](https://dblp.org/rec/journals/corr/abs-2406-07648) - [MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training](https://openreview.net/forum?id=w3YZ9MSlBu)。[ICLR](https://dblp.org/rec/conf/iclr/LiYZMCYXLRBGDLC24) - [MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions](https://doi.org/10.48550/ARXIV.2407.20962)。[CoRR](https://dblp.org/rec/journals/corr/abs-2407-20962) - [NoRA: Nested Low-Rank Adaptation for Efficient Fine-Tuning Large Models](https://doi.org/10.48550/ARXIV.2408.10280)。[CoRR](https://dblp.org/rec/journals/corr/abs-2408-10280) - [PSHuman: Photorealistic Single-view Human Reconstruction using Cross-Scale Diffusion](https://doi.org/10.48550/ARXIV.2409.10141)。[CoRR](https://dblp.org/rec/journals/corr/abs-2409-10141) - [PyramidCodec: Hierarchical Codec for Long-form Music Generation in Audio Domain](https://doi.org/10.18653/V1/2024.FINDINGS-EMNLP.246)。[EMNLP (Findings)](https://dblp.org/rec/conf/emnlp/ChenDY0LGX24) - [Real-time updating of dynamic social networks for COVID-19 vaccination strategies](https://doi.org/10.1007/S12652-023-04589-7)。[J. Ambient Intell. Humaniz. Comput.](https://dblp.org/rec/journals/jaihc/ChengPGA24) - [ReChoreoNet: Repertoire-based Dance Re-choreography with Music-conditioned Temporal and Style Clues](https://doi.org/10.1007/S11633-023-1478-9)。[Mach. Intell. Res.](https://dblp.org/rec/journals/ijautcomp/AuCJG24) - [RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generation](https://doi.org/10.48550/ARXIV.2404.00610)。[CoRR](https://dblp.org/rec/journals/corr/abs-2404-00610) - [SINGER: Vivid Audio-driven Singing Video Generation with Multi-scale Spectral Diffusion Model](https://doi.org/10.48550/ARXIV.2412.03430)。[CoRR](https://dblp.org/rec/journals/corr/abs-2412-03430) - [Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training](http://papers.nips.cc/paper_files/paper/2024/hash/143ea4a156ef64f32d4d905206cf32e1-Abstract-Conference.html)。[NeurIPS](https://dblp.org/rec/conf/nips/DuLQHSCG024) - [The potential and pitfalls of using a large language model such as ChatGPT, GPT-4, or LLaMA as a clinical assistant](https://doi.org/10.1093/JAMIA/OCAE184)。[J. Am. Medical Informatics Assoc.](https://dblp.org/rec/journals/jamia/ZhangSJFKTGGGGG24) - [Topology of Neural Processes](https://doi.org/10.1007/978-3-031-72332-2_25)。[ICANN (1)](https://dblp.org/rec/conf/icann/TaiG24a) - [Video-Instrument Synergistic Network for Referring Video Instrument Segmentation in Robotic Surgery](https://doi.org/10.1109/TMI.2024.3426953)。[IEEE Trans. Medical Imaging](https://dblp.org/rec/journals/tmi/WangYZQGXJZ24) - [Weakly-Supervised Emotion Transition Learning for Diverse 3D Co-Speech Gesture Generation](https://doi.org/10.1109/CVPR52733.2024.00992)。[CVPR](https://dblp.org/rec/conf/cvpr/QiPLYCLLXZLG24) - [You Know What I'm Saying: Jailbreak Attack via Implicit Reference](https://doi.org/10.48550/ARXIV.2410.03857)。[CoRR](https://dblp.org/rec/journals/corr/abs-2410-03857)