个人简介
李宇渊，杭州电子科技大学 通信工程学院 特聘副教授，2023年博士毕业于浙江大学 计算机学院，中国通信学会高级会员。主要研究方向为可信人工智能，面向大模型、推荐系统等场景，探索人工智能的安全、隐私、攻防、公平等问题。在AI三大会（ICML、NeurIPS、ICLR）和Cell子刊等国际会议和期刊发表论文30余篇。近年来担任多个国际顶级会议的领域主席或程序委员会委员，以及多个国际知名期刊的审稿人。与蚂蚁集团等企业合作，相关研究成果入选2024年世界人工智能大会“卓越人工智能引领者（SAIL）TOP30”榜单。 课题组长期招收硕博研究生和科研/开发实习生，欢迎对可信人工智能研究/开发感兴趣的同学与我邮件联系；基础较好的学生可推荐至浙江大学、达摩院进行联合培养。
教育经历
2018-09 至 2023-12，浙江大学，计算机科学与技术，博士 2017-09 至 2018-06，英国拉夫堡大学，计算机科学，公派交流 2014-09 至 2017-06，浙江工业大学，计算机科学与技术，学士
工作经历
2024-01 至 今，杭州电子科技大学 通信工程学院，特聘副教授
社会职务
期刊审稿：TKDE, IJCV, TOIS, TCSVT, TIST, TNNLS, ESWA, INS, KBS, EAAI, PR, NN 会议审稿： 2026: AAAI, ICLR (AC), WWW, CVPR, ICML, SIGIR, ACL, ECCV, KDD (AC), MM, NeurIPS (AC), CIKM 2025: AAAI, AISTATS, CVPR, CIKM, ICCV, ICLR, ICML, MM, NeurIPS, SIGIR, WWW 2024: AAAI, ACL, ICLR, ICML, IJCAI, KDD, MM, NeurIPS, WWW 2023: AAAI, ACL, ICML, IJCAI, KDD, MM, NeurIPS, SIGIR 2022: ECML PKDD, IJCAI, KDD, MM, NeurIPS
纵向科研
2026.01-2027.12，浙江省领雁计划项目“面向异构受限资源的大模型端边协同理论方法和关键技术研究”，课题负责人。 2025.09-2030.09，国家社会科学基金重点项目“人工智能大模型驱动的学术评价可信性增强机制与实现路径研究”，参与。 2025.01-2027.12，国家自然科学基金青年基金项目“面向隐私保护服务的多维度推荐逆学习方法研究”，主持。 2022.01-2025.12，国家自然科学基金面上项目“跨域推荐系统研究”，参与。 2019.07-2022.06，国家重点研发计划项目“大数据征信及智能评估技术”，参与。
论文
Zhifei Ren, Jiaming Zhang*, Xiaohua Feng, Yuyuan Li, Chaochao Chen. Deepfake-HMDE: Hierarchical Mixture of Deepfake Experts for Deepfake Detection. ICASSP 2026 (CCF-B). Fengyuan Yu, Xiaohua Feng, Yuyuan Li, Changwang Zhang, Jun Wang, Chaochao Chen*. Sharpness-Aware Minimization for Generalized Embedding Learning in Federated Recommendation. WWW 2026 (CCF-A). Jiaming Zhang, Yuyuan Li, Xiaohua Feng, Li Zhang, Longfei Li, Jun Zhou, Chaochao Chen*. Taming the Long Tail: Efficient Item-wise Sharpness-Aware Minimization for LLM-based Recommender Systems. WWW 2026 (CCF-A). Jianing Sun, Chenhao Xiong, Chunjie Zhai*, Yuyuan Li, Xiongding Liu, Chugiao Chen, Chenggang Yan, Yahong Chen. Adaptive Eco-Cooperative Adaptive Cruise Control for Heterogeneous Vehicle Platoons Using Online Identification-Informed Deep Reinforcement Learning. EAAI 2026 (SCI TOP).
Yuyuan Li, Xiaohua Feng, Chaochao Chen*, Qiang Yang. A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questions. TKDE 2025 (CCF-A). Naen Xu, Jinghuai Zhang, Changjiang Li, Hengyu An, Chunyi Zhou, Jun Wang, Boyu Xu, Yuyuan Li, Tianyu Du*, Shouling Ji. Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content? AAAI 2026 (CCF-A). Yuyuan Li, Junjie Fang, Fengyuan Yu, Xichun Sheng, Tianyu Du, Xuyang Teng, Shaowei Jiang, Linbo Jiang, Jianan Lin, Chaochao Chen*. FedAU2: Attribute Unlearning for User-Level Federated Recommender Systems with Adaptive and Robust Adversarial Training. AAAI 2026 (CCF-A). Shuo Shi, Jinghuai Zhang, Shijie Jiang, Chunyi Zhou, Yuyuan Li, Mengying Zhu, Yangyang Wu, Tianyu Du*. DP-GenG : Differentially Private Dataset Distillation Guided by DP-Generated Data. AAAI 2026 (CCF-A). Li Zhang, Zhongxuan Han, Xiaohua Feng, Jiaming Zhang, Yuyuan Li*, Linbo Jiang, Jianan Lin, Chaochao Chen. TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Models. AAAI 2026 (CCF-A). Chengye Wang, Yuyuan Li, XiaoHua Feng, Chaochao Chen, Xiaolin Zheng*, Jianwei Yin. UMU-Bench: Closing the Modality Gap in Multimodal Unlearning Evaluation. NeurIPS 2025 (CCF-A). Li Zhang, Zhongxuan Han, Chaochao Chen*, Xiaohua Feng, Jiaming Zhang, Yuyuan Li. FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning. NeurIPS 2025 (CCF-A). Zhongxuan Han, Li Zhang, Chaochao Chen*, Xiaolin Zheng, Yuyuan Li, Shuiguang Deng, Guanjie Cheng, Schahram Dustdar. Towards Fairness Exploration and Optimization for Digital Service Networks. TSC 2025 (CCF-A). Yuyuan Li, Yizhao Zhang, Weiming Liu, Xiaohua Feng, Zhongxuan Han, Chaochao Chen*, Chenggang Yan. Multi-Objective Unlearning in Recommender Systems via Preference Guided Efficient Pareto Exploration. TSC 2025 (CCF-A). Jiajie Su, Chaochao Chen, Yihao Wang, Weiming Liu, Yuyuan Li, Tao Wang, Zhigang Li, Xiaolin Zheng, Jianwei Yin. DuAda: Adaptive Targeted Model Poisoning Attack Framework via Dummy User Simulation on Federated Recommendation. TOIS 2025 (CCF-A). Fengyuan Yu, Yuyuan Li, Xiaohua Feng, Junjie Fang, Tao Wang, Chaochao Chen*. LEGO: A Lightweight and Efficient Multiple-Attribute Unlearning Framework for Recommender Systems. ACM MM 2025 (CCF-A). Yuyuan Li, Jiaming Zhang, Yixiu Liu, Chaochao Chen*.Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generation. KBS 2025 (SCI TOP). Shuwei Shi, Biao Gong, Xi Chen, Dandan Zheng, Shuai Tan, Zizheng Yang, Yuyuan Li, Jingwen He, Kecheng Zheng, Jingdong Chen, Ming Yang, Yinqiang Zheng. MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation. CVPR 2025 (CCF-A). Xiaohua Feng#, Yuyuan Li#, Chaochao Chen*, Li Zhang, Longfei Li, Jun Zhou, Xiaolin Zheng. Controllable Unlearning for Image-to-Image Generative Models via ϵ-Constrained Optimization. ICLR 2025 (CCF-A). Xiaohua Feng, Yuyuan Li*, Fengyuan Yu, Li Zhang, Chaochao Chen, Xiaolin Zheng. Plug and Play: Enabling Pluggable Attribute Unlearning in Recommender Systems. WWW 2025 (CCF-A). Chaochao Chen, Xiaohua Feng, Yuyuan Li, Lingjuan Lyu, Jun Zhou, Xiaolin Zheng*, Jianwei Yin*. Integration of Large Language Models and Federated Learning. Patterns 2024 (Cell子刊). Chaochao Chen, Yizhao Zhang, Yuyuan Li*, Jun Wang, Lianyong Qi, Xiaolong Xu, Xiaolin Zheng, Jianwei Yin. Post-Training Attribute Unlearning in Recommender Systems. TOIS 2024 (CCF-A, 高被引). Biao Gong, Shuai Tan, Yutong Feng, Xiaoying Xie, Yuyuan Li*, Chaochao Chen, Kecheng Zheng, Yujun Shen, Deli Zhao. UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training. NeurIPS 2024 (CCF-A). Chaochao Chen, Jiaming Zhang, Yizhao Zhang, Li Zhang, Lingjuan Lyu, Yuyuan Li*, Biao Gong, Chenggang Yan. CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence. NeurIPS 2024 (CCF-A). Xiaohua Feng, Chaochao Chen*, Yuyuan Li, Zibin Lin. Fine-grained Pluggable Gradient Ascent for Knowledge Unlearning in Language Models. EMNLP 2024 (CAAI-A). Chaochao Chen, Jiaming Zhang, Yuyuan Li*, Zhongxuan Han. One for All: A Universal Generator for Concept Unlearnability via Multi-Model Alignment. ICML 2024 (CCF-A). Zhongxuan Han, Chaochao Chen*, Xiaolin Zheng, Li Zhang, Yuyuan Li. Hypergraph Convolutional Network for User-Oriented Fairness in Recommender Systems. SIGIR 2024 (CCF-A). Biao Gong, Siteng Huang, Yutong Feng, Shiwei Zhang, Yuyuan Li, Yu Liu. Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation. CVPR 2024 (CCF-A). Zhongxuan Han, Chaochao Chen*, Xiaolin Zheng, Meng Li, Weiming Liu, Binhui Yao, Yuyuan Li, Jianwei Yin. Intra- and Inter-Group Optimal Transport for User-Oriented Fairness in Recommender Systems. AAAI 2024 (CCF-A). Yuyuan Li, Chaochao Chen, Xiaolin Zheng*, Junlin Liu, Jun Wang. Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation. KBS 2024 (SCI TOP). Yuyuan Li, Chaochao Chen*, Yizhao Zhang, Weiming Liu, Lingjuan Lyu, Xiaolin Zheng, Dan Meng, Jun Wang. UltraRE: Enhancing RecEraser for Recommendation Unlearning via Error Decomposition. NeurIPS 2023 (CCF-A). Yuyuan Li, Chaochao Chen*, Xiaolin Zheng, Yizhao Zhang, Zhongxuan Han, Dan Meng, Jun Wang. Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems. ACM MM 2023 (CCF-A). Yuyuan Li, Chaochao Chen, Xiaolin Zheng*, Yizhao Zhang, Biao Gong, Jun Wang. Selective and Collaborative Influence Function for Efficient Recommendation Unlearning. ESWA 2023 (SCI TOP) Yuyuan Li, Chaochao Chen, Xiaolin Zheng*, Yan Wang, Biao Gong. REFER: Randomized Online Factor Selection Framework for Portfolio Management. ESWA 2023 (SCI TOP). Zhongxuan Han, Chaochao Chen*, Xiaolin Zheng, Weiming Liu, Jun Wang, Wenjie Cheng, Yuyuan Li. In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender Systems. ACM MM 2023 (CCF-A). Siteng Huang, Biao Gong, Yulin Pan, Jianwen Jiang, Yiliang Lv, Yuyuan Li, Donglin Wang*. VoP: Text-Video Cooperative Promp-t Tuning for Cross-Modal Retrieval. CVPR 2023 (CCF-A).
Yuyuan Li, Xiaolin Zheng*, Chaochao Chen, Jiawei Wang, Shuai Xu. Exponential Gradient with Momentum for Online Portfolio Selection. ESWA 2022 (SCI TOP).
科研成果
2026.01-2027.12，浙江省领雁计划项目“面向异构受限资源的大模型端边协同理论方法和关键技术研究”，课题负责人。 2025.09-2030.09，国家社会科学基金重点项目“人工智能大模型驱动的学术评价可信性增强机制与实现路径研究”，参与。 2025.01-2027.12，国家自然科学基金青年基金项目“面向隐私保护服务的多维度推荐逆学习方法研究”，主持。 2022.01-2025.12，国家自然科学基金面上项目“跨域推荐系统研究”，参与。 2019.07-2022.06，国家重点研发计划项目“大数据征信及智能评估技术”，参与。
|
