I am currently with the infrastructure team at Alibaba Tongyi Wanx. I received my Ph.D. from the Intelligent and Distributed Computing (IDC) Laboratory at Huazhong University of Science and Technology (HUST), where I was advised by Prof. Ruixuan Li. Before that, I received my bachelor’s degree from Beijing University of Posts and Telecommunications (BUPT).
My current research interests center on video generation and reinforcement learning. I am open to collaboration and welcome inquiries about internship opportunities. You can also reach me on WeChat: Leopold0909.
🔥 News
- 2026.07: 🎉🎉 One paper was accepted by ACM MM 2026.
- 2026.04: 🎉🎉 Three papers were accepted by ICML 2026.
- 2026.01: 🎉🎉 One paper was accepted by ICLR 2026.
- 2025.09: 🎉🎉 Two papers were accepted by NeurIPS 2025.
- 2025.09: 🎉🎉 One paper was accepted by TPDS.
- 2025.05: 🎉🎉 One paper was accepted by KDD 2025 ADS Track.
- 2025.05: 🎉🎉 Two papers were accepted by ICML 2025.
- 2024.07: 🎉🎉 One paper was accepted by MM 2024.
- 2024.05: 🎉🎉 One paper was accepted by ICML 2024.
📃 Selective Publications
-
Shiwei Li, Xiandi Luo, Haozhao Wang, Xing Tang, Ziqiang Cui, Dugang Liu, Yuhua Li, Yichen Li, Xiuqiang He, Ruixuan Li†. BoRA: Towards More Expressive Low-Rank Adaptation with Block Diversity. The 14th International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, April 23rd–27th, 2026. (CCF-A) [paper] [code]
-
Shiwei Li, Xiandi Luo, Haozhao Wang, Xing Tang, Ziqiang Cui, Dugang Liu, Yuhua Li, Xiuqiang He, Ruixuan Li. Beyond Higher Rank: Token-wise Input-Output Projections for Efficient Low-Rank Adaptation. The 39th Annual Conference on Neural Information Processing Systems (NeurIPS), San Diego, USA, December 2–7, 2025. (CCF-A) [paper] [code]
- Shiwei Li, Qunwei Li, Haozhao Wang, Ruixuan Li†, Jianbin Lin, Wenliang Zhong. FedBiF: Communication-Efficient Federated Learning via Bits Freezing. IEEE Transactions on Parallel and Distributed Systems (TPDS), 2025, 36(12): 2668–2678. (CCF-A) [paper] [code]
- Shiwei Li*, Xiandi Luo*, Haozhao Wang†, Xing Tang†, Hao Chen, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Li†. Beyond Zero Initialization: Investigating the Impact of Non-Zero Initialization on LoRA Fine-Tuning Dynamics. The 42nd International Conference on Machine Learning (ICML), Vancouver, Canada, July 13-19, 2025. (CCF-A) [paper] [code]
- Shiwei Li*, Xiandi Luo*, Haozhao Wang, Xing Tang, Shijie Xu, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Li†. The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning. The 42nd International Conference on Machine Learning (ICML), Vancouver, Canada, July 13-19, 2025. (CCF-A) [paper] [code]
- Shiwei Li, Yingyi Cheng, Haozhao Wang†, Xing Tang, Shijie Xu, Weihong Luo, Yuhua Li, Dugang Liu, Xiuqiang He, Ruixuan Li. Masked Random Noise for Communication-Efficient Federated Learning. The 32nd ACM International Conference on Multimedia (ACM MM), Melbourne, Australia, October 28 - November 1, 2024. (CCF-A) [paper] [code]
- Shiwei Li, Wenchao Xu, Haozhao Wang†, Xing Tang†, Yining Qi, Shijie Xu, Weihong Luo, Yuhua Li, Xiuqiang He, Ruixuan Li†. FedBAT: Communication-Efficient Federated Learning via Learnable Binarization. The 41st International Conference on Machine Learning (ICML), Vienna, Austria, July 21-27, 2024. (CCF-A) [paper] [code]
- Shiwei Li*, Huifeng Guo*, Xing Tang, Ruiming Tang, Lu Hou, Ruixuan Li†, Rui Zhang†. Embedding Compression in Recommender Systems: A Survey. ACM Computing Surveys (CSUR), 2024, 56(5): 1-21. (Q1, IF=28.0) [paper]
- Shiwei Li, Huifeng Guo, Lu Hou, Wei Zhang, Xing Tang, Ruiming Tang, Rui Zhang†, Ruixuan Li†. Adaptive Low-Precision Training for Embeddings in Click-Through Rate Prediction. The 37th AAAI Conference on Artificial Intelligence (AAAI), Washington, DC, USA, February 7-14, 2023. (CCF-A) [paper] [code]
👨💻 Service
- Area Chair: KDD 2025, KDD 2026
- Reviewer: KDD 2025, NeurIPS 2025, ACM MM 2025, IJCAI 2025, ECAI 2025, AAAI 2026, ICLR 2026, CVPR 2026, KDD 2026, ICML 2026, IJCAI 2026, ACM MM 2026