Selected Publications

You can find my articles on Full-Publications page or my Google Scholar profile.

Why Can Accurate Models Be Learned from Inaccurate Annotations?
Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations
Unleashing the Power of Task-Specific Directions in Parameter Efficient Fine-tuning
Unveiling the Mystery of Weight in Large Foundation Models: Gaussian Distribution Never Fades
Recent Publications

You can find my articles on Full-Publications page or my Google Scholar profile.

Zhiyi Shi, Binjie Wang, Chongjie Si, Yichen Wu, Junsik Kim, Hanspeter Pfister (2025). DualEdit: Dual Editing for Knowledge Updating in Vision-Language Models. COLM.
PDF Cite
Chongjie Si, Zhiyi Shi, Yadao Wang, Xiaokang Yang, Susanto Rahardja, Wei Shen (2025). MAP: Revisiting Weight Decomposition for Low-Rank Adaptation. Arxiv.
PDF Cite
Chongjie Si, Xuankun Yang, Muqing Liu, Yadao Wang, Xiaokang Yang, Wenbo Su, Bo Zheng, Wei Shen (2025). Weight Spectra Induced Efficient Model Adaptation. Arxiv.
PDF Cite
Chongjie Si, Yidan Cui, Fuchao Yang,, Xiaokang Yang, Wei Shen (2025). Revisiting Sparsity Constraint Under High-Rank Property in Partial Multi-Label Learning. Arxiv.
PDF Cite
Chongjie Si, Kangtao Lv, Jingjing Jiang, Yadao Wang, Yongwei Wang, Xiaokang Yang, Wenbo Su, Bo Zheng, Wei Shen (2025). NAN: A Training-Free Solution to Coefficient Estimation in Model Merging. Arxiv.
PDF Cite Zhihu
Chongjie Si, Yidan Cui, Fuchao Yang, Xiaokang Yang, Wei Shen (2025). Why Can Accurate Models Be Learned from Inaccurate Annotations?. Arxiv.
PDF Cite Code Zhihu
See all