Publications

2025, COLM. Zhiyi Shi, Binjie Wang, Chongjie Si, Yichen Wu, Junsik Kim, Hanspeter Pfister. DualEdit: Dual Editing for Knowledge Updating in Vision-Language Models.

2025, arXiv. Chongjie Si, Xuankun Yang, Muqing Liu, Yadao Wang, Xiaokang Yang, Wenbo Su, Bo Zheng, Wei Shen. Weight Spectra Induced Efficient Model Adaptation.

2025, arXiv. Chongjie Si, Zhiyi Shi, Yadao Wang, Xiaokang Yang, Susanto Rahardja, Wei Shen. MAP: Revisiting Weight Decomposition for Low-Rank Adaptation.

2025, arXiv. Chongjie Si, Yidan Cui, Fuchao Yang,, Xiaokang Yang, Wei Shen. Revisiting Sparsity Constraint Under High-Rank Property in Partial Multi-Label Learning.

2025, arXiv. Chongjie Si, Yidan Cui, Fuchao Yang, Xiaokang Yang, Wei Shen. Why Can Accurate Models Be Learned from Inaccurate Annotations?.

2025, arXiv. Chongjie Si, Kangtao Lv, Jingjing Jiang, Yadao Wang, Yongwei Wang, Xiaokang Yang, Wenbo Su, Bo Zheng, Wei Shen. NAN: A Training-Free Solution to Coefficient Estimation in Model Merging.

2025, ICCV. Chongjie Si, Zhiyi Shi, Xuehui Wang, Yichen Xiao, Xiaokang Yang, Wei Shen. Generalized Tensor-based Parameter-Efficient Fine-Tuning via Lie Group Transformations.

2025, ICLR. Chongjie Si, Zhiyi Shi, Shifan Zhang, Xiaokang Yang, Hanspeter Pfister, Wei Shen. Unleashing the Power of Task-Specific Directions in Parameter Efficient Fine-tuning.

2025, ICLR. Chongjie Si, Xuehui Wang, Xue Yang, Zhengqin Xu, Qingyun Li, Jifeng Dai, Yu Qiao, Xiaokang Yang, Wei Shen. Maintaining Structural Integrity in Parameter Spaces for Parameter Efficient Fine-Tuning.

2025, arXiv. Chongjie Si, Jingjing Jiang, Xiaokang Yang, Wei Shen. Unveiling the Mystery of Weight in Large Foundation Models: Gaussian Distribution Never Fades.

2024, arXiv. Chongjie Si, Xiaokang Yang, Wei Shen. See Further for Parameter Efficient Fine-tuning by Standing on the Shoulders of Decomposition.

2024, ECCV. Chongjie Si, Xuehui Wang, Xiaokang Yang, Wei Shen. Tendency-driven Mutual Exclusivity for Weakly Supervised Incremental Semantic Segmentation.

2024, arXiv. Chongjie Si, Xuehui Wang, Yan Wang, Xiaokang Yang, Wei Shen. Appeal: Allow Mislabeled Samples the Chance to be Rectified in Partial Label Learning.

2024, AAAI, Oral. Chongjie Si, Zekun Jiang, Xuehui Wang, Yan Wang, Xiaokang Yang, Wei Shen. Partial Label Learning with a Partner.

2023, TKDE. Chongjie Si, Yuheng Jia, Ran Wang, Min-Ling Zhang, Yanghe Feng, Chongxiao Qu. Multi-label Classification with High-rank and High-order Label Correlations.

2023, KDD, Oral. Yuheng Jia, Chongjie Si, Min-Ling Zhang. Complementary Classifier Induced Partial Label Learning.