 Random Masking Finds Winning Tickets for Parameter Efficient Fine-tuningInternational Conference on Machine Learning (ICML), 2024 Jing Xu Jingzhao Zhang |
 BAdam: A Memory Efficient Full Parameter Optimization Method for Large
Language ModelsNeural Information Processing Systems (NeurIPS), 2024 |
 Test-Time Model Adaptation with Only Forward PassesInternational Conference on Machine Learning (ICML), 2024 |
 Linear Combination of Saved Checkpoints Makes Consistency and Diffusion Models BetterInternational Conference on Learning Representations (ICLR), 2024 En-hao Liu Junyi Zhu Zinan Lin Xuefei Ning Shuaiqi Wang ...Sergey Yekhanin Guohao Dai Huazhong Yang Yu Wang Yu Wang |
 Debiased Noise Editing on Foundation Models for Fair Medical Image
ClassificationInternational Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2024 |
