Publications
* indicates equal contribution.
Publications
2025
- Can Diffusion Models Learn Hidden Inter-Feature Rules Behind Images? [PDF]
Yujin Han*, Andi Han*, Wei Huang, Chaochao Lu, Difan Zou.
International Conference on Machine Learning (ICML), 2025 - Masked Autoencoders Are Effective Tokenizers for Diffusion Models. [PDF] [Code]
Hao Chen*, Yujin Han*, Fangyi Chen, Xiang Li, Yidong Wang, Jindong Wang, Ze Wang, Zicheng Liu, Difan Zou, Bhiksha Raj.
International Conference on Machine Learning (ICML), 2025 (Spotlight) Parallelized Autoregressive Visual Generation. [PDF] [Project]
Yuqing Wang, Shuhuai Ren, Zhijie Lin, Yujin Han, Haoyuan Guo, Zhenheng Yang, Difan Zou, Jiashi Feng, Xihui Liu.
Conference on Computer Vision and Pattern Recognition (CVPR), 2025 (Highlight)- Beyond Surface Structure: A Causal Assessment of LLMs’ Comprehension Ability. [PDF] [Code] [Slide]
Yujin Han, Lei Xu, Sirui Chen, Difan Zou, Chaochao Lu.
International Conference on Learning Representations (ICLR), 2025
2024
Slight Corruption in Pre-training Data Makes Better Diffusion Models. [PDF]
Hao Chen, Yujin Han, Diganta Misra, Xiang Li, Kai Hu, Difan Zou, Masashi Sugiyama, Jindong Wang, Bhiksha Raj.
Conference on Advances in Neural Information Processing Systems (NeurIPS), 2024 (Spotlight)Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference. [PDF] [Code] [Slide]
Yujin Han, Difan Zou.
International Conference on Machine Learning (ICML), 2024Conformalized semi-supervised random forest for classification and abnormality detection. [PDF] [Code]
Yujin Han*, Mingwenchan Xu*, Leying Guan.
International Conference on Artificial Intelligence and Statistics (AISTATS), 2024
Preprints
Self-Contradiction as Self-Improvement: Mitigating the Generation-Understanding Gap in MLLMs. [ArXiv]
Yujin Han, Hao Chen, Andi Han, Zhiheng Wang, Xinyu Lin, Yingya Zhang, Shiwei Zhang, Difan ZouTheory of Autoregressive Diffusion Model: Inference Efficiency and Conditional Dependency Learning. [ArXiv]
Xunpeng Huang*, Yujin Han*, Difan Zou, Yian Ma, Tong ZhangOn the Discrepancy and Connection between Memorization and Generation in Diffusion Models. [PDF]
Hanyu Wang, Yujin Han, Difan Zou.
ICML 2024 Workshop on Foundation Models in the Wild, 2024