Publications

^* indicates equal contribution.

Publications

2024

• Slight Corruption in Pre-training Data Makes Better Diffusion Models.
  Hao Chen, Yujin Han, Diganta Misra, Xiang Li, Kai Hu, Difan Zou, Masashi Sugiyama, Jindong Wang, Bhiksha Raj. [PDF]
  Conference on Advances in Neural Information Processing Systems (NeurIPS), 2024 (Spotlight)

• Improving Group Robustness on Spurious Correlation Requires Preciser Group Inference.
  Yujin Han, Difan Zou. [PDF] [Code]
  NeurIPS Workshop on Causal Representation Learning (CRL), 2023
  International Conference on Machine Learning (ICML), 2024

• Conformalized semi-supervised random forest for classification and abnormality detection.
  Yujin Han^*, Mingwenchan Xu^*, Leying Guan. [PDF] [Code]
  International Conference on Artificial Intelligence and Statistics (AISTATS), 2024

Preprint

• On the Discrepancy and Connection between Memorization and Generation in Diffusion Models.
  Hanyu Wang, Yujin Han, Difan Zou
  ICML 2024 Workshop on Foundation Models in the Wild, 2024