Chao Du

Chao Du

Scientist · AMI Labs, Singapore

Google Scholar Twitter LinkedIn

I am a founding scientist at AMI Labs. Before that, I was a senior research scientist at Sea AI Lab, where I led a research group working on generative models. I received my Ph.D. from Tsinghua University, where I was advised by Prof. Jun Zhu, and my undergraduate degree from the Yao Class at Tsinghua University.

I work on machine learning. My research aims to understand intelligence from the perspective of probability and statistics. Currently, I focus on developing probabilistic methods for world modeling from first principles, seeking to explain how knowledge and intelligence emerge from real-world data.

We are hiring interns, scientists, and engineers to work on world models and video foundation models. Feel free to reach out if you are interested.

Selected Publications

Generative Modeling

Nonparametric Data Attribution for Diffusion Models
Yutian Zhao*, Chao Du*, Xiaosen Zheng, Tianyu Pang, Min Lin
International Conference on Machine Learning (ICML), Seoul, South Korea, 2026
Paper Code
On Memorization in Diffusion Models
Xiangming Gu, Chao Du, Tianyu Pang, Chongxuan Li, Min Lin, Ye Wang
Transactions on Machine Learning Research (TMLR), 2025
Paper Code
Scaling up Masked Diffusion Models on Text
Shen Nie, Fengqi Zhu, Chao Du, Tianyu Pang, Qian Liu, Guangtao Zeng, Min Lin, Chongxuan Li
International Conference on Learning Representations (ICLR), Singapore, 2025
Paper Code
Nonparametric Generative Modeling with Conditional Sliced-Wasserstein Flows
Chao Du, Tianbo Li, Tianyu Pang, Shuicheng Yan, Min Lin
International Conference on Machine Learning (ICML), Hawaii, USA, 2023
Paper Code Slides Poster
Error Analyses of Auto-Regressive Video Diffusion Models
Jing Wang, Fengzhuo Zhang, Xiaoli Li, Vincent Tan, Tianyu Pang, Chao Du, Aixin Sun, Zhuoran Yang
Journal of Machine Learning Research (JMLR), 2026
Paper

Reinforcement Learning

Continual Reinforcement Learning by Planning with Online World Models
Zichen Liu, Guoji Fu, Chao Du, Wee Sun Lee, Min Lin
International Conference on Machine Learning (ICML), Vancouver, Canada, 2025
Paper Benchmark
Locality Sensitive Sparse Encoding for Learning World Models Online
Zichen Liu, Chao Du, Wee Sun Lee, Min Lin
International Conference on Learning Representations (ICLR), Vienna, Austria, 2024
Paper Code in Appendix

RL for Language Models

Reinforcing General Reasoning Without Verifiers
Xiangxin Zhou, Zichen Liu, Anya Sims, Haonan Wang, Tianyu Pang, Chongxuan Li, Liang Wang, Min Lin, Chao Du
International Conference on Learning Representations (ICLR), Rio de Janeiro, Brazil, 2026
Paper Code
Sample-Efficient Alignment for LLMs
Zichen Liu, Changyu Chen, Chao Du, Wee Sun Lee, Min Lin
Language Gamification Workshop (LanGame), NeurIPS 2024
Paper Code

Service