Publications

Scaling World-Model Reinforcement Learning Through Diffusion Policy Optimization

Xiaoyuan Cheng*, Wenxuan Yuan*, Zhancun Mu, Yuanzhao Zhang, Yiming Yang, Hai Wang, Zhuo Sun†, Che Liu†

Preprint · arXiv:2605.26282 2026

Paper · Code · Project page

Fisher Decorator: Refining Flow Policy via A Local Transport Map

Xiaoyuan Cheng*, Haoyu Wang*, Wenxuan Yuan, Ziyan Wang, Zonghao Chen, Li Zeng, Zhuo Sun

Conference on Neural Information Processing Systems (NeurIPS) 2026 Poster

Paper · Code

On Stability and Robustness of Diffusion Posterior Sampling for Bayesian Inverse Problems

Yiming Yang, Xiaoyuan Cheng, Yi He, Kaiyu Li, Wenxuan Yuan, Zhuo Sun

Conference on Neural Information Processing Systems (NeurIPS) 2026 Poster

Paper

How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?

Xiaoyuan Cheng*, Wenxuan Yuan*, Boyang Li, Yuanchao Xu, Yiming Yang, Hao Liang, Bei Peng, Robert Loftin, Zhuo Sun, Yukun Hu

International Conference on Machine Learning (ICML) 2026 Poster

Paper · Code

Information Shapes Koopman Representation

Xiaoyuan Cheng*, Wenxuan Yuan*, Yiming Yang, Yuanzhao Zhang, Sibo Cheng, Yi He, Zhuo Sun

International Conference on Learning Representations (ICLR) 2026 Oral

Paper · Code

MSTCN-VAE: An unsupervised learning method for micro gesture recognition based on skeleton modality

Wenxuan Yuan, Shanchuan He, Jianwen Dou

International Joint Conference on Artificial Intelligence (IJCAI) 2023 Oral

Physics-guided multistage neural network: A physically guided network for step initial values and dispersive shock wave phenomena

Wenxuan Yuan, Rui Guo

Physical Review E 2024

Physics-informed Neural Network method for the Modified Nonlinear Schrödinger equation

Wenxuan Yuan, Rui Guo, Yining Gao

Optik 2023

Paper