Ph.D. Student in Computer Science at Mila - Quebec AI Institute & Université de Montréal. Advised by Prof. Pierre-Luc Bacon.
I have been a Ph.D. student in Computer Science at Université de Montréal and Mila - Quebec AI Institute from May 2025 to present, advised by Prof. Pierre-Luc Bacon. Before starting my Ph.D., I completed my M.Sc. in the LAMDA Group at Nanjing University.
My research centers on reinforcement learning for general-purpose embodied intelligence, with a particular focus on world models and model-based reinforcement learning. I am interested in building generative world models for embodied environments and developing algorithms that use them for efficient policy learning, planning, and adaptation.
*: equal contribution, see Google Scholar for the full list
ICML, 2026
VLA-MBPO integrates a series of pratical techniques to train VLAs in world models, including (i) adapting unified multimodal models (UMMs) for data-efficient world modeling; (ii) an interleaved view decoding mechanism to enforce multi-view consistency; and (iii) chunk-level branched rollout to mitigate error compounding.
A researcher-friendly PyTorch reinforcement-learning library for Vision-Language-Action models, with clean modular design and decoupled env denpendency.
An elegant PyTorch offline-reinforcement-learning library with clear, extensible implementations of model-free and model-based algorithms.