Interest
I study world models that faithfully simulate how environments evolve in response to actions. These models can serve as substitutes for their target environments, generating interaction data to support decision-making methods such as reinforcement learning and planning. I am also interested in broader computer vision such as generative modeling and unsupervised representational learning.
Goal
I want to build world models that:
perfectly simulate external environments, such as the video game World of Warcraft;
generalize across diverse tasks and environments, eliminating the need to train a separate world model for each task; and
capture the underlying concepts and rules of the real world, such as the law of gravity.
Selected publications
Concept-Guided Spatial Regularization for World Models in Atari Pong Yukuan Lu, Zaishuo Xia, Weyl Lu, and Yubei Chen.
arXiv preprint, 2026.An original and self-led first research project. This work shows that:
As of 2026, successful world-model agents—policies trained with a world model—frequently rely on
weak underlying world models, a phenomenon I term the agent–world-model gap.
Our method improves world models in Atari Pong, while broader generalization remains open.
Other resources
Talks
A Brief Overview of Code World Models
UC Davis SSL Lab · August 14, 2026
Slides · Notes