Guowei Zou (邹国伟)
I am a third-year PhD student at Sun Yat-Sen University.
Currently, I am a visiting student at the National University of Singapore.
Research Area: Artificial Intelligence, Embodied AI, World Models, Vision-Language-Action (VLA) Model, Multi-Agent Systems
News
We introduce 
, our research framework for policy optimization with generative models.
Our paper Co-π-tree has been accepted to EMNLP 2026!
Our paper OGPO has been accepted to ACM MM 2026!
Our paper D²PPO has been accepted to AAAI 2026!
Biography
I am a third-year PhD student at 
Sun Yat-Sen University, School of Computer Science and Engineering. Currently, I am a visiting student at the 
School of Computing, National University of Singapore. Previously, I worked as a Hardware Engineer at 
Huawei Technologies Co., Ltd. Before that, I received my Master's degree from Sun Yat-Sen University (State Key Laboratory of Optoelectronic Materials and Technologies).
Research Interests
My research lies at the intersection of artificial intelligence and robotics, where I explore how generative modeling and reinforcement learning can be unified to create embodied agents capable of real-time decision-making in the physical world. Currently, I am particularly focused on World Models and RL-based policy optimization within world models.
We introduce POInfra, a research framework for policy optimization with generative models. Our work spans pretraining, online policy optimization, and inference-time guidance and planning for robot control and multi-agent decision-making.
I believe artificial intelligence is not merely a tool, but a revolutionary force that will profoundly reshape every aspect of human society. I am convinced that the era of AI for everything is fast approaching. AI will not only transform how we live, but also how we understand ourselves: the process of creating intelligence is, in essence, the process of rediscovering humanity. The age of human–AI coevolution is coming.