Talk: Large Scale Reinforcement Leanring for General Computer Agents Bio: Zhiyong Wu currently serves as a Research Scientist at ByteDance SEED. Prior to this, he was affiliated with the Shanghai AI Laboratory. He earned his doctoral degree from the University of Hong Kong and has been recognized as a Shanghai Overseas High-Level Talent. His primary research focuses on large pre-trained language models. He has published over 30 academic papers in top conferences and has served as an Area Chair for prestigious events such as NeurIPS, ICML, ICLR, and ACL. Actively contributing to the field of computer agents, he has released several early pioneering models and datasets, with his work attracting over 5,000 citations.