Jiajun Fan

Jiajun Fan is a Ph.D. student in Computer Science at the University of Illinois Urbana-Champaign, where he researches reinforcement learning post-training for generative models, including flow and diffusion models as well as multimodal reasoning large language models. He previously earned a master's degree from Tsinghua University and is known for his work on sample-efficient deep reinforcement learning, including breaking 24 Atari world records, for which he received an ICLR 2023 Oral presentation. His recent research focuses on autonomous RL post-training methods that reduce the need for human supervision, with applications spanning audio LLMs and vision-language-action models.