💡  Research Interests: reinforcement learning, LLM agents, post-training, combinatorial optimization

I am an AI researcher at Shanda Tokyo Research Center, where I work on reinforcement learning (RL) post-training and LLM agents. I am also a co-founder of the AI4CO open-source research community and work closely with the DiffEqML open-source group.

Previously, I spent one year as an InnoCore Research Fellow in Korea. I completed my M.E. and Ph.D. at KAIST under the supervision of Prof. Jinkyoo Park. I received my undergraduate degree in mathematics from HIT.