Chuheng Zhang

Currently, I am a Researcher/Post-doc in Microsoft Research Asia. My research interest is on reinforcement learning (RL) methods in the era of foundation models, including RL for foundation models (e.g., alignment, RLHF) and foundation models for control (e.g., embodied AI). I am enthusiastic about foundation models for practical industrial problems, and have wide cooperation with industrial teams from different fields including quantitative investment, recommending systems, dialog systems, and inventory management. I have published 30+ papers in ICLR, ICML, AAAI, WWW, SIGIR, CIKM, ICDM, etc., and I serve as the reviewer in top AI conferences and journals. I have been granted the best student paper award runner-up in ICDM-22 and several competition awards in ABC Credit Risk Prediction Contest, UBIQUANT Quantitative Trading Contest, etc.