About me

Welcome! I am a machine learning, deep learning and reinforcement learning researcher who strives to solve difficult problems in real world. I am also an affiliated graduate research assistant in the Machine Learning and Data Intensive Computing Lab.

Currently, I am a PhD candidate in Computer Science from the Rochester Institute of Technology and my B.E. in Software Engineering from Dalian University of Technology. My academic work has been published or is forthcoming in ICDM, KDD, ICML, Neurips, MICCAI, ACM MM, among other outlets. This research tries to solve RL online interaction unavailability under safety or economic concerns by using a broad variety of methods such as offline learning, inverse RL, imitation RL, distributional RL, and meta RL. While primarily focused on small dataset novel algorithm development, I am also enthusiastic in applying RL technique to real-world applications like time series analysis, speech recognition, dense object detection, LLMs safety alignment, network compression, recommender system, medicine, etc.

Currently, I am working on RL driven LLM safety alignment, multi-modal fusion and quantization. Besides, I also spend time on LLM benchmark construction, including data set collection and model evaluation.