Li Jiang

About me

Hello! I am Li Jiang (姜力), a third-year Ph.D. student at McGill and Mila - Quebec AI Institute, advised by Prof. Yichuan Ding and Prof. Xue Liu. My research interests include:

• LLM Fine-tuning and Alignment: Reinforcement Learning with Human Feedback (RLHF) for LLMs and agents.
• LLMs + X: Applications of LLMs in complex, human-centric domains, leveraging their unique strengths in reasoning over and synthesizing unstructured data.

I am open to collaboration, feel free to reach me out!

News

• One paper related to LLM alignment is accepted to COLM 2024.
• One paper related to offline RL is accepted to NeurIPS 2023.
• One paper related to offline RL is accepted to ICLR 2023.
• One paper related to offline RL is accepted to NeurIPS 2022.

Awards

• Shenzhen University International Scholarship, 2023.
• Stanford Existential Risk Initiative Research Fellowship, 2022.

Service & Teaching

• Reviewer for conferences (ICML, NeurIPS, ICLR) and Journals (JMLR, TMLR).
• TA for MGCR 372 Operations Management, McGill (Fall 2023, Winter 2024, Fall 2024).

Misc

I love mountain climbing as it allows me to witness the awe-inspiring vastness of the universe from great heights. Feel free to reach me at li.jiang3[AT]mail[DOT]mcgill[DOT]ca (research) or jiangli3859[AT]gmail[DOT]com (personal).