Haojin Wang

Heyyy, welcome to my homepage 😊

I am a Master's student in Computer Science at University of Illinois Urbana-Champaign (UIUC), working with professor Hao Peng. I work mostly on ML and related problems, especially post-training methods for lifelong learning of agents. I am currently interested in continual learning of agents.

I am applying to PhD programs for this round. Please feel free to reach out if you think I might be a good fit.

Email / Twitter / Google Scholar / Semantic Scholar / GitHub

📷 Kamakura, Japan

Selected Publication

💪 Good SFT Optimizes for SFT, Better SFT Prepares for Reinforcement Learning

Dylan Zhang, Yufeng Xu, Haojin Wang, Qingzhi Chen, Hao Peng
Proceedings of ICML, 2026
arxiv

📊 Distribution Prompting: Understanding the Expressivity of Language Models Through the Next-Token Distributions They Can Produce

Haojin Wang, Zining Zhu, Freda Shi
Proceedings of EMNLP, 2025
paper, arxiv

Ongoing Work

🌹 ROSE

Service

Reviewer: COLM(2026)

Misc

I am a huge fan of Arsenal. COYG!

Source