Hao Peng

3314 SC
201 North Goodwin Avenue
Urbana, IL 61801
I am an Assistant Professor at the Department of Computer Science of the University of Illinois at Urbana-Champaign (UIUC).
I received my Ph.D. from the University of Washington, with Noah Smith, and my Bachelors Degree from Peking University. I spent one year at the Allen Institute for Artificial Intelligence as a Young Investigator, and time at Microsoft Research, Google, and DeepMind.
My current research interests focus on large language models (LLMs). Specifically, I work on AI towards:
- Solving complex reasoning problems in a generalizable way; I believe that learning from experience (e.g., through reinforcement learning) and insights from human cognition are crucial towards this goal;
- Understanding and reasoning about the world causally;
- Positively impacting society;
- Advancing the frontier of human knowledge and contributing to scientific discovery, which I see as the ultimate demonstration of true generalization beyond the human knowledge they have been trained on.
Outside work, I cater to the whims of a quartet of furry overlords: Meera, Loki, Sylvie, and Kea. When they release me from their service, I cycle in the summer, and (backcountry) ski in the winter.
Undergraduate and master’s students: We love hearing from motivated undergraduate and master’s students! If you’d like to collaborate with us, the best way to get in touch is by email. When reaching out, please read one of our recent papers that excites you and ask a few questions about it in your message. Please start your subject line with [Meera+Loki+Sylvie+Kea] to indicate that you have read this message.
recent publications
- From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones2025
-
- Context Length Alone Hurts LLM Performance Despite Perfect RetrievalIn Findings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2025
- spotlightThe Best Instruction-Tuning Data are Those That FitIn Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), 2025
- The Unreasonable Effectiveness of Entropy Minimization in LLM ReasoningIn Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), 2025
- Reinforcement Learning Finetunes Small Subnetworks in Large Language ModelsIn Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), 2025