Haofei Yu

于昊飞

Siebel School of Computing and Data ScienceUniversity of Illinois Urbana-Champaign

2119B, 201 N Goodwin Ave, Urbana, IL 61801

Haofei Yu
Taken at Goreme, Cappadocia, Turkey. Credit to Naisong.

I am currently a second-year PhD student at Siebel School of Computing and Data Science, University of Illinois Urbana-Champaign advised by Jiaxuan You. I also work closely with Paul Pu Liang. My main research interests lie in reinforcement learning and world modeling.

Before UIUC, I got my B.Eng. degree in Computer Science (with honors) at ChuKochen Honors College of Zhejiang University. Afterwards, I got my M.S. in Intelligent Information Systems in Language Technologies Institute of School of Computer Science at Carnegie Mellon University.

I have multiple industrial internship experiences including Tencent AI Lab (2022), Apple Siri Information and Intelligence Team (2023), MIT-IBM Watson AI Lab (2024), Allen Institute for AI (Ai2) (2025), and Meta AI (2026). All focusing on language modeling and its applications.

Publications

CTM-AI: A Blueprint for General AI Inspired by a Model of Consciousness
Haofei Yu*, Yining Zhao*, Lenore Blum, Manuel Blum, Paul Pu Liang
Under Review
ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery
Haofei Yu, Jiaxuan You, Peter Clark, Bodhisattwa Prasad Majumder, Kyle Richardson
Under Review
Sotopia-RL: Reward Design for Social Intelligence
Haofei Yu*, Zhengyang Qi*, Yining Zhao*, Kolby Nottingham, Keyang Xuan, Bodhisattwa Prasad Majumder, Hao Zhu, Paul Pu Liang, Jiaxuan You
Under Review
Building Social World Models with Large Language Models
Haofei Yu, Yining Zhao, Guanyu Lin, Jiaxuan You
The 43rd International Conference on Machine Learning (ICML 2026)
ResearchTown: Simulator of Human Research Community
Haofei Yu*, Zhaochen Hong*, Zirui Cheng*, Kunlun Zhu*, Keyang Xuan, Jinwei Yao, Tao Feng, Jiaxuan You
The 42nd International Conference on Machine Learning (ICML 2025)
MMoE: Enhancing Multimodal Models with Mixtures of Multimodal Interaction Experts
Haofei Yu*, Zhengyang Qi*, Lawrence Jang*, Ruslan Salakhutdinov, Louis-Philippe Morency, Paul Pu Liang
The 2024 Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)