Run Peng

Run Peng

University of Michigan

Hi This is Run Peng å½­ę¶¦. You can call me Run or Roihn. I am a first-year Ph.D. student in Computer Science and Engineering, advised by professor Joyce Chai. My primary research focus is to bridge the gap between humans and AI agents.

Agents need to be able to perceive, to reason, and to interact with the world and humans. Iā€™m thrilled to explore agent behaviors, human behaviors, and human-AI interaction when humans are cosituated with the agents. From cognitive perspective, as we figure out the commonalities and distinctions between human and agent behaviors, I believe we can unlock new insights into the nature of understanding itself, ultimately guiding us toward the development of more general AI agents.

šŸ”„ News

  • 2024.12: Ā ā“ My photo occasionally appeared in CSE 2024 Annual Report of Umich. (?)
  • 2024.10: Ā šŸŽ‰ One paper accepted at EMNLP 2024 findings! See you at Miami!
  • 2024.09: Ā šŸŽ‰ I would like to continue working with Professor Joyce Chai at SLED lab as a Ph.D. student!

šŸ“ Publications

EMNLP 2023 Findings
sym

Towards A Holistic Landscape of Situated Theory of Mind in Large Language Models

Ziqiao Ma, Jacob Sansom, Run Peng, Joyce Chai

[Paper] [Dataset] [Survey]

ICRA 2024
sym

Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation

Yinpei Dai, Run Peng, Sikai Li, Joyce Chai

[Paper] [Code] [Video]

ICML 2023
sym

Go Beyond Imagination: Maximizing Episodic Reachability with World Models

Yao Fu, Run Peng, Honglak Lee

[Paper] [Code]

EMNLP 2024 Findings
sym

Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents

Zengqing Wu*, Run Peng*, Shuyuan Zheng, Qianying Liu, Xu Han, Brian I. Kwon, Makoto Onizuka, Shaojie Tang, Chuan Xiao

[Project] [Paper] [Code]

preprint
sym

Smart Agent-Based Modeling: On the Use of Large Language Models in Computer Simulations

Zengqing Wu, Run Peng, Xu Han, Shuyuan Zheng, Yixin Zhang, Chuan Xiao

[Paper] [Code]

Learning Exploration Policies with View-based Intrinsic Rewards, Yijie Guo*, Yao Fu*, Run Peng, Honglak Lee, In NeurIPS 2022 DRL Workshop

šŸ“– Educations

  • 2024.09 - Now, Ph.D. in Computer Science & Engineering, University of Michigan
  • 2022.09 - 2024.05, MSE in Computer Science & Engineering, University of Michigan
  • 2020.09 - 2022.05, BSE in Computer Science & Engineering, University of Michigan
  • 2018.09 - 2024.08, BSE in Electrical & Computer Engineering, Shanghai Jiao Tong University

šŸ’» Internships & Research Experience

  • 2023.09 - 2023.12, LG AI Research, Ann Arbor. Mentored by Lajanugen Logeswaran and Sungryull Sohn.
  • 2021.10 - 2023.08, Lee Lab, University of Michigan. Advised by professor Honglak Lee, mentored by Yijie Guo and Violet Yao Fu.
  • 2022.12 - Now, SLED Lab, University of Michigan.

šŸ‘” Service

  • Paper Review:
    • Conference: (AI) NeurIPS, ICLR, AISTATS (NLP) EMNLP, NAACL, COLM, (HCI) HRI, CHI
    • Journal: Journal of Simulation
  • Social Activity:
    • Explore Grad Studies Volunteer, University of Michigan