Hongxin Zhang

I am Hongxin Zhang (张洪鑫), a second-year Ph.D. student in Computer Science at UMass Amherst, advised by Prof. Chuang Gan.

I received my bachelor’s degree from ACM Honors Class, Shanghai Jiao Tong University. I was fortunate to be advised by Prof. Diyi Yang at Stanford during my undergraduate.

I am curious about how humans differentiate from other beings and from each other. Currently, I am conducting research in Artificial Intelligence, trying to understand humans by creating something similar. My current interests lie in Embodied Intelligence, especially how to build better Agents with Foundation Models to enhance their Reasoning and Planning, Social Interaction, and be more like humans.

Outside of research, I enjoy reading books, playing billiards and board games.

Email  /  CV  /  Google Scholar  /  Twitter  /  Github

profile photo

Professional Services

  • Conference Reviewer: ICML'23-24, NeurIPS'23-24, ICLR'24, CVPR'24, ARR, COLM'24, IJCAI'24
  • Journal Reviewer: IJCV, TIP

News

  • [2024.5] Interning at Adobe for the summer
  • [2024.4] COMBO is out on arXiv, check it out!

Publications

COMBO: Compositional World Models for Embodied Multi-Agent Cooperation
Hongxin Zhang*, Zeyuan Wang*, Qiushi Lyu*, Zheyuan Zhang, Sunli Chen, Tianmin Shu, Yilun Du, Chuang Gan
Preprint
Project Page | Paper | Code
Building Cooperative Embodied Agents Modularly with Large Language Models
Hongxin Zhang*, Weihua Du*, Jiaming Shan, Qinhong Zhou, Yilun Du, Joshua B. Tenenbaum, Tianmin Shu, Chuang Gan
International Conference on Learning Representations (ICLR), 2024
Project Page | Paper | Code |
HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments
Qinhong Zhou*, Sunli Chen*, Yisong Wang, Haozhe Xu, Weihua Du, Hongxin Zhang, Yilun Du, Joshua B. Tenenbaum, Chuang Gan
International Conference on Learning Representations (ICLR), 2024
Project Page | Paper | Code
img SALMON: Self-Alignment with Principle-Following Reward Models
Zhiqing Sun, Yikang Shen, Hongxin Zhang, Qinhong Zhou, Zhenfang Chen, David Cox, Yiming Yang, Chuang Gan
International Conference on Learning Representations (ICLR), 2024
Paper | Code
img Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision
Zhiqing Sun, Yikang Shen, Qinhong Zhou, Hongxin Zhang, Zhenfang Chen, David Cox, Yiming Yang, Chuang Gan
Conference on Neural Information Processing Systems (NeurIPS), 2023
Paper | Code
img On Second Thought, Let’s Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
Omar Shaikh, Hongxin Zhang, William Held, Michael Bernstein, Diyi Yang
Annual Meeting of the Association for Computational Linguistics (ACL), 2023
Paper | Code
img Werewolf Among Us: A Multimodal Dataset for Modeling Persuasion Behaviors in Social Deduction Games
Bolin Lai*, Hongxin Zhang*, Miao Liu*, Aryan Pariani*, Fiona Ryan, Wenqi Jia, Shirley Anugrah Hayati, James M. Rehg, Diyi Yang
Annual Meeting of the Association for Computational Linguistics (ACL), 2023 Findings
Paper | Code
img Bounding the Capabilities of Large Language Models in Open Text Generation with Prompt Constraints
Albert Lu*, Hongxin Zhang*, Yanzhe Zhang, Xuezhi Wang, Diyi Yang
Conference of the European Chapter of the Association for Computational Linguistics (EACL), 2023 Findings
Paper | Code
img Robustness of Demonstration-based Learning Under Limited Data Scenario
Hongxin Zhang, Yanzhe Zhang, Ruiyi Zhang, Diyi Yang
The Conference on Empirical Methods in Natural Language Processing (EMNLP), 2022.
Paper | Code

Website's code is from Jon Barron.