Yifan Zhong Ph.D. Candidate School of Intelligence Science and Technology Peking University E-mail  /  CV  /  Google Scholar  /  Github

Biography

Hi, I'm Yifan Zhong. I am currently a second-year Ph.D. student in the PAIR Lab at Peking University guided by Prof. Yaodong Yang. Prior to this, I earned my bachelor's degree from Tongji University in Computer Science and Technology. Earlier in my education, I attended No. 1 experimental class at The High School Affiliated to Renmin University of China.

My research interests include reinforcement learning and large language model. Please do not hesitate to reach out to me via email at zhongyifan@stu.pku.edu.cn !

Selected Publications

* equal contribution

	In-Context Editing: Learning Knowledge from Self-Induced Distributions Siyuan Qi, Bangcheng Yang, Kailin Jiang, Xiaobo Wang, Jiaqi Li, Yifan Zhong, Yaodong Yang, Zilong Zheng. Under Review. arXiv / Code
	Panacea: Pareto Alignment via Preference Adaptation for LLMs Yifan Zhong*, Chengdong Ma*, Xiaoyuan Zhang*, Ziran Yang, Haojun Chen, Qingfu Zhang, Siyuan Qi, Yaodong Yang. Advances in Neural Information Processing Systems (NeurIPS), 2024. Paper / arXiv
	Maximum Entropy Heterogeneous-Agent Reinforcement Learning Jiarong Liu*, Yifan Zhong*, Siyi Hu, Haobo Fu, QIANG FU, Xiaojun Chang, Yaodong Yang. International Conference on Learning Representations (ICLR), 2024. (Spotlight) Project / Paper / arXiv / Code
	CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents Siyuan Qi*, Shuo Chen*, Yexin Li*, Xiangyu Kong*, Junqi Wang*, Bangcheng Yang, Pring Wong, Yifan Zhong, Xiaoyuan Zhang, Zhaowei Zhang, Nian Liu, Yaodong Yang, Song-Chun Zhu. International Conference on Learning Representations (ICLR), 2024. (Spotlight) Paper / arXiv / Code
	Heterogeneous-agent reinforcement learning Yifan Zhong*, Jakub Grudzien Kuba*, Xidong Feng*, Siyi Hu, Jiaming Ji, Yaodong Yang. Journal of Machine Learning Research (JMLR), 2024. Paper / arXiv / Code
	Safety gymnasium: A unified safe reinforcement learning benchmark Jiaming Ji*, Borong Zhang*, Jiayi Zhou*, Xuehai Pan, Weidong Huang, Ruiyang Sun, Yiran Geng, Yifan Zhong, Juntao Dai, Yaodong Yang. Advances in Neural Information Processing Systems Track on Datasets and Benchmarks (NeurIPS DB), 2023. Project / Paper / arXiv / Code / Docs
	MARLlib: A Scalable and Efficient Multi-agent Reinforcement Learning Library Siyi Hu, Yifan Zhong, Minquan Gao, Weixun Wang, Hao Dong, Xiaodan Liang, Zhihui Li, Xiaojun Chang, Yaodong Yang. Journal of Machine Learning Research Machine Learning Open Source Software (JMLR MLOSS), 2023. Paper / arXiv / Code / Docs
	MyoChallenge: Learning contact-rich manipulation using a musculoskeletal hand Yiran Geng*, Boshi An*, Yifan Zhong*, Jiaming Ji, Yuanpei Chen, Hao Dong, Yaodong Yang. First Place in NeurIPS 2022 Challenge Track (1st in 340 submissions from 40 teams). Paper / Challenge Page / Code / Slides / Award / Media (BIGAI) / Media (PKU-IAI)

Experiences

Research Intern, Multi-Agent Systems Laboratory, BIGAI Aug. 2022 - Aug. 2024 Topic: Reinforcement Learning, Multi-Agent Systems, LLM Alignment Supervised by: Yaodong Yang, Siyuan Qi.

Professional Services

• Conference Reviewer for NeurIPS (2024)
• Area Chair for DAI (2024)

Teaching Experiences

• Teaching Assistant for Large Language Models and Alignment

Selected Honors & Awards

• Second Prize of BIGAI Research Rising Star Award
  2024
• Outstanding Graduate of Shanghai
  2023
• First Place in NeurIPS 2022 Challenge Track
  2022
• CCF Outstanding Undergraduate Student
  2022
• National Scholarship
  2022, 2020
• The 46th ICPC Asia Regional Contest (Jinan Site) Silver Medal
  2021
• Qidi Scholarship
  2021
• First Prize of Undergraduate Outstanding Student Scholarship
  2021

Sports

I am very into sports, especially swimming, badminton, and running. Currently, I am a member of the university's swimming team and the school's badminton team, where I train regularly. If you share the same interests, feel free to reach out and connect!