Yipeng Kang 坑易澎
I am currently a researcher at Beijing Institute for General Artificial Intelligence (BIGAI), under the leadership of Prof. Songchun Zhu. I earned my PhD as an Outstanding Graduate from the Institute for Interdisciplinary Information Sciences (IIIS) at Tsinghua University, which is led by Prof. Andrew Chi-Chih Yao. Additionally, I was a visiting scholar at CCLS, Columbia University and received my bachelor’s degree from the University of Science and Technology of China.
Email: kangyipeng[at]bigai[dot]ai
Research Interests
My main research interests lie at the intersection of natural language processing (NLP) and multiagent systems (MAS), with a particular focus on:
- AI and social governance
- Value system and alignment of large language models
- Social intelligence of language agents
Recent Works
(†: equal contribution)
-
Are the Values of LLMs Structurally Aligned with Humans? A Causal Perspective
Yipeng Kang, Junqi Wang, Yexin Li, Mengmeng Wang, Wenming Tu, Quansen Wang, Hengli Li, Tingjun Wu, Xue Feng, Fangwei Zhong, Zilong Zheng
ACL 2025 Findings (CCF-A). -
IBGP: Imperfect Byzantine Generals Problem for Zero-Shot Robustness in Communicative Multi-Agent Systems
Yihuan Mao†, Yipeng Kang†, Peilun Li, Ning Zhang, Wei Xu, Chongjie Zhang.
AAMAS 2025 (Extended Abstract). -
Multi-Agent Policy Transfer via Task Relationship Modeling
Rongjun Qin, Feng Chen, Tonghan Wang, Lei Yuan, Xiaoran Wu, Yipeng Kang, Zongzhang Zhang, Chongjie Zhang, Yang Yu.
SCIS 2023 (CCF-A). -
Multi-Agent Policy Transfer via Task Relationship Modeling
Rongjun Qin, Feng Chen, Tonghan Wang, Lei Yuan, Xiaoran Wu, Yipeng Kang, Zongzhang Zhang, Chongjie Zhang, Yang Yu.
NeurIPS 2022 Deep Reinforcement Learning Workshop. -
Non-Linear Coordination Graphs
Yipeng Kang†, Tonghan Wang†, Qianlan Yang†, Xiaoran Wu, Chongjie Zhang
NeurIPS 2022 (CCF-A). Spotlight Paper. -
Incorporating Pragmatic Reasoning Communication into Emergent Language
Yipeng Kang, Tonghan Wang, Gerard de Melo
NeurIPS 2020 (CCF-A). Spotlight Paper.
Other works.
- RAM: Towards an Ever-Improving Memory System by Learning from Communications
Jiaqi Li, Xiaobo Wang, Wentao Ding, Zihao Wang, Yipeng Kang, Zixia Jia, Zilong Zheng.
Reported by 麻省理工科技评论.
- Reinforced Natural Language Interfaces via Entropy Decomposition
Xiaoran Wu, Yipeng Kang
Professional Services
Conference reviewer for NeurIPS 2023-2025, ICLR 2024-2025, ICML2025.
Program Committee AGI-25.
Other Experiences
- I was a freelance writer for 得到.
Students
- PhD Students: 涂文明 (BIGAI & SJTU), 陈国球 (BIGAI & BNU)， 何布帷(BIGAI & BUPT)
-
Other Students with Collaboration:
–IIIS, Tsinghua： 毛怡欢，杨乾澜
–Tong Class, Tsinghua： 吴廷钧，高晗晴，汪上砚，陈子昂
Update: 15th Sep 2024