Notice：
Research
Structural Intelligence
PI：Andrew Chi-Chih Yao. Yuan Yang
研究方向：Research on the integration of category theory, topos theory, and artificial intelligence
Email：
Introduction to the Research Group
Starting from fundamental theories such as category theory and topos theory, we analyze the intrinsic structures of mathematical proofs, automatic programming, or the training algorithms of artificial intelligence. Based on these structures, we design better AI algorithms. We aim to use theory to guide AI, rather than merely using theory to explain AI.
Research Achievements
Autonomous Data Selection with Zero-shot Generative Classifiers for Mathematical Texts, Yifan Zhang, Yifan Luo, Yang Yuan, Andrew C Yao, ACL 2025 Findings.
Hierarchical Attention Generates Better Proofs, Jianlong Chen, Chao Li, Yang Yuan, Andrew C Yao, ACL 2025 Main.
CatCode: A Comprehensive Evaluation Framework for LLMs On the Mixture of Code and Text, Zhenru Lin, Yiqun Yao, Yang Yuan, COLM 2024.
Matrix Information Theory for Self-Supervised Learning, Yifan Zhang, Zhiquan Tan, Jingqin Yang, Weiran Huang, Yang Yuan, ICML 2024.
Information Flow in Self-Supervised Learning, Zhiquan Tan, Jingqin Yang, Weiran Huang, Yang Yuan, Yifan Zhang, ICML 2024.
Contrastive Learning is Spectral Clustering on Similarity Graph, Zhiquan Tan, Yifan Zhang, Jingqin Yang, Yang Yuan, ICLR 2024.
On the Power of Foundation Models, Yang Yuan, ICML 2023.
Member Information
Students:
Luo Yifan (2024-)
Xu Kangping (co-advised with Professor Andrew Yao, 2024-)
Huang Ziru
Zhang Yifan (2021-2025, after graduation: pursuing a Ph.D. at Princeton University)