Yang Yuan

Yang Yuan is now an assistant professor at IIIS, Tsinghua. He finished his undergraduate study at Peking University in 2012. Afterwards, he received his PhD at Cornell University in 2018, advised by Professor Robert Kleinberg. During his PhD, he was a visiting student at MIT/Microsoft New England (2014-2015) and Princeton University (2016 Fall). Before joining Tsinghua, he spent one year at MIT Institute for Foundations of Data Science (MIFODS) as a postdoc researcher. He works on AI+Healthcare, AI Theory and Applied Category Theory.

Personal honor:

Beijing Zhiyuan Young Scientists (2020)

2019 Forbes China 30 under 30 (Science List)

AI theory

Build theory foundation for AI with Category theory and Topos theory. Focus on theory inspired algorithm design, and characterization of the power of foundation models.

AI for math

Build foundation models that can prove theorems.

None

8. Jing Xu, Jiaye Teng, Yang Yuan, Andrew C. Yao, Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression, Conference on Neural Information Processing Systems (NeurIPS), 2023 查看PDF

7. Yifan Zhang, Haowei He, Zhiquan Tan, Yang Yuan, Trade-off Between Efficiency and Consistency for Removal-based Explanations, Conference on Neural Information Processing Systems (NeurIPS), 2023 查看PDF

6. Yang Yuan, On the Power of Foundation Models, International Conference on Machine Learning (ICML), 2023 查看PDF

5. Chenzhuang Du, Jiaye Teng, Tingle Li, Yichen Liu, Tianyuan Yuan, Yue Wang, Yang Yuan, Hang Zhao, On Uni-Modal Feature Learning in Supervised Multi-Modal Learning, International Conference on Machine Learning (ICML), 2023 查看PDF

4. Jiaye Teng, Bohang Zhang, Ruichen Li, Haowei He, Yequan Wang, Yan Tian, Yang Yuan, Finding Generalization Measures by Contrasting Signal and Noise, International Conference on Machine Learning (ICML), 2023 查看PDF

3. Jiaye Teng*, Chuan Wen*, Dinghuai Zhang*, Yoshua Bengio, Yang Gao, Yang Yuan, Predictive Inference with Feature Conformal Prediction, International Conference on Learning Representations (ICLR), 2023 查看PDF

2. Jiaye Teng, Jianhao Ma, Yang Yuan, Towards Understanding Generalization Via Decomposing Excess Risk Dynamics, International Conference on Learning Representations（ICLR), 2022.

1. Jiaye Teng , Zeren Tan , Yang Yuan, T-SCI: A Two-Stage Conformal Inference Algorithm with Guaranteed Coverage for Cox-MLP, International Conference on Machine Learning（ICML), 2021