My name is Binghui Li. I am a second-year Ph.D. student in The Center for Machine Learning Research (CMLR), Peking University, where I am extremely fortunate to be advised by Prof. Liwei Wang and Prof. Lei Wu. I am also pleased to have worked closely with Prof. Yuanzhi Li and Prof. Ruoyu Sun. Before joining CMLR, I received my Bachelor’s degree in Intelligence Science and Technology (Honor Track) from Turing Class, Peking University. My research area is machine learning, with special interests in understanding deep learning and algorithms inspired by theoretical insights. If you are interested, please feel free to contact me (libinghui@pku.edu.cn or WeChat)!

Education

• Ph.D. in Data Science (Computer Science and Technology), Peking University, 2023-2028 (Expected).
• B.S. in Intelligence Science and Technology (Summa Cum Laude), Peking University, 2019-2023.

Overall GPA: 3.82 / 4.00, Average Score: 90.2 / 100, Rank: 2 / 81

Invited Talk

• At International Joint Conference on Theoretical Computer Science – Frontier of Algorithmic Wisdom (IJTCS-FAW 2023), Robust Generalization Requires Exponentially Large Models [Slides]

• At the Turing Student Research Forum, Peking University, Robust Generalization Requires Exponentially Large Models [Video]

• At the Fourth BAAI Conference, Robust Generalization Requires Exponentially Large Models [Slides] [Video]

Publications & Preprints

• (Preprint) Feature Averaging: An Implicit Bias of Gradient Descent Leading to Non-Robustness in Neural Networks
  Binghui Li*, Zhixuan Pan*, Kaifeng Lyu, Jian Li

• (NeurIPS 2024 Workshop M3L) Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data
  Binghui Li, Yuanzhi Li

• (ICLR 2024 Workshop BGPT) Towards Understanding Clean Generalization and Robust Overfitting in Adversarial Training
  Binghui Li, Yuanzhi Li

• (NeurIPS 2022) Why Robust Generalization in Deep Learning is Difficult: Perspective of Expressive Power
  Binghui Li*, Jikai Jin*, Han Zhong, John E. Hopcroft, Liwei Wang

• (Preprint) Reconstruction Task Finds Universal Winning Tickets
  Ruichen Li, Binghui Li, Qi Qian, Liwei Wang

• (Preprint) Boosting Certified ℓ_∞ Robustness with EMA Method and Ensemble Model
  Binghui Li*, Shiji Xin*, Qizhe Zhang*

Teaching

• 2024 Fall: CS 33400 Discrete Mathematics and Structures, PKU (TA, with Prof. Tianren Liu)

• 2023 Fall: CS 33400 Discrete Mathematics and Structures, PKU (TA, with Prof. Tianren Liu)

• 2022 Fall: CS 33400 Discrete Mathematics and Structures, PKU (TA, with Prof. Xiaotie Deng)

• 2021 Fall: CS 33400 Discrete Mathematics and Structures, PKU (TA, with Prof. Xiaotie Deng)

Selected Courses

• Machine Learning: 93/100
• Numerical Methods (B): 95/100
• High-Dimensional Probability: 90/100
• Study and Practice on Topics of Frontier Computing (II): 96/100
• Introduction to the Theory of Computation: 92/100
• Mathematical Analysis (I): 97.5/100
• Discrete Mathematics and Structures (I): 97/100
• Probability Theory and Statistics (A): 96/100
• Python Programming and Application: 96/100
• Advanced Algebra (II): 99/100
• Practice of Programming in C&C++: 93/100
• Algorithm Design and Analysis (Honor Track): 91.5/100
• Information Theory: 90/100
• Mathematical Foundations for the Information Age: 92/100
• The Brain and Cognitive Science: 91/100

Selected Awards

• Peking University Elite Student Program for Applied Mathematics, 2024-2028 (Expected)
• President Scholarship of PKU, 2023
• Weiming Scholar of PKU, 2023 (top 1%, the highest honor for undergraduates in Peking University)
• Top 10 Bachelor Thesis of School of EECS, PKU, 2023
• Third Class Scholarship of PKU, 2022
• John Hopcroft Scholarship, 2021
• Peking University Collegiate Programming Contest, Third Prize, 2021
• Third Class Scholarship of PKU, 2020
• Chinese Mathematical Olympiad, Bronze Medal, 2018
• Chinese Southeast Mathematical Olympiad, Gold Medal, 2017
• Physics Olympiad of Shaanxi, Third Prize, 2017

Professional Service

• Conference reviewer of ICLR 2023/ NeurIPS 2024/ ICLR 2025/ AISTATS 2025
• Committee member of Turing Class Research Committee since 2020