Here are some topics I am recently interested in:
AI safety & reliability (e.g., risk control of AI systems, uncertainty quantification)
Collaborative intelligence in multi-agent systems (e.g., agentic communication, human-AI collaboration)
Efficient and scalable ML (e.g., efficient reasoning, test-time scaling, self-evolving)
AI for X (e.g., AI for mathematics, AI for finance)
Departmental Seminar 2025, Statistics & Operations Research, UNC, "New Frontiers on Performativity: Inference and Risk Control".
TOC4Fairness Seminar, 2025, "Responsible Learning with Quantile-Based Risk Measures".
Departmental Statistical Seminar 2025, Statistic Department, Michigan State University, "Responsible Learning with Quantile-Based Risk Measures".
Lunch Seminar 2024, Center for Data Science, NYU, "Taming the Beast: Practical Theories for Responsible Machine Learning".
Theory Lunch Seminar 2024, CMU, "Taming the Beast: Practical Theories for Responsible Machine Learning".
Penn Research in Machine Learning forum 2024, University of Pennsylvania, "Knowing the Unknowns: Uncertainty Quantification for Responsible AI Deployment".
ITCS 2023, "Happymap: a generalized multi-calibration method".
AI TIME, one hour talk, 2022 "Reinforcement Learning with Stepwise Fairness Constraints".
Microsoft Research Asia, Beijing, 2022, "New Tools in Algoritmic Statbility".
JSM 2022, "Obtaining More Generalizable Fair Classifiers on Imbalanced Datasets".
ICML 2022, long talk "Robustness Implies Generalization via Data-dependent Generalization Bounds".
Simons Institute for the Theory of Computing, Data Privacy: Foundations and Applications Reunion, 2022 "Scaffolding Sets".
Tsinghua University, AI TIME, 2022 "Adversarial Training Encourages More Transferable Representations".
NeurIPS 2021, "Adversarial Training Helps Transfer Learning via Better Representations".
ICML 2021, "Towards Better Generalization Bounds with Locally Elastic Stability".
ICLR 2021, "How Does Mixup Helps Robustness and Generalization".
AISTATS 2021, "Improving Adversarial Robustness via Unalabeled Out-of-Domain Data".
ICML 2020, "The Optimization Landscape of the First-Order Adversaries".
University of Minnesota Twin Cities, Jie Ding's Group, 2018 "Recent Advances in Differential Privacy: Theory And Application".
I am grateful for the kind and generous support from the following sponsors.
