Biography
I am a final-year PhD candidate in CS at UVa and will be joining STOR at UNC as a tenure-track assistant professor. My advisors are Prof. Haifeng Xu and Prof. Hongning Wang. Currently I’m interested in modeling human-AI interactions, with the goal of understanding their societal implications and designing interventions that promote social good. If you are interested in collaboration, feel free to drop an email!
Download my resumé.
Interests
- Social aspects of AI
- Multi-agent modeling
- Algorithmic game theory
- Online learning
Education
-
Ph.D. in Computer Science, 2025
University of Virginia
-
MSc. in Computational Mathematics, 2016
Peking University
-
BSc. in Computational Mathematics, 2013
Peking University
Working Papers
indicates equal contribution, authors in alphabetical order.
Publications
indicates equal contribution, authors in alphabetical order.
(2024).
Single-Agent Poisoning Attacks Suffice to Ruin Multi-Agent Learning.
ICLR, 2025.
ICLR, 2025.
(2024).
Learning from Imperfect Human Feedback: a Tale from Corruption-Robust Dueling.
ICLR, 2025.
ICLR, 2025.
(2024).
Unveiling User Satisfaction and Creator Productivity Trade-Offs in Recommendation Platforms.
Neurips, 2024.
Neurips, 2024.
(2024).
Human vs Generative AI in Content Creation Competition: Symbiosis or Conflict?.
ICML, 2024
Oral presented at Econometric Society Interdisciplinary Frontiers (ESIF) conference on Economics and AI+ML.
ICML, 2024
Oral presented at Econometric Society Interdisciplinary Frontiers (ESIF) conference on Economics and AI+ML.
(2024).
User Welfare Optimization in Recommender Systems with Competing Content Creators.
KDD, 2024.
KDD, 2024.
(2023).
Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial?.
Neurips, 2023.
Neurips, 2023.
(2023).
How Bad is Top- Recommendation under Competing Content Creators?.
ICML, 2023 (oral presentation, 2.4%).
ICML, 2023 (oral presentation, 2.4%).
(2022).
Learning from a Learning User for Optimal Recommendations.
ICML, 2022
Selected as spotlight presentation at ICML, 2023, Workshop on Interactive Learning with Implicit Human Feedback.
ICML, 2022
Selected as spotlight presentation at ICML, 2023, Workshop on Interactive Learning with Implicit Human Feedback.
(2022).
Multi-Agent Learning for Iterative Dominance Elimination: Formal Barriers and New Algorithms.
COLT, 2022
Extended version under major revision at JMLR.
COLT, 2022
Extended version under major revision at JMLR.
(2022).
Learning the Optimal Recommendation from Explorative Users.
AAAI, 2022.
AAAI, 2022.
(2022).
Reversible Action Design for Combinatorial Optimization with Reinforcement Learning.
AAAI-ML4OR, 2022.
AAAI-ML4OR, 2022.
(2021).
PAC-Learning for Strategic Classification.
The Journal of Machine Learning Research (JMLR)
Shorter version at ICML, 2021 (oral presentation, 3%).
The Journal of Machine Learning Research (JMLR)
Shorter version at ICML, 2021 (oral presentation, 3%).
Experience
Graduate Research Assistant
Ph.D. candidate in CS department
Visiting Student
Multi-agent and economic modeling for online content market.
Student Researcher
- Host: Dr. Qifan Wang
- Deploy mechanism design solutions for improving user engagement on Instagram Reels.
Student Researcher
- Manager: Dr. Chih-wei Hsu, Dr. Craig Boutilier
- Bayesian preference elicitation in interactive recommender systems using Concept Activation Vectors.
Research Intern
- Manager: Dr. Chong Wang, Dr. Taiqing Wang
- Enhance the recommendation diversity and mitigate the echo chamber effect via collaborative Thompson sampling approach and gradient-based Determinantal Point Processes.
Algorithm Engineer
Design and maintain content recommendation system for Taobao main page, focusing on deep-learning based match and ranking solution.
Featured Publications
Contact
- fy4bc@virginia.edu
- +1 434 227 6287
- Rice Hall, 85 Engineer's Way, Charlottesville, VA 22904