Scholar
Zhihan Xiong
Google Scholar ID: OsSiEMEAAAAJ
University of Washington
Citations & Impact
Citations
103
H-index
5
i10-index
2
Publications
14
Co-authors
7
list available
Publications
Resume (English only)
Academic Achievements
- - Publications:
- * Hybrid Preference Optimization for Alignment: Faster Convergence Rates by Combining Offline Preferences with Online Exploration
- * Language Model Preference Evaluation with Multiple Weak Evaluators
- * Policy Mirror Descent with Dual Function Approximation
- * LoRe: Personalizing LLMs via Low-Rank Reward Modeling
- * A/B Testing and Best-arm Identification for Linear Bandits with Robustness to Non-stationarity
- * A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
- * Offline Congestion Games: How Feedback Type Affects Data Coverage Requirement
- * Learning in Congestion Games with Bandit Feedback
- * Near-Optimal Randomized Exploration for Tabular Markov Decision Processes
- * Fourier Learning with Cyclical Data
- * Selective Sampling for Online Best-arm Identification
- * Parameterized Indexed Value Function for Efficient Exploration in Reinforcement Learning
- - Conference Papers:
- * COLM 2025, AISTATS 2024, CODE@MIT 2023, ICLR 2024, NeurIPS 2022, ICML 2022, NeurIPS 2021, AAAI 2020
Research Experience
- - Visiting Researcher at Meta (FAIR Labs), Oct 2022 -- Sep 2024
- - Research Intern at Bytedance (AML Group), Jun 2021 -- Sep 2021
- - Applied Scientist Intern at Zillow (Personalization Team), Jun 2019 -- Sep 2019
Education
- - Ph.D. in Computer Science & Engineering from the Paul G. Allen School of Computer Science & Engineering, University of Washington, 2025, Advisor: Prof. Maryam Fazel
- - Master's Degree in Statistics from Stanford University, 2020
- - Bachelor's Degree in Mathematics and Engineering Physics from University of Illinois at Urbana-Champaign, 2018, Advisor: Prof. Pierre Moulin
Background
- - Research Interests: Theory and application of reinforcement learning and bandit problems
- - Current Position: Research Scientist at Meta
- - Advisor: Prof. Maryam Fazel
- - Collaborators: Prof. Simon S. Du, Prof. Kevin Jamieson, Dr. Lin Xiao
Miscellany
- - Reviewer for: ICML (2021, 2022, 2023, 2024), NeurIPS (2021, 2022, 2023) and ICLR (2022, 2023, 2024)
- - Teaching Experiences:
- * CSE 541: Interactive Learning, Teaching Assistant, Spring 2025, University of Washington
- * CSE/EE/ME 578: Convex Optimization, Teaching Assistant, Winter 2025, University of Washington
