Scholar
Haolin Liu
Google Scholar ID: DgvwKhgAAAAJ
University of Virginia
Citations & Impact
Citations
65
H-index
4
i10-index
4
Publications
13
Co-authors
11
list available
Publications
Resume
Academic Achievements
- An Improved Model-Free Decision-Estimation Coefficient with Applications in Adversarial MDPs (2025, Preprint)
- One Token to Fool LLM-as-a-Judge (NeurIPS 2025 MATH-AI Workshop)
- Decision Making in Hybrid Environments: A Model Aggregation Approach (COLT 2025)
- Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback (NeurIPS 2024)
- Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification (NeurIPS 2024)
- Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback (ICLR 2024, Spotlight)
- Bypassing the simulator: Near-optimal adversarial linear contextual bandits (NeurIPS 2023)
Background
- Third-year PhD student in the Department of Computer Science at the University of Virginia
- Research centered on Reinforcement Learning (RL), spanning both theoretical and practical domains
- Theoretical focus: advancing understanding of how RL algorithms learn and adapt in dynamic environments
- Practical focus: applying RL to post-training of large language models (LLMs), with emphasis on alignment and reasoning
- Also has experience in game theory and mechanism design
