publications

publications by categories in reversed chronological order. generated by jekyll-scholar.

2026

  1. Preprint
    On the Complexity of Offline Reinforcement Learning with Q*-Approximation and Partial Coverage
    (α-β) Haolin Liu, Braham Snyder, and Chen-Yu Wei
    2026
    PDF
  2. ICLR
    An Improved Model-Free Decision-Estimation Coefficient with Applications in Adversarial MDPs
    (α-β) Haolin Liu, Chen-Yu Wei, and Julian Zimmert
    ICLR, 2026
    PDF
  3. ICLR
    CDE: Curiosity-driven Exploration for Efficient Reinforcement Learning in Large Language Models
    Runpeng Dai, Linfeng Song, Haolin Liu, Zhenwen Liang, Dian Yu, Haitao Mi, Zhaopeng Tu, Rui Liu, Tong Zheng, Hongtu Zhu, and 1 more author
    ICLR, 2026
    PDF

2025

  1. MATH-AI
    Evolving Language Models without Labels: Majority Drives Selection, Novelty Promotes Variation
    Yujun Zhou, Zhenwen Liang, Haolin Liu, Wenhao Yu, Kishan Panaganti, Linfeng Song, Dian Yu, Xiangliang Zhang, Haitao Mi, and Dong Yu
    NeurIPS 2025 MATH-AI Workshop, 2025
    PDF
  2. MATH-AI
    One Token to Fool LLM-as-a-Judge
    Yulai Zhao*, Haolin Liu*, Dian Yu, S.Y. Kung, Haitao Mi, and Dong Yu
    NeurIPS 2025 MATH-AI Workshop, 2025
    PDF
  3. Preprint
    RAG-Gym: Systematic Optimization of Language Agents for Retrieval-Augmented Generation
    Guangzhi Xiong*, Qiao Jin*, Xiao Wang, Yin Fang, Haolin Liu, Yifan Yang, Fangyuan Chen, Zhixing Song, Dengyu Wang, Minjia Zhang, and 2 more authors
    2025
    PDF
  4. COLT
    Decision Making in Hybrid Environments: A Model Aggregation Approach
    (α-β) Haolin Liu, Chen-Yu Wei, and Julian Zimmert
    COLT, 2025
    PDF
  5. AAAI
    Sample Complexity of Opinion Formation on Networks (Oral)
    (α-β) Haolin Liu, Rajmohan Rajaraman, Ravi Sundaram, Anil Vullikanti, Omer Wasim, and Haifeng Xu
    AAAI, 2025
    PDF

2024

  1. NeurIPS
    Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
    (α-β) Haolin Liu, Zakaria Mhammedi, Chen-Yu Wei, and Julian Zimmert
    NeurIPS, 2024
    PDF
  2. NeurIPS
    Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification
    (α-β) Haolin Liu, Artin Tajdini, Andrew Wagenmaker, and Chen-Yu Wei
    NeurIPS, 2024
    PDF
  3. ICLR
    Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback (Spotlight)
    (α-β) Haolin Liu, Chen-Yu Wei, and Julian Zimmert
    ICLR, 2024
    PDF

2023

  1. NeurIPS
    Bypassing the simulator: Near-optimal adversarial linear contextual bandits
    (α-β) Haolin Liu, Chen-Yu Wei, and Julian Zimmert
    NeurIPS, 2023
    PDF
  2. AAMAS/ECAI
    Diffusion multi-unit auctions with diminishing marginal utility buyers
    Haolin Liu*, Xinyuan Lian*, and Dengji Zhao
    AAMAS (also in ECAI), 2023
    PDF