PPaperPicks

John C. S. Lui

Chinese University of Hong Kong, Department of Computer Science and Engineering, Hong Kong

32 papers at tracked venues · 29 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-7466-0384 ↗Homepage ↗

Venues

ICML ×8AAAI ×5ICLR ×4NeurIPS ×3SIGKDD ×3ICDE ×2WWW ×2ACL ×1ACM MM ×1AISTATS ×1ECAI ×1IJCAI ×1

Frequent coauthors

Zhiyong Wang
DBLP profile ↗ORCID search ↗
×4
Xiangxiang Dai
DBLP profile ↗ORCID search ↗
×3
Jin Cheng
DBLP profile ↗ORCID search ↗
×3
Chengchang Liu
DBLP profile ↗ORCID search ↗
×3
Zhuohua Li
DBLP profile ↗ORCID search ↗
×3
Xuchuang Wang
DBLP profile ↗ORCID search ↗
×3
Xutong Liu
DBLP profile ↗ORCID search ↗
×2
Jiahang Sun
DBLP profile ↗ORCID search ↗
×1
Manhin Poon
DBLP profile ↗ORCID search ↗
×1
Fang Kong
DBLP profile ↗ORCID search ↗
×1
Ruhan Wang
DBLP profile ↗ORCID search ↗
×1
Maoli Liu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. A Multi-Agent Conversational Bandit Approach to Online Evaluation and Selection of User-Aligned LLM Responses
    AAAI 2026 ·
    Xiangxiang Dai
    DBLP profile ↗ORCID search ↗
  2. BANCO: Drift-Aware Batched Bandits for Adaptive Proximity Graph Pruning
    WWW 2026 ·
    Jin Cheng
    DBLP profile ↗ORCID search ↗
  3. Large Language Model-Enhanced Multi-Armed Bandits
    ACL 2026 ·
    Jiahang Sun
    DBLP profile ↗ORCID search ↗
  4. Online Multi-LLM Selection via Contextual Bandits Under Unstructured Context Evolution
    AAAI 2026 ·
    Manhin Poon
    DBLP profile ↗ORCID search ↗
  5. Trading Vector Data in Vector Databases
    ICDE 2026 ·
    Jin Cheng
    DBLP profile ↗ORCID search ↗
  6. A Unified Online-Offline Framework for Co-Branding Campaign Recommendations
    SIGKDD 2025 ·
    Xiangxiang Dai
    DBLP profile ↗ORCID search ↗
  7. An Enhanced Levenberg-Marquardt Method via Gram Reduction
    AAAI 2025 ·
    Chengchang Liu
    DBLP profile ↗ORCID search ↗
  8. Bandit Learning in Matching Markets with Indifference
    ICLR 2025 ·
    Fang Kong
    DBLP profile ↗ORCID search ↗
  9. Demystifying Online Clustering of Bandits: Enhanced Exploration Under Stochastic and Smoothed Adversarial Contexts
    ICLR 2025 ·
    Zhuohua Li
    DBLP profile ↗ORCID search ↗
  10. Federated In-Context Learning: Iterative Refinement for Improved Answer Quality
    ICML 2025 ·
    Ruhan Wang
    DBLP profile ↗ORCID search ↗
  11. Fusing Reward and Dueling Feedback in Stochastic Bandits
    ICML 2025 ·
    Xuchuang Wang
    DBLP profile ↗ORCID search ↗
  12. Leveraging the Power of Conversations: Optimal Key Term Selection in Conversational Contextual Bandits
    SIGKDD 2025 ·
    Maoli Liu
    DBLP profile ↗ORCID search ↗
  13. Model-based RL as a Minimalist Approach to Horizon-Free and Second-Order Bounds
    ICLR 2025 ·
    Zhiyong Wang
    DBLP profile ↗ORCID search ↗
  14. OSTOR: Online Scheduling Framework for Trading Continuous Queries
    ICDE 2025 ·
    Jin Cheng
    DBLP profile ↗ORCID search ↗
  15. Offline Learning for Combinatorial Multi-armed Bandits
    ICML 2025 ·
    Xutong Liu
    DBLP profile ↗ORCID search ↗
  16. Online Clustering of Dueling Bandits
    ICML 2025 ·
    Zhiyong Wang
    DBLP profile ↗ORCID search ↗
  17. Provable Zero-Shot Generalization in Offline Reinforcement Learning
    ICML 2025 ·
    Zhiyong Wang
    DBLP profile ↗ORCID search ↗
  18. Quantum Algorithms for Finite-horizon Markov Decision Processes
    ICML 2025 ·
    Bin Luo
    DBLP profile ↗ORCID search ↗
  19. Quantum Best Arm Identification with Quantum Oracles
    AAAI 2025 ·
    Xuchuang Wang
    DBLP profile ↗ORCID search ↗
  20. Quantum Speedups for Minimax Optimization and Beyond
    NeurIPS 2025 ·
    Chengchang Liu
    DBLP profile ↗ORCID search ↗
  21. Stochastic Bandits Robust to Adversarial Attacks
    ICLR 2025 ·
    Xuchuang Wang
    DBLP profile ↗ORCID search ↗
  22. Time Matters: Enhancing Sequential Recommendations with Time-Guided Graph Neural ODEs
    SIGKDD 2025 ·
    Haoyan Fu
    DBLP profile ↗ORCID search ↗
  23. Towards Efficient Conversational Recommendations: Expected Value of Information Meets Bandit Learning
    WWW 2025 ·
    Zhuohua Li
    DBLP profile ↗ORCID search ↗
  24. Variance-Dependent Regret Bounds for Nonstationary Linear Bandits
    AISTATS 2025 ·
    Zhiyong Wang
    DBLP profile ↗ORCID search ↗
  25. AxiomVision: Accuracy-Guaranteed Adaptive Visual Model Selection for Perspective-Aware Video Analytics
    ACM MM 2024 ·
    Xiangxiang Dai
    DBLP profile ↗ORCID search ↗
  26. Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond
    ICML 2024 ·
    Xutong Liu
    DBLP profile ↗ORCID search ↗
  27. D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models
    NeurIPS 2024 ·
    Yikun Jiang
    DBLP profile ↗ORCID search ↗
  28. FedConPE: Efficient Federated Conversational Bandits with Heterogeneous Clients
    IJCAI 2024 ·
    Zhuohua Li
    DBLP profile ↗ORCID search ↗
  29. Federated Contextual Cascading Bandits with Asynchronous Communication and Heterogeneous Users
    AAAI 2024 ·
    Hantao Yang
    DBLP profile ↗ORCID search ↗
  30. Merit-Based Fair Combinatorial Semi-Bandit with Unrestricted Feedback Delays
    ECAI 2024 ·
    Ziqun Chen
    DBLP profile ↗ORCID search ↗
  31. Quantum Algorithm for Online Exp-concave Optimization
    ICML 2024 ·
    Jianhao He
    DBLP profile ↗ORCID search ↗
  32. Quantum Algorithms for Non-smooth Non-convex Optimization
    NeurIPS 2024 ·
    Chengchang Liu
    DBLP profile ↗ORCID search ↗