PPaperPicks

Shuai Li

Shanghai Jiao Tong University, John Hopcroft Center for Computer Science, Shanghai, China

26 papers at tracked venues · 18 at CORE A* · active 2024–2025

DBLP profile ↗ORCID 0000-0002-3935-0708 ↗Google Scholar ↗Homepage ↗

Venues

ICML ×6NeurIPS ×6AAAI ×2ICLR ×2NAACL ×2WWW ×2AAMAS ×1AISTATS ×1CIKM ×1IJCAI ×1UAI ×1WSDM ×1

Frequent coauthors

Fang Kong
DBLP profile ↗ORCID search ↗
×4
Ruofeng Yang
DBLP profile ↗ORCID search ↗
×4
Canzhe Zhao
DBLP profile ↗ORCID search ↗
×3
Yu Xia
DBLP profile ↗ORCID search ↗
×3
Xu Liu
DBLP profile ↗ORCID search ↗
×2
Dongxie Wen
DBLP profile ↗ORCID search ↗
×1
Songwen Hu
DBLP profile ↗ORCID search ↗
×1
Xiao Huang
DBLP profile ↗ORCID search ↗
×1
Zilong Wang
DBLP profile ↗ORCID search ↗
×1
Zhihui Xie
DBLP profile ↗ORCID search ↗
×1
Xutong Liu
DBLP profile ↗ORCID search ↗
×1
Zhijie Wang
DBLP profile ↗ORCID search ↗
×1

Papers

  1. Adaptive Offline Data Replay in Offline-to-Online Reinforcement Learning
    AAMAS 2025 ·
    Xu Liu
    DBLP profile ↗ORCID search ↗
  2. Bandit Learning in Matching Markets with Indifference
    ICLR 2025 ·
    Fang Kong
    DBLP profile ↗ORCID search ↗
  3. Fast Second-Order Online Kernel Learning Through Incremental Matrix Sketching and Decomposition
    IJCAI 2025 ·
    Dongxie Wen
    DBLP profile ↗ORCID search ↗
  4. Improved Discretization Complexity Analysis of Consistency Models: Variance Exploding Forward Process and Decay Discretization Scheme
    ICML 2025 ·
    Ruofeng Yang
    DBLP profile ↗ORCID search ↗
  5. Interactive Visualization Recommendation with Hier-SUCB
    WWW 2025 ·
    Songwen Hu
    DBLP profile ↗ORCID search ↗
  6. Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit Feedback
    ICML 2025 ·
    Canzhe Zhao
    DBLP profile ↗ORCID search ↗
  7. Logarithmic Regret for Linear Markov Decision Processes with Adversarial Corruptions
    AAAI 2025 ·
    Canzhe Zhao
    DBLP profile ↗ORCID search ↗
  8. Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation
    ICML 2025 ·
    Xiao Huang
    DBLP profile ↗ORCID search ↗
  9. Optimal Algorithm for Max-Min Fair Bandit
    ICML 2025 ·
    Zilong Wang
    DBLP profile ↗ORCID search ↗
  10. The Polynomial Iteration Complexity for Variance Exploding Diffusion Models: Elucidating SDE and ODE Samplers
    AISTATS 2025 ·
    Ruofeng Yang
    DBLP profile ↗ORCID search ↗
  11. Towards Provably Efficient Learning of Imperfect Information Extensive-Form Games with Linear Function Approximation
    UAI 2025 ·
    Canzhe Zhao
    DBLP profile ↗ORCID search ↗
  12. Aligning as Debiasing: Causality-Aware Alignment via Reinforcement Learning with Interventional Feedback
    NAACL 2024 ·
    Yu Xia
    DBLP profile ↗ORCID search ↗
  13. Calibrating Reasoning in Language Models with Internal Consistency
    NeurIPS 2024 ·
    Zhihui Xie
    DBLP profile ↗ORCID search ↗
  14. Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and Beyond
    ICML 2024 ·
    Xutong Liu
    DBLP profile ↗ORCID search ↗
  15. Few-Shot Diffusion Models Escape the Curse of Dimensionality
    NeurIPS 2024 ·
    Ruofeng Yang
    DBLP profile ↗ORCID search ↗
  16. Hallucination Diversity-Aware Active Learning for Text Summarization
    NAACL 2024 ·
    Yu Xia
    DBLP profile ↗ORCID search ↗
  17. Improved Analysis for Bandit Learning in Matching Markets
    NeurIPS 2024 ·
    Fang Kong
    DBLP profile ↗ORCID search ↗
  18. Improved Bandits in Many-to-One Matching Markets with Incentive Compatibility
    AAAI 2024 ·
    Fang Kong
    DBLP profile ↗ORCID search ↗
  19. In-context Learning on Function Classes Unveiled for Transformers
    ICML 2024 ·
    Zhijie Wang
    DBLP profile ↗ORCID search ↗
  20. Interact with the Explanations: Causal Debiased Explainable Recommendation System
    WSDM 2024 ·
    Xu Liu
    DBLP profile ↗ORCID search ↗
  21. Learning Versatile Skills with Curriculum Masking
    NeurIPS 2024 ·
    Yao Tang
    DBLP profile ↗ORCID search ↗
  22. Leveraging Drift to Improve Sample Complexity of Variance Exploding Diffusion Models
    NeurIPS 2024 ·
    Ruofeng Yang
    DBLP profile ↗ORCID search ↗
  23. On Stationary Point Convergence of PPO-Clip
    ICLR 2024 ·
    Ruinan Jin
    DBLP profile ↗ORCID search ↗
  24. Sequential Optimum Test with Multi-armed Bandits for Online Experimentation
    CIKM 2024 ·
    Fang Kong
    DBLP profile ↗ORCID search ↗
  25. The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
    NeurIPS 2024 · Shuai Li
  26. Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing Bandits
    WWW 2024 ·
    Yu Xia
    DBLP profile ↗ORCID search ↗