Lune

Profiles2020-2026

Shuai Li

Shanghai Jiao Tong University

37Papers
25Last author
41Unique co-authors
3First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers37

  1. Multi-Subspace Multi-Modal Modeling for Diffusion Models: Estimation, Convergence and Mixture of ExpertsAuthor 5 of 5ICLR 2026 · 4 citations
  2. Interactive Visualization Recommendation with Hier-SUCBAuthor 7 of 7WWW 2025 · 2 citations
  3. Logarithmic Regret for Linear Markov Decision Processes with Adversarial CorruptionsAuthor 4 of 4AAAI 2025 · 1 citation
  4. Improved Discretization Complexity Analysis of Consistency Models: Variance Exploding Forward Process and Decay Discretization SchemeAuthor 4 of 4ICML 2025
  5. Learning Imperfect Information Extensive-form Games with Last-iterate Convergence under Bandit FeedbackAuthor 5 of 5ICML 2025
  6. Learning Preferences without Interaction for Cooperative AI: A Hybrid Offline-Online ApproachAuthor 4 of 4NeurIPS 2025
  7. Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion GenerationAuthor 5 of 5ICML 2025
  8. Online-to-Offline RL for Agent AlignmentAuthor 5 of 5ICLR 2025
  9. Optimal Algorithm for Max-Min Fair BanditAuthor 3 of 3ICML 2025
  10. The Closeness of In-Context Learning and Weight Shifting for Softmax RegressionAuthor 1 of 5NeurIPS 2024 · 53 citations
  11. Calibrating Reasoning in Language Models with Internal ConsistencyAuthor 4 of 4NeurIPS 2024 · 37 citations
  12. Which LLM to Play? Convergence-Aware Online Model Selection with Time-Increasing BanditsAuthor 7 of 7WWW 2024 · 33 citations
  13. On Stationary Point Convergence of PPO-ClipAuthor 2 of 3ICLR 2024 · 14 citations
  14. Few-Shot Diffusion Models Escape the Curse of DimensionalityAuthor 6 of 6NeurIPS 2024 · 13 citations
  15. Improved Bandits in Many-to-One Matching Markets with Incentive CompatibilityAuthor 2 of 2AAAI 2024 · 10 citations
  16. Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and BeyondAuthor 7 of 10ICML 2024 · 9 citations
  17. Improved Analysis for Bandit Learning in Matching MarketsAuthor 3 of 3NeurIPS 2024 · 8 citations
  18. In-context Learning on Function Classes Unveiled for TransformersAuthor 3 of 3ICML 2024 · 8 citations
  19. Leveraging Drift to Improve Sample Complexity of Variance Exploding Diffusion ModelsAuthor 4 of 4NeurIPS 2024 · 7 citations
  20. Future-conditioned Unsupervised Pretraining for Decision TransformerAuthor 6 of 6ICML 2023 · 32 citations
  21. Efficient Explorative Key-Term Selection Strategies for Conversational Contextual BanditsAuthor 3 of 4AAAI 2023 · 18 citations
  22. Few-Shot Composition Learning for Image Retrieval with Prompt TuningAuthor 6 of 7AAAI 2023 · 16 citations
  23. Online Clustering of Bandits with Misspecified User ModelsAuthor 4 of 5NeurIPS 2023 · 16 citations
  24. Online Corrupted User Detection and Regret MinimizationAuthor 4 of 5NeurIPS 2023 · 8 citations
  25. Player-optimal Stable Regret for Bandit Learning in Matching MarketsAuthor 2 of 2SODA 2023 · 6 citations
  26. Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information FeedbackAuthor 5 of 5NeurIPS 2023 · 5 citations
  27. Understanding Representation Learnability of Nonlinear Self-Supervised LearningAuthor 4 of 4AAAI 2023 · 3 citations
  28. Simultaneously Learning Stochastic and Adversarial Bandits with General Graph FeedbackAuthor 3 of 3ICML 2022 · 8 citations
  29. Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based ModelAuthor 3 of 3AAAI 2022 · 5 citations
  30. Discovering Low-rank Subspaces for Language-agnostic Multilingual RepresentationsAuthor 4 of 4EMNLP 2022 · 3 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines