Lune

Profiles2022-2026

Siwei Wang

Microsoft Research Asia, Beijing

11Papers
0Last author
24Unique co-authors
1First author
0Solo

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

Recent papers11

  1. PaT: Planning-after-Trial for Efficient Test-Time Code GenerationAuthor 4 of 6ACL 2026
  2. Mechanism Design for LLM Fine-tuning with Multiple Reward ModelsAuthor 3 of 6NeurIPS 2025 · 26 citations
  3. ALPINE: Unveiling The Planning Capability of Autoregressive Learning in Language ModelsAuthor 1 of 6NeurIPS 2024 · 18 citations
  4. Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human FeedbackAuthor 4 of 6ICLR 2024 · 12 citations
  5. Whittle Index with Multiple Actions and State Constraint for Inventory ManagementAuthor 5 of 7ICLR 2024 · 10 citations
  6. Combinatorial Multivariant Multi-Armed Bandits with Applications to Episodic Reinforcement Learning and BeyondAuthor 2 of 10ICML 2024 · 9 citations
  7. Provable Risk-Sensitive Distributional Reinforcement Learning with General Function ApproximationAuthor 3 of 4ICML 2024 · 3 citations
  8. Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst PathAuthor 2 of 3ICLR 2023 · 2 citations
  9. Batch-Size Independent Regret Bounds for Combinatorial Semi-Bandits with Probabilistically Triggered Arms or Independent ArmsAuthor 3 of 6NeurIPS 2022 · 31 citations
  10. Combinatorial Bandits with Linear Constraints: Beyond Knapsacks and FairnessAuthor 3 of 4NeurIPS 2022 · 28 citations
  11. Matching in Multi-arm Bandit with CollisionAuthor 2 of 3NeurIPS 2022 · 18 citations
Dusk over the sea between two cliffs drawn in fine vertical lines