Lune

Profiles2021-2026

Ying Wen

Shanghai Jiao Tong University

16Papers
6Last author
19Unique co-authors
0First author
0Solo

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

Recent papers16

  1. ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function CallingAuthor 13 of 13ACL 2026 · 3 citations
  2. Offline Fictitious Self-Play for Competitive GamesAuthor 5 of 5AAAI 2026 · 1 citation
  3. Learning to Reason in Structured In-context Environments with Reinforcement LearningAuthor 6 of 6ICLR 2026
  4. Model-Based Imaginative Planning for Embodied AgentsAuthor 8 of 9ACL 2026
  5. Progra: Progress-Aware Reinforcement Learning for Multi-Turn Function CallingAuthor 14 of 14ACL Findings 2026
  6. SafeLab: An Interactive High-Fidelity Benchmark for Embodied Safety in Scientific RoboticsAuthor 11 of 14ICML 2026
  7. RAT: Adversarial Attacks on Deep Reinforcement Agents for Targeted BehaviorsAuthor 4 of 5AAAI 2025 · 15 citations
  8. Leveraging Dual Process Theory in Language Agent Framework for Real-time Simultaneous Human-AI CollaborationAuthor 13 of 13ACL 2025 · 14 citations
  9. Retrieval-Augmented Process Reward Model for Generalizable Mathematical ReasoningAuthor 5 of 8ACL Findings 2025
  10. Critic-Guided Decision Transformer for Offline Reinforcement LearningAuthor 3 of 5AAAI 2024 · 35 citations
  11. Reinforcing LLM Agents via Policy Optimization with Action DecompositionAuthor 5 of 5NeurIPS 2024 · 31 citations
  12. Aligning Individual and Collective Objectives in Multi-Agent CooperationAuthor 6 of 7NeurIPS 2024 · 15 citations
  13. TRAD: Enhancing LLM Agents with Step-Wise Thought Retrieval and Aligned DecisionAuthor 4 of 6SIGIR 2024 · 5 citations
  14. Cooperative Open-ended Learning Framework for Zero-Shot CoordinationAuthor 5 of 7ICML 2023 · 35 citations
  15. GEAR: A GPU-Centric Experience Replay System for Large Reinforcement Learning ModelsAuthor 4 of 8ICML 2023 · 5 citations
  16. Towards Unifying Behavioral and Response Diversity for Open-ended Learning in Zero-sum GamesAuthor 3 of 8NeurIPS 2021 · 67 citations
Dusk over the sea between two cliffs drawn in fine vertical lines