Profiles2023-2026
Lu Wang
Microsoft
7Papers
0Last author
16Unique co-authors
1First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers7
- Text2Grad: Reinforcement Learning from Natural Language FeedbackAuthor 2 of 8ICLR 2026 · 18 citations
- Pretrain Value, Not Reward: Decoupled Value Policy OptimizationAuthor 2 of 7ICLR 2026 · 4 citations
- RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to RepositoryAuthor 5 of 10ACL 2026 · 4 citations
- Zipage: Maintain High Request Concurrency for LLM Reasoning through Compressed PagedAttentionAuthor 2 of 9ACL Findings 2026
- LettinGo: Explore User Profile Generation for Recommendation SystemAuthor 1 of 14KDD 2025 · 2 citations
- Self-Evolved Reward Learning for LLMSAuthor 3 of 10ICLR 2025
- Conservative State Value Estimation for Offline Reinforcement LearningAuthor 4 of 8NeurIPS 2023 · 15 citations
