About Me
I am a second-year Ph.D. student in Computer Science and Technology at Nanjing University of Aeronautics and Astronautics (NUAA), advised by Professor Sheng-Jun Huang.
My research focuses on the foundations and practical applications of reinforcement learning (RL), with an emphasis on three main areas:
- Fundamental RL algorithms, including offline RL, offline-to-online RL, and skill-based RL.
- RL for large language models (LLMs), particularly the use of RL to improve their reasoning capabilities.
- Real-world applications of RL in embodied AI, including RL for vision-language-action (VLA) models and world action models (WAMs).
I am always happy to discuss research, explore collaborations, and connect with people who share similar interests.
News
- 2026-5One first-author paper has been accepted by KDD 2026 (CCF-A).
- 2025-7One co-first-author paper has been accepted by ECAI 2025 (CCF-B).
- 2025-5One first-author paper has been accepted by ICML 2025 (CCF-A).
- 2024-10One first-author paper has been accepted by NeurIPS 2024 (CCF-A).
Publications
View All →Compress the Easy, Explore the Hard: Difficulty-Aware Entropy Regularization for Efficient LLM Reasoning
Qin-Wen Luo, Sheng Ren, Xiang Chen*, Rui Liu, Jun Fang, Naiqiang Tan, Sheng-Jun Huang*
KDD 2026 (CCF-A)
Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL
Qin-Wen Luo, Ming-Kun Xie, Ye-Wen Wang, Sheng-Jun Huang*
ICML 2025 (CCF-A)
Conservative Query and Adaptive Regularization for Offline RL under Uncertainty Estimation
Li-Rong Zhou, Qin-Wen Luo†, Sheng-Jun Huang*
ECAI 2025 (CCF-B)
Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL
Qin-Wen Luo, Ming-Kun Xie, Ye-Wen Wang, Sheng-Jun Huang*
NeurIPS 2024 (CCF-A)