Liyuan Mao
发表论文 11 篇 · 总被引 245 次 · h-index 5
代表论文
- Diffusion-Based Planning for Autonomous Driving with Flexible Guidance (2025 · International Conference on Learning Representations · 被引 174)
- Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning (2024 · Neural Information Processing Systems · 被引 47)
- ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update (2024 · International Conference on Learning Representations · 被引 30)
- DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning (2024 · International Conference on Machine Learning · 被引 24)
- Why Distillation can Outperform Zero-RL: The Role of Flexible Reasoning (2025 · arXiv.org · 被引 13)
- Information-Theoretic Reward Decomposition for Generalizable RLHF (2025 · Neural Information Processing Systems · 被引 6)