Jiafei Lyu

7

Papers

2

Total Citations

Papers (7)

ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning

NeurIPS 2025arXiv

Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning

SUMO: Search-Based Uncertainty Estimation for Model-Based Offline Reinforcement Learning

Using Human Feedback to Fine-tune Diffusion Models without Any Reward Model

Cross-Domain Policy Adaptation by Capturing Representation Mismatch

Exploration and Anti-Exploration with Distributional Random Network Distillation

PEARL: Zero-shot Cross-task Preference Alignment and Robust Reward Learning for Robotic Manipulation