-
FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies
Paper • 2603.27450 • Published -
Diffusion Reinforcement Learning via Centered Reward Distillation
Paper • 2603.14128 • Published -
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
Paper • 2604.18518 • Published • 7 -
GoRL: An Algorithm-Agnostic Framework for Online Reinforcement Learning with Generative Policies
Paper • 2512.02581 • Published • 15
🤝 Open to Collab
Dung Ngoc Pham
dzungpham
AI & ML interests
Reinforcement learning, diffusion models, representation learning and quantum computation (perhaps)
Organizations
-
FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies
Paper • 2603.27450 • Published -
Diffusion Reinforcement Learning via Centered Reward Distillation
Paper • 2603.14128 • Published -
UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
Paper • 2604.18518 • Published • 7 -
GoRL: An Algorithm-Agnostic Framework for Online Reinforcement Learning with Generative Policies
Paper • 2512.02581 • Published • 15