Robot policies using diffusion models for action generation.
Arman Akbari, Ci Zhang, Arash Akbari et al.
World-action models (WAMs) jointly generate future video and robot actions through iterative diffusion, achieving strong performance on manipulation benchmarks but requiring tens of denoising steps, a cost that precludes real-time control.
Jianing Guo, Fangzheng Chen, Zihao Mao et al.
Flow matching has emerged as a standard paradigm for robotic manipulation owing to its strong expressive power for modelling complex, multimodal action distributions, alongside similar approaches like diffusion policy.
Jianing Guo, Fangzheng Chen, Zihao Mao et al.
Flow matching has emerged as a standard paradigm for robotic manipulation owing to its strong expressive power for modelling complex, multimodal action distributions, alongside similar approaches like diffusion policy.
Shutong Ding, Zejia Zhong, Zhongyi Wang et al.
Recent advances in reinforcement learning (RL) have achieved great successes by leveraging the multimodality and exploration capability of diffusion policies. Among these approaches, one representativ
Read these papers in order to build expertise in Diffusion Policy.
Arman Akbari, Ci Zhang et al. · 2026
Jianing Guo, Fangzheng Chen et al. · 2026
Jianing Guo, Fangzheng Chen et al. · 2026
Shutong Ding, Zejia Zhong et al. · 2026
