Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
Robot control is formulated as conditional denoising of action sequences, linking diffusion models to visuomotor learning.
A vision-language-action system studies generalization across environments and tasks using varied sources of supervision.
Location refers to credited institutions or the listed organization, not author citizenship or an exhaustive collaboration list.
Look at what “open-world” means in the experiments rather than assuming universal capability.
@misc{intelligence2025vision,
title = {π0.5: a Vision-Language-Action Model with Open-World Generalization},
author = {Physical Intelligence and Kevin Black and Noah Brown and James Darpinian and Karan Dhabalia and Danny Driess and Adnan Esmail and Michael Equi and Chelsea Finn and Niccolo Fusai and Manuel Y. Galliker and Dibya Ghosh and Lachy Groom and Karol Hausman and Brian Ichter and Szymon Jakubczak and Tim Jones and Liyiming Ke and Devin LeBlanc and Sergey Levine and Adrian Li-Bell and Mohith Mothukuri and Suraj Nair and Karl Pertsch and Allen Z. Ren and Lucy Xiaoyang Shi and Laura Smith and Jost Tobias Springenberg and Kyle Stachowicz and James Tanner and Quan Vuong and Homer Walke and Anna Walling and Haohuan Wang and Lili Yu and Ury Zhilinsky},
year = {2025},
eprint = {2504.16054},
archivePrefix = {arXiv},
primaryClass = {cs.LG},
url = {https://arxiv.org/abs/2504.16054}
}Rights remain with the original authors. Refer to the original source for citations and licensing.
Robot control is formulated as conditional denoising of action sequences, linking diffusion models to visuomotor learning.
Vision-language models are trained to produce robot actions, exploring transfer from web-scale learning to robotic control.
An open vision-language-action model and adaptation framework make generalist robot policy research more accessible.