{"id":15601073,"url":"https://github.com/lucidrains/diffusion-policy","last_synced_at":"2025-04-14T17:11:35.013Z","repository":{"id":196102023,"uuid":"694349556","full_name":"lucidrains/diffusion-policy","owner":"lucidrains","description":"Implementation of Diffusion Policy, Toyota Research's supposed breakthrough in leveraging DDPMs for learning policies for real-world Robotics","archived":false,"fork":false,"pushed_at":"2024-07-06T15:12:02.000Z","size":1069,"stargazers_count":106,"open_issues_count":2,"forks_count":2,"subscribers_count":4,"default_branch":"main","last_synced_at":"2025-04-14T17:11:31.083Z","etag":null,"topics":["artificial-intelligence","attention-mechanisms","deep-learning","denoising-diffusion","robotics","transformers"],"latest_commit_sha":null,"homepage":"","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/lucidrains.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-09-20T20:25:32.000Z","updated_at":"2025-03-30T16:54:24.000Z","dependencies_parsed_at":"2023-11-20T18:31:08.073Z","dependency_job_id":"9f36c2a1-4586-467c-8033-d1036ff3c76c","html_url":"https://github.com/lucidrains/diffusion-policy","commit_stats":null,"previous_names":["lucidrains/diffusion-policy"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Fdiffusion-policy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Fdiffusion-policy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Fdiffusion-policy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Fdiffusion-policy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lucidrains","download_url":"https://codeload.github.com/lucidrains/diffusion-policy/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248923765,"owners_count":21183953,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["artificial-intelligence","attention-mechanisms","deep-learning","denoising-diffusion","robotics","transformers"],"created_at":"2024-10-03T02:13:49.730Z","updated_at":"2025-04-14T17:11:34.981Z","avatar_url":"https://github.com/lucidrains.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg src=\"./diffusion-policy.png\" width=\"450px\"\u003e\u003c/img\u003e\n\n## Diffusion Policy (wip)\n\nImplementation of \u003ca href=\"https://arxiv.org/abs/2303.04137\"\u003eDiffusion Policy\u003c/a\u003e, Toyota Research's supposed \u003ca href=\"https://www.tri.global/news/toyota-research-institute-unveils-breakthrough-teaching-robots-new-behaviors\"\u003ebreakthrough\u003c/a\u003e in leveraging DDPMs for learning policies for real-world Robotics\n\nWhat seemed to have happened is that a research group at Columbia adapted the popular SOTA text-to-image models (complete with denoising diffusion with cross attention conditioning) to policy generation (predicting robot actions conditioned on observations). Toyota research then validated this at a certain scale for imitation learning with real world robotic demonstrations. It is hard to know how much of a breakthrough this is given corporate press is prone to exaggerations, but let me try to get a clean implementation out, just in the case that it is.\n\nThe great thing is, if this really works, all the advances being made in text-to-image space can translate to robotics. Yes, this includes stuff like dreambooth.\n\n\u003ca href=\"https://discord.gg/TYq72J3Cp4\"\u003eDiscord\u003c/a\u003e\n\n## Todo\n\n- [ ] add rlhf\n- [ ] add adversarial distillation\n\n## Citations\n\n```bibtex\n@article{Chi2023DiffusionPV,\n    title   = {Diffusion Policy: Visuomotor Policy Learning via Action Diffusion},\n    author  = {Cheng Chi and Siyuan Feng and Yilun Du and Zhenjia Xu and Eric A. Cousineau and Benjamin Burchfiel and Shuran Song},\n    journal = {ArXiv},\n    year    = {2023},\n    volume  = {abs/2303.04137},\n    url     = {https://api.semanticscholar.org/CorpusID:257378658}\n}\n```\n\n```bibtex\n@article{Sauer2023AdversarialDD,\n    title   = {Adversarial Diffusion Distillation},\n    author  = {Axel Sauer and Dominik Lorenz and A. Blattmann and Robin Rombach},\n    journal = {ArXiv},\n    year    = {2023},\n    volume  = {abs/2311.17042},\n    url     = {https://api.semanticscholar.org/CorpusID:265466173}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Fdiffusion-policy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flucidrains%2Fdiffusion-policy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Fdiffusion-policy/lists"}