{"id":34705195,"url":"https://github.com/lucidrains/locoformer","last_synced_at":"2026-02-09T21:18:54.798Z","repository":{"id":316593778,"uuid":"1064036265","full_name":"lucidrains/locoformer","owner":"lucidrains","description":"LocoFormer - Generalist Locomotion via Long-Context Adaptation","archived":false,"fork":false,"pushed_at":"2026-01-22T15:05:19.000Z","size":36197,"stargazers_count":97,"open_issues_count":1,"forks_count":4,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-01-23T09:57:34.351Z","etag":null,"topics":["adaptation","artificial-intelligence","attention-mechanisms","cross-embodiment","deep-learning","locomotion","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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-25T13:02:18.000Z","updated_at":"2026-01-22T15:05:52.000Z","dependencies_parsed_at":"2026-01-12T12:03:33.598Z","dependency_job_id":null,"html_url":"https://github.com/lucidrains/locoformer","commit_stats":null,"previous_names":["lucidrains/locoformer"],"tags_count":131,"template":false,"template_full_name":null,"purl":"pkg:github/lucidrains/locoformer","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Flocoformer","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Flocoformer/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Flocoformer/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Flocoformer/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/lucidrains","download_url":"https://codeload.github.com/lucidrains/locoformer/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/lucidrains%2Flocoformer/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29281763,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-09T19:05:41.198Z","status":"ssl_error","status_checked_at":"2026-02-09T19:05:37.449Z","response_time":56,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":["adaptation","artificial-intelligence","attention-mechanisms","cross-embodiment","deep-learning","locomotion","transformers"],"created_at":"2025-12-24T23:17:27.139Z","updated_at":"2026-02-09T21:18:54.763Z","avatar_url":"https://github.com/lucidrains.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cimg src=\"./fig3.png\" width=\"400px\"\u003e\u003c/img\u003e\n\n## LocoFormer (wip)\n\n[LocoFormer - Generalist Locomotion via Long-Context Adaptation](https://generalist-locomotion.github.io/)\n\nThe gist is they trained a simple Transformer-XL in simulation on robots with many different bodies (cross-embodiment) and extreme domain randomization. When transferring to the real-world, they noticed the robot now gains the ability to adapt to insults. The XL memories span across multiple trials, which allowed the robot to learn in-context adaptation.\n\n## Sponsors\n\nThis open sourced work is sponsored by [Safe Sentinel](https://www.safesentinels.com/)\n\n## Citations\n\n```bibtex\n@article{liu2025locoformer,\n    title   = {LocoFormer: Generalist Locomotion via Long-Context Adaptation},\n    author  = {Liu, Min and Pathak, Deepak and Agarwal, Ananye},\n    journal = {Conference on Robot Learning ({CoRL})},\n    year    = {2025}\n}\n```\n\n```bibtex\n@inproceedings{anonymous2025flow,\n    title   = {Flow Policy Gradients for Legged Robots},\n    author  = {Anonymous},\n    booktitle = {Submitted to The Fourteenth International Conference on Learning Representations},\n    year    = {2025},\n    url     = {https://openreview.net/forum?id=BA6n0nmagi},\n    note    = {under review}\n}\n```\n\n```bibtex\n@misc{ashlag2025stateentropyregularizationrobust,\n    title   = {State Entropy Regularization for Robust Reinforcement Learning}, \n    author  = {Yonatan Ashlag and Uri Koren and Mirco Mutti and Esther Derman and Pierre-Luc Bacon and Shie Mannor},\n    year    = {2025},\n    eprint  = {2506.07085},\n    archivePrefix = {arXiv},\n    primaryClass = {cs.LG},\n    url     = {https://arxiv.org/abs/2506.07085}, \n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Flocoformer","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Flucidrains%2Flocoformer","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Flucidrains%2Flocoformer/lists"}