{"name":"Uni-SuperMimic","repo":"Motphys/Uni-SuperMimic","url":"https://midorreal.com/project/motphys-uni-supermimic","repository":"https://github.com/Motphys/Uni-SuperMimic","description":"SuperMimic-UniLab: An Independent reproduction of SuperMimic on UniLab for whole-body humanoid motion tracking.","facts":{"license":{"value":"Apache-2.0","source":"https://github.com/Motphys/Uni-SuperMimic","checked":"21 Nov 2026"},"language":{"value":"Python","source":"https://github.com/Motphys/Uni-SuperMimic","checked":"21 Nov 2026"},"last_release":{"value":"checkpoints-v1, 31 Oct 2026","source":"https://github.com/Motphys/Uni-SuperMimic/releases","checked":"21 Nov 2026"},"releases":{"value":"1","source":"https://github.com/Motphys/Uni-SuperMimic/releases","checked":"20 Nov 2026"},"contributors":{"value":"3","source":"https://github.com/Motphys/Uni-SuperMimic/graphs/contributors","checked":"20 Nov 2026"},"archived":{"value":"no","source":"https://github.com/Motphys/Uni-SuperMimic","checked":"21 Nov 2026"}},"stars":313.0,"writeup":{"what_it_is":"UniSuperMimic is an independent reproduction of SuperMimic on the UniLab framework, for whole-body motion tracking of the Unitree G1 humanoid robot. It includes a differentiable world model, a goal-conditioned policy, and training and evaluation pipelines for the LAFAN1 and BONES-SEED motion datasets.","audience":"Researchers and developers working on humanoid whole-body motion tracking","claims":[{"kind":"specific","claim":"Supports three simulation backends: mjwarp, MuJoCo, and Motrix","excerpt":"with **mjwarp, MuJoCo, and Motrix** backends","status":"not_checked"},{"kind":"specific","claim":"Handles a 129,487-clip BONES-SEED motion library","excerpt":"a 129,487-clip / 47.3M-frame motion library from one repository","status":"not_checked"},{"kind":"specific","claim":"Reaches a strong BONES-SEED checkpoint in about 40 minutes on a single GPU","excerpt":"reaching a strong BONES-SEED checkpoint in about 40 minutes","status":"not_checked"},{"kind":"broad","claim":"Provides an efficient single-GPU workflow","excerpt":"mjwarp, MuJoCo, and Motrix all support an efficient one-GPU workflow","status":"too_broad"},{"kind":"specific","claim":"Switches between backends without changing policy or dataset configuration","excerpt":"switch between mjwarp, MuJoCo, and Motrix without changing the policy or dataset configuration","status":"not_checked"}],"alternatives":[],"written_by":"AI, from the project's README","date":"2026-11-14"},"why_now":null,"owner_supplied":null,"score":{"verdict":"sleeper","hype":31,"reality":69,"gap":-38,"momentum":null,"confidence":60,"version":"score-2.0","rule":"verdict-2.0","calculated_at":"2026-11-22T08:00:00+00:00","verdict_source":"rule"},"early_read":null,"changes":[{"date":"2026-10-31T03:49:38+00:00","text":"Latest release checkpoints-v1","source":"https://github.com/Motphys/Uni-SuperMimic/releases"},{"date":"2026-10-22T09:06:45+00:00","text":"Repository created","source":"https://github.com/Motphys/Uni-SuperMimic"}],"cite":"Uni-SuperMimic is a GitHub project at https://github.com/Motphys/Uni-SuperMimic written mainly in Python, described there as \"SuperMimic-UniLab: An Independent reproduction of SuperMimic on UniLab for whole-body humanoid motion tracking\".","attribution":"Data from Mid or Real, https://midorreal.com/project/motphys-uni-supermimic, checked 22 November 2026. Attribution with a link is required.","still_real":null}