LeRobot v0.6.0 Release
LeRobot v0.6.0 introduces new world models, reward models, and datasets, enhancing its capabilities in imagination, evaluation, and improvement.
01
Evidence
- HHugging Face BlogCompany2026-07-07
LeRobot v0.6.0 introduces world model policies (VLA-JEPA, FastWAM, LingBot-VA) that learn to imagine the future, a wave of new VLAs (GR00T N1.7, MolmoAct2, EO-1, EVO1, Multitask DiT), and a new reward models API (Robometer, TOPReward). It ships six new simulation benchmarks unif…
- HHugging Face BlogCompany2026-07-07
The robotics world is asking a big question: do world models actually help robot policies? v0.6.0 brings three policies to LeRobot to help answer that question. Each one learns to imagine the future as part of its training, and each takes a different path to keep that imaginatio…