LeRobot v0.6.0: Imagine, Evaluate, Improve

Back to Articles LeRobot v0. 0: Imagine, Evaluate, Improve Published July 7, 2026 Update on GitHub Upvote 1 Steven Palma imstevenpmwork Follow Pepijn Kooijmans pepijn223 Follow Caroline Pascal CarolinePascal Follow Khalil Meftah lilkm Follow Martino Russi nepyope Follow Nikodem Bartnik nikodembartnik Follow Nicolas Rabault Nico-robot Follow Thomas Wolf thomwolf Follow This new release is about closing the robot learning loop: policies that imagine the future before acting, reward models that tell you when your robot succeeds, a deployment CLI that turns failures into training data, and six new simulation benchmarks to measure it all. It also brings depth sensing, VLM-powered dataset annotation, custom video encoding, cloud training on HF Jobs, and a much leaner install. 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 unified under lerobot-eval, the lerobot-rollout CLI with DAgger-style human-in-the-loop corrections, FSDP training, and cloud training on HF Jobs. Datasets get depth support, an automatic language annotation pipeline, custom video encoding, and up to 2x faster data loading, all on top of a leaner installation. Table of contents LeRobot v0. 0: Imagine, Evaluate, Improve TL;DR Table of contents World models: policies that imagine VLA-JEPA LingBot-VA FastWAM VLAs: the model zoo keeps growing GR00T N1.