LeRobot v0.6.0: Imagine, Evaluate, Improve

We’re on a journey to advance and democratize artificial intelligence through open source and open science.

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. TL;DR 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…

saved by

• Yoyo Yuan

related reading

• GitHub - robotics-survey/Awesome-Robotics-Foundation-Modelsgithub.com
• How Claude Performs on Robotics Tasks \ Anthropicanthropic.com
• State of Robot Learning, December 2025vedder.io
• LeRobot Community Datasets: The “ImageNet” of Robotics — When and How?huggingface.co
• Generalist - GEN-0 / Embodied Foundation Models That Scale with Physical Interactiongeneralistai.com
• Causal Video Models Are Data-Efficient Robot Policy Learners | Rhoda AIrhoda.ai
• Pretrained to Imagine, Fine-Tuned to Act: The Rise of World-Action Models | NVIDIA Technical Blogdeveloper.nvidia.com
• A Unified Model for Motion-Conditioned Robot Co-designtransformer-transformer.github.io
• Dexterous Robotic Foundation Modelsyoutube.com
• [2510.13626] LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Modelsarxiv.org
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixelsle-wm.github.io
• Robocurve — Real-world evaluations of physical AIrobocurve.org