LeRobot v0.6.0: Imagine, Evaluate, Improve
We're on a journey to advance and democratize artificial intelligence through open source and open science. Back to Articles a]:hidden"> LeRobot v0. It also brings depth sensing, VLM-powered dataset annotation, custom video encoding, cloud training on HF Jobs, and a much leaner install.
Key Takeaways
- 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).
- 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 imagination affordable.
- LingBot-VA LingBot-VA goes one step further: an autoregressive video-action model that predicts future video and actions together, chunk by chunk, and feeds real observations back in to keep its imagination grounded.
You can even save what the robot imagined ( ) and compare it with what actually happened.
- It pairs a ~5B video-generation expert with a compact action expert in a single network, so the model literally learns to dream its own rollouts.
At inference it skips the dreaming entirely and directly denoises action chunks.
- 7, the newest open generation of NVIDIA's cross-embodiment foundation model.
Stats & Key Facts
- #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.
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 , the 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. 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. 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 imagination affordable. VLA-JEPA VLA-JEPA teaches a compact VLA (built on Qwen3-VL-2B) to predict the future in latent space while it learns to act: during training, a JEPA world model has to anticipate upcoming frames from the model's own actions. The trick is that the world model then disappears at inference, so you get world-model supervision at zero extra inference cost.
For more details please read the original article at Hugging Face.
Continue Learning
Comments
Sign in to join the conversation