LeRobot v0.4.0: Supercharging OSS Robot Learning

LeRobot v0.6.0: Imagine, Evaluate, Improve

LeRobot Community Datasets: The “ImageNet” of Robotics — When and How?

!Imperio, smolVLA: The Implications of Data Poisoning on Open Source Robotics

arXiv:2607. 04146v1 Announce Type: cross Abstract: This work establishes that trigger-word data poisoning of vision language action models is practical, while at the same time the open-source robotics ecosystem holds trust assumptions about community contributions.

`LeRobotDataset:v3.0`: Bringing large-scale datasets to `lerobot`

LeRobot goes to driving school: World’s largest open-source self-driving dataset

SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data

ASPIRE: Agentic /Skills Discovery for Robotics

arXiv:2607. 00272v1 Announce Type: cross Abstract: Traditional robot programming is challenging: it requires orchestrating multimodal perception, managing physical contact dynamics, and handling diverse configurations and execution failures.

Teach and Grow: An Agent-Centered Architecture for General Robot Learning

arXiv:2608. 17209v1 Announce Type: cross Abstract: End-to-end vision-language-action (VLA) and world-action models offer an elegant route to general-purpose robotics, but their reliability is bounded by validated physical coverage.

G0.5: One Autoregressive Stream for Robot Reasoning and Action

arXiv:2608. 11739v1 Announce Type: cross Abstract: The prevailing recipe for Vision-Language-Action (VLA) models couples a pretrained VLM with a separately trained flow-matching action expert.

Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm

Robots that learn

We’ve created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done once.

SKooP: Symmetric Koopman Predictions for Faster and More Generalizable Legged Robot Locomotion with Reinforcement Learning

Reinforcement learning (RL) algorithms classically suffer from poor sample efficiency. In robotics, a recent line of work has emerged addressing this problem by encoding physics priors in the learning process.