this is crazy - how sample-efficient it is. I remember collecting 100 trajectories to train a diffusion policy with the exact same setup on a similar task early last year.

Blog: https://ginwind.github.io/VLA-JEPA/ Docs: https://huggingface.co/docs/lerobot/main/en/vla_jep Models: https://huggingface.co/collections/lerobot/vla-jepa

@LeRobotHF So I record nearly 800 duck episodes only to find there is a model that could have done it with 13 examples? 😭

@LeRobotHF The 13 example fine tune is the most interesting part.

V-JEPA2 helps the robot learn how actions affect the world before training on the real task. Then during use the world model is removed so the system stays simple and fast.

That is a smart setup for real time robotics.

@LeRobotHF Only 13 demos is great

@LeRobotHF What's blows my mind is that it's a 3B parameter, 6 GB model! It should run on a $200 GPU!

Actions are cheaper than words..! 🤯

jepa makes sense: skip pixel reconstruction, learn latent dynamics directly. but i keep wondering how much of the gain is better feature alignment vs actual world model reasoning. libero is controlled lighting, objects, camera. the interesting failure mode is whether the latent world model helps in messy ood scenarios where standard vlAs hallucinate

@mattparlmer I agree. Parallel grippers + toolchangers + HF repos will be the factory integration choice. But "vast" is doing a lot of work. Those are mostly low-hanging fruit where classic industrial automation already dominates (LeRobot's sweet spot).

@SAldwais @pepijn2233 @LeRobotHF Here’s the link for the ROBOTIS OMX (Dynamixel-X) arms: https://www.robotis.us/omx-ai-us/

OMX-AI bundle (leader + follower) ~$344. Built for teleop, imitation learning & Physical AI.

@VoidAsuka I wonder about the relationship between learning efficiency and generalization?

@LeRobotHF Amazing!! This is "merely" a way to make use of VJEPA, not to fine tune it, right?

@LeRobotHF 🙏 Honored to have our VLA‑JEPA work included — this kind of open, well‑engineered plumbing is exactly what the embodied AI community needs right now. Looking forward to seeing what people build with it. 🤗📦

@LeRobotHF I need the same arms. Were to order it ?

@LeRobotHF Congrats to the LeRobot team! Now the real question: will JEPA actually deliver in robotics?

@KuphDev @LeRobotHF it's a bit more complicated than that 😅 the demo we made is quite simple: pick up from mostly the same area a red nut, and then screwing at mostly the same place aswell. So there is not a lot of variety in the 13 episodes

@LeRobotHF @_lilkm_ neat

@SAldwais @LeRobotHF Its the Dynamixel OMX

@mattparlmer Isn’t the real promise of physical AI to tackle the complex, variable tasks that classical systems can’t handle. For those, what actually bridges impressive demos to production-ready scale?

@LeRobotHF "I do not understand how you can even think of building an agentic system without [...] having the ability of predicting the consequences of its actions." - Yann LeCun

It's great to see this finally taking off 🦾