LeRobot

~ Lowering the barrier to entry for robotics ~
Crafted with care by @HuggingFace 🤗
Join our discord:

[LeRobot @LeRobotHF]

VLA-JEPA just dropped in LeRobot 🤖

What makes this model special is that it does not just learn what action to take from a given observation, it also leverages a JEPA world model to learn action-relevant dynamics.

During training, the VLA leverages V-JEPA2 by conditioning its predictor. This clever trick adds a world modeling objective to the training, which also allows pretraining on human videos.
At inference, the world model is dropped entirely, keeping only a standard VLA architecture: Qwen backbone and action head.

The demo here was only fine-tuned on 13 examples, showing great pretraining capability and running in real time on @NVIDIARobotics DGX Spark!

VLA-JEPA is the first world model to be ported to LeRobot, and I feel like it won't be the last 🚀

@Thom_Wolf @ClementDelangue

[LeRobot @LeRobotHF]

@VMises76153 Here is a link to the full video: https://t.co/c9qZUVAdBn

[LeRobot @LeRobotHF]

Cleaning your home with Cable-Driven Parallel Robot and LeRobot.

Meet Stringman, an open-source project by Nathaniel Nifong (@VMises76153). The goal is to completely automate picking up household laundry, toys, and trash.

It operates as an overhead Cable-Driven Parallel Robot (CDPR) using 4 wall-mounted motors and fishing line. Offloading the motor weight from the end-effector keeps the moving gripper assembly lightweight, incredibly cheap, and quiet while maximizing payload capacity. Most of the parts are 3D printed.

The technical stack:
- Model: Multitask Diffusion Transformer (DiT)
- Data: Learned via teleoperation and trained on just 400 local human demonstration examples
- Framework: Built and trained locally using LeRobot on a consumer GPU

This is a fantastic showcase of how accessible, community-driven hardware and open-source AI can rethink home automation constraints without needing a complex humanoid base.

[clem 🤗 @ClementDelangue]

Very cool and massive dataset on @huggingface of course: https://t.co/1OvlkLhdGl!

[LeRobot @LeRobotHF]

🤗 LeLab now keeps itself up to date! 🦾

We shipped an in-app popup that alerts you the moment a newer version is on GitHub - plus same upgrades based on users feedback:

- Import any external/Hub model to run & rollout, no retraining
- Per-camera codec & backend control when recording
- Warning when your GPU is present but CUDA isn't being used
- Real camera names on Windows & Linux
- Smoother calibration & teleop (cameras stay off until you turn them on

🛠️ Update now with:
uv tool install --force git+https://t.co/UjyT3dBkyA

GitHub: https://t.co/SFuOiN8rjN
Docs: https://t.co/PrUEIeaXKW

[Hackster.io @Hacksterio]

LeLab is @HuggingFace’s new browser-based GUI for the LeRobot ecosystem. https://t.co/77pkiFhqkA

[Ilir Aliu @IlirAliu_]

ETH has semester-long courses.
Stanford? Lecture halls. MIT 826-page textbooks.
📌 Hugging Face’s robotics? 10 minutes…

>pip install lerobot

That’s it.

This command gets you started:

Classical foundations. Imitation learning. Reinforcement learning. Foundation models. Real datasets. Real robots.

The gap between academic and accessible is closing faster than most people realize.

And that matters more than any single course.

📌[https://t.co/QVOjxYFPhd]

——-

Weekly robotics and AI insights.
Subscribe free: https://t.co/9Nm01QUcw3

[Julien Chaumond @julien_c]

i am unsure if anyone who actually needs to read this will, but here goes:

https://t.co/Lq3GYjoVE0

[LeRobot @LeRobotHF]

One question follows us to every robotics panel: 𝘈𝘳𝘦𝘯’𝘵 𝘺𝘰𝘶 𝘸𝘰𝘳𝘳𝘪𝘦𝘥 𝘵𝘩𝘢𝘵 𝘰𝘱𝘦𝘯-𝘴𝘰𝘶𝘳𝘤𝘪𝘯𝘨 𝘳𝘰𝘣𝘰𝘵𝘪𝘤𝘴 𝘸𝘪𝘭𝘭 𝘫𝘶𝘴𝘵 𝘮𝘢𝘬𝘦 𝘪𝘵 𝘦𝘢𝘴𝘪𝘦𝘳 𝘧𝘰𝘳 𝘪𝘭𝘭-𝘪𝘯𝘵𝘦𝘯𝘵𝘪𝘰𝘯𝘦𝘥 𝘢𝘤𝘵𝘰𝘳𝘴 𝘵𝘰 𝘥𝘦𝘱𝘭𝘰𝘺 𝘥𝘢𝘯𝘨𝘦𝘳𝘰𝘶𝘴 𝘴𝘺𝘴𝘵𝘦𝘮𝘴?

It's a fair question.

We think the answer is the opposite of what most people expect: 𝗧𝗵𝗲 𝘀𝗮𝗳𝗲𝘀𝘁 𝗳𝘂𝘁𝘂𝗿𝗲 𝗳𝗼𝗿 𝗿𝗼𝗯𝗼𝘁𝗶𝗰𝘀 𝗶𝘀 𝗮𝗻 𝗼𝗽𝗲𝗻 𝗼𝗻𝗲. Here's why:

https://t.co/ymwjRH3Xi0

[LeRobot @LeRobotHF]

@neurosp1ke 👀, maybe soon

[LeRobot @LeRobotHF]

As many of you were interested in the technical details of the model, here is a followup thread to go more into technical details about VLA-JEPA.

1. Architecture
2. Training
3. Recipe for the demo
4. TLDR

🧵below

[LeRobot @LeRobotHF]

VLA-JEPA just dropped in LeRobot 🤖

What makes this model special is that it does not just learn what action to take from a given observation, it also leverages a JEPA world model to learn action-relevant dynamics.

During training, the VLA leverages V-JEPA2 by conditioning its predictor. This clever trick adds a world modeling objective to the training, which also allows pretraining on human videos.
At inference, the world model is dropped entirely, keeping only a standard VLA architecture: Qwen backbone and action head.

The demo here was only fine-tuned on 13 examples, showing great pretraining capability and running in real time on @NVIDIARobotics DGX Spark!

VLA-JEPA is the first world model to be ported to LeRobot, and I feel like it won't be the last 🚀

@Thom_Wolf @ClementDelangue

[LeRobot @LeRobotHF]

TLDR: VLA-JEPA has a promising architecture leveraging V-JEPA2, enabling pre-training using human videos. Shows greater robustness to perturbations at inference, yet runs quite fast on consumer grade GPUs.

Thanks to everyone involved in the implementation, especially the authors of VLA-JEPA: Jingwen Sun & @zhang_weny92997

Paper: https://t.co/nc3vc8pP3k
Docs: https://t.co/7diSKkvCyG

Any further question? We will answer them in the comments!

[LeRobot @LeRobotHF]

For the demo, we collected 13 examples of a screwing task available here: https://t.co/br0pGozegK

Then started the training from the https://t.co/eXjCWgxhQT pretrained weights, 5k steps with a small 16 batch-size.

This task is a good mix of picking + dexterity, but still quite simple enough not to require too many examples.

[Wenyao (Wayne) Zhang @zhang_weny92997]

Hi @LeRobotHF team! 🎉 Great to see VLA‑JEPA landing in the framework — huge thanks for the shoutout and for building such an accessible home for robotics research. Excited to keep pushing this direction together! 🤖🤗

[LeRobot @LeRobotHF]

Blog: https://t.co/FoMZbXA9Cc
Docs: https://t.co/nBdF5xsgHP
Models: https://t.co/eQqsP8ul5b

[LeRobot @LeRobotHF]

VLA-JEPA just dropped in LeRobot 🤖

What makes this model special is that it does not just learn what action to take from a given observation, it also leverages a JEPA world model to learn action-relevant dynamics.

During training, the VLA leverages V-JEPA2 by conditioning its predictor. This clever trick adds a world modeling objective to the training, which also allows pretraining on human videos.
At inference, the world model is dropped entirely, keeping only a standard VLA architecture: Qwen backbone and action head.

The demo here was only fine-tuned on 13 examples, showing great pretraining capability and running in real time on @NVIDIARobotics DGX Spark!

VLA-JEPA is the first world model to be ported to LeRobot, and I feel like it won't be the last 🚀

@Thom_Wolf @ClementDelangue

[LeRobot @LeRobotHF]

The latest haptic glove from LeRobot's @nepyope looks alive 👀

Homunculus F³ drops next month.

Repost if you're hyped for new #lerobot hardware 🤗

#HF #lerobot #haptics

[Martino Russi @NepYope]

Homunculus F³ (Full Force Feedback) haptic glove coming soon 😁

[Jonathan Zamora @jonzamora_ai]

Kicking off a mini-series of videos with the @LeRobotHF SO-100 robot arm 🦾🚀 — showing the fun and accessible side of robotics, one experiment at a time! Here, i'm teleoperating the SO-100 to do pick-and-place w/ a conventional leader-follower setup. More to come soon!

[LeRobot @LeRobotHF]

@LeoKharon @rabault_nicolas For now so101/100, but are happy to support more robots in future!

[LeRobot @LeRobotHF]

Train AI robots without writing a single line of code. 🤖

We just launched LeLab, the official graphical user interface for LeRobot built by @rabault_nicolas. It completely removes the command line from the robot learning workflow, taking you from raw hardware to autonomous movement visually.

If you've ever wanted to get into AI robotics but were held back by complex terminal setups, this is for you.

- Zero-Terminal Setup: Smart calibration with automatic USB port detection.
- Easy Data Collection: Teleoperate your robot and record a dataset.
- One-Click GPU Training: Don't have a massive local GPU? Scale your training instantly with Hugging Face Jobs right inside the app.

Just plug in your SO-ARM101 and start teaching your robot. We put together a complete, step-by-step video guide showing exactly how to get started and train your first policy.

Docs: https://t.co/PrUEIeaXKW
GitHub: https://t.co/SFuOiN8rjN