Remi Cadene

Meet the game-changer: SO-100 🦾 Crafted by @therobotstudio and @huggingface 🤗 At 1/3 the cost and 2x the capabilities of our previous arms, it's the most accessible, high-performance robotic arm for $115. Easiest DIY at home! 1/🧵 Link and details in thread 👇

Generalization needs data. But data collection is hard for precise tasks like plugging USBs, swiping cards, inserting plugs, and keying locks. Introducing robust, precise VisuoTactile Local (ViTaL) policies: >90% success rates from just 30 demos and 45 min of real-world RL.🧶⬇️

Implemented @physical_int’s Real‑Time Chunking (RTC) on @huggingface’s SmolVLA in the @LeRobotHF repo! It noticeably reduces jerky motion compared with basic merge strategies during async inference!🧵1/

LeKiwi's got a new look🤯 We redesigned our mobile manipulator from the ground up with full Dynamixel integration 🦾 Check out the build instructions on our GitHub (linked below)👀 Huge thanks to @ROBOTISAmerica for sponsoring this project!

XLeRobot 0.2.3 (XLeVR) out! xlerobot.readthedocs.io • VR (Quest 3) Whole-body Control • Reads everything: head and hand poses, joysticks, and all the buttons • Minimal dependencies, web-based • Modular, can use it on other robots • Open-source, easy install, play in 20min

i love the simplicity of @LeRobotHF to interact with robots, especially for beginners like me there is one very huge problem: it's written in python, but i love js introducing: LeRobot.js interact with your robot directly in the browser

5 days after launch and we've sold $1M of Reachy Mini Steadily getting $50k orders per day following the release peak time to ramp up production!

4mo ago: We bought a used forklift & strapped an Ai kit to it 4mo later: We’re moving hundreds of pallets a day in a customers warehouse Yesterday I got 3 requests totaling 100+ forklifts We have to scale right now V2 coming soon

Quick update and announcement: 24h since we announced Reachy Mini and we're quickly approaching $500,000 in pre-orders (!) We knew this product was special (everyone on the team wanted one), but the response has been even more overwhelming than expected—thanks for the incredible…

Happy to announce 🤗Datasets 4 ! we've added the most requested feature 👀 Introducing streaming data pipelines for Hugging Face Datasets ✨ With support for large, multimodal datasets in any standard file format, and with num_proc= for speed⚡

$120k worth of order in just a few hours! 🤗 - Cute robots will be present in our daily lives - Reachy mini is an important step forward - And it's open-source! youtube.com/watch?v=JvdBJZ…

Reachy Mini 🤗

SmolVLM has been accepted to @COLM_conf 2025 🥳! See you in Montreal!

Can’t wait!

We tested WSRL (Warm-start RL) on a Franka Robot, and it leads to really efficient online RL fine-tuning in the real world! WSRL learned the peg insertion task perfectly with only 11 minutes of warmup and *7 minutes* of online RL interactions 👇🧵

🚀 With minimal data and a straightforward training setup, our VisualTactile Local Policy (ViTaL) fuses egocentric vision + tactile feedback to achieve millimeter-level precision & zero-shot generalization! 🤖✨ Details ▶️ vitalprecise.github.io

Current robot policies often face a tradeoff: they're either precise (but brittle) or generalizable (but imprecise). We present ViTaL, a framework that lets robots generalize precise, contact-rich manipulation skills across unseen environments with millimeter-level precision. 🧵

Recording more @LeRobotHF datasets today. I’m using the Ryobi to “reset my environment” 😁

recorded my first @LeRobotHF dataset today 🦾🤖 I finally got my hands on it @ErikKaum 😊

Inspiring work :)

What would a World Model look like if we start from a real embodied agent acting in the real world? It has to have: 1) A real, physically grounded and complex action space—not just abstract control signals. 2) Diverse, real-life scenarios and activities. Or in short: It has to…