Welcome to the official Mayo Clinic #STRX Fellowship account. We look forward to sharing a glimpse into our one-year, accredited fellowship in Jacksonville, FL through education, research, and patient care. Fellowship details: college.mayo.edu/academics/r…@MayoClinicNeuro
More NVIDIA models and tools are coming to robot learning with LeRobot 0.7. 🤖
New integrations include:
•Cosmos 3 and Long-WAM for world action modeling.
• RoboLab on NVIDIA Isaac Lab for evaluating policies across 120 tabletop tasks.
•SONIC integration for humanoid whole-body control, with decoding on NVIDIA Jetson.
Congrats to @huggingface and the LeRobot community. 🦾
𝗟𝗲𝗥𝗼𝗯𝗼𝘁 𝘃𝟬.𝟳.𝟬 𝗶𝘀 𝗟𝗜𝗩𝗘 🚀🤖
From terabytes of data to prompting robots! Check out all what's new in the video below and join the 50,000+ developers & 300+ organizations in the LeRobot ecosystem 🤗
We built a robotics data engine with Astra-level performance at 125x lower cost. And we are open-sourcing the weights today! Introducing Flora, a suite of open models to parse the physical world and turn raw footage into rich training signals.
Flora already powers our in-house data engine, labeling 200K hours of videos a day on 500 GPUs. We created it to scale the frontier for robot learning. Now you own the weights too.
Flora gives you:
- High-quality, timestamped captions to curate and filter human egocentric and robot data;
- Dense progress rewards for quality control and RL post-training;
- Rubrics scoring for real-world benchmarking
Try it today, links in thread:
Introducing EmbeddingGemma 2! 🚀
Our lightweight, multimodal embedding model maps text, code, images, video, and audio into a single, unified embedding space. Optimized for on-device use cases, it features:
- 740M parameter form factor with modular encoders
- Flexible dimension sizes (768dim-128dim) via Matryoshka Representation Learning (MRL)
- 8K context window (4x larger than text-only EmbeddingGemma)
- A commercially permissive Apache 2.0 license
The most important thing we can apply AI to is improving medicine and human health - very excited about this partnership with the CZI and the Virtual Biology Initiative!
Today, Isomorphic Labs joins the Virtual Biology Initiative (VBI) as a founding member.
We are helping build an open resource for the global research community to accelerate how we understand and treat disease.
Read more here: isomorphiclabs.com/articles/…
Still deciding which hands-on training sessions to attend at #NVIDIAGTC Berlin?
If robotics is on your agenda, add these two must-attend sessions to your list:
🔹 Building Surgical and Medical Robotics With NVIDIA Isaac for Healthcare: nvidia.com/en-eu/gtc/session…
🔹 From Teleop to Torque: Deploying a GR00T Policy on a Humanoid: nvidia.com/en-eu/gtc/session…
Your #NVIDIAGTC Berlin agenda could use some work. 👀
Don't worry, we have recommended hands-on trainings for you.
Explore our lineup to build physical AI skills across NVIDIA Cosmos, visual AI agents, humanoid robot policies, and more.
👉 nvda.ws/4dThidQ
Today, we are open-sourcing the Innate OS, the intuitive agentic OS for general-purpose robots
🎮 Try it today in our simulator and make the smartest robot
⬇️ Here is a demo with two robots collaborating
We are entering the physical agents era, but building for mobile robots is still reserved for PhDs. We designed the Innate OS for intuitiveness, so that everyone can start automating their lives.
Innate OS runs on our <$1k open-source robot or on your computer. It takes just a minute to build your first agent in our simulator.
We put GPT-6 Astra in the RoboDojo. 🥋🤖
The RoboDojo Team conducted a comprehensive evaluation of GPT-6 Astra as an embodied agent, including:
• RoboDojo Sim & Real, compared with GPT-5.5 and DeepSeek-Flash
• Humanoid high-level control
• Dexterous piano playing with RoboPianist 🎹
• A systematic study of in-context learning (ICL)
Our key takeaway:
GPT-6 Astra demonstrates remarkably strong semantic and spatial understanding, together with impressive in-context adaptation.
At the same time, physical commonsense remains a clear bottleneck — revealing an important gap between understanding the world and truly reasoning about its physics.
Full report & demos:
robodojo-benchmark.com/repor…@_wenbozhang (project lead), @wenhaocha1, @frankzydou, @JinWeiyang18434, @YutaoOuyang, @minifullcapsule, @x_h_ucb, @YutaoOuyang, @YueChen614
For 20+ years @ShaneLegg and I've discussed AGI’s potential impact on the economy, science & society. With the DeepMind Institute, we're expanding interdisciplinary research on key questions for the AI era. We hope it spurs the discussions needed to get the next steps right: deepmind.google/institute
Gpt-6 astra can do in-context learning on mobile manipulation!
• Different environment
• Different camera angle
• Different layout
No text prompt, it infers from video
It even chooses when to use end-effector or joint space
Trace recording after ⬇️
@nvidia and @huggingface are joining forces!
At LeRobot, we believe the future of physical AI must be collaborative, open, and accessible to everyone. This partnership brings incredible momentum to the open robotics community while keeping our commitment to flexible, multi-platform development stronger than ever.
Can't wait to see what you all build as we push the boundaries of embodied AI together. 🤗💚
I'm so excited that our @theworldlabs team has achieved a major milestone today! Introducing Atlas - a first of its kind multimodal world model trained from scratch! 🚀
Atlas is capable of generating frames with pixel-perfect camera control, reconstructing large scenes from as few as one single input image, simulating space-time by reframing videos, natively outputting 3D spaces from one or more input images, composing multiple posed images into a consistent 3d world, and more! This is the best camera conditioned world model ever, opening doors to many possible use cases from VFX to robotics. I'm so so so proud of our team!♥️
Introducing Atlas:
The world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D.
Model the world, move the camera, and simulate space & time.
We took part in the research preview of MHS from @AnthropicAI
Here is Claude Code running a real SO-ARM101. Nothing in this was trained - no policy, no teleoperation, no demonstrations. The agent measured the workspace itself and wrote the motion.
The calibration is the interesting part. No checkerboard, no camera intrinsics: the arm is its own ruler. Torque drops, a human rests the closed gripper on 16 dots the software draws in the camera view, and the robot reads back where they are. 4.1 mm position accuracy, 3.0 mm placement.
Best run so far: 12 bricks placed with all four colour groups formed. A full hands-off run, start to finish, is what's next.
Research preview today, open source coming soon.