Presenting DemoDiffusion: An extremely simple approach enabling a pre-trained 'generalist' diffusion policy to follow a human-demonstration for a novel task during inference One-shot human imitation *without* requiring any paired human-robot data or online RL 🙂 1/n

Got to visit the Robotics Institute at CMU today. The institute has a long legacy of pioneering research and pushing the frontiers of robotics. Thanks Kenny Shaw Jason Liu Adam for showing your latest projects. Here’s a live autonomous demo trained with DexWild data

Want to add diverse, high-quality data to your robot policy? Happy to share that the DexWild Dataset is now fully public, hosted by Hugging Face 🤗 Find it here! huggingface.co/datasets/board…

Awesome to hear about my former labmates doing big things at Skild!

Tactile interaction in the wild can unlock fine-grained manipulation! 🌿🤖✋ We built a portable handheld tactile gripper that enables large-scale visuo-tactile data collection in real-world settings. By pretraining on this data, we bridge vision and touch—allowing robots to:

📹Recording now available! If you missed our workshop at RSS, you can now watch the full session here: youtu.be/7a5HYjQ4wJo?si… Thanks again to all the speakers and participants!

Scaling dexterous robot learning is going to require a lot of data. DexWild is a way of collecting a lot of useful real-world data in diverse settings for training diverse robot skills. Cool work by Tony Tao and Mohan Kumar Srirama

🚨 The era of infinite internet data is ending, So we ask: 👉 What’s the right generative modelling objective when data—not compute—is the bottleneck? TL;DR: ▶️Compute-constrained? Train Autoregressive models ▶️Data-constrained? Train Diffusion models Get ready for 🤿 1/n

I’m thrilled to announce that we just released GraspGen, a multi-year project we have been cooking at NVIDIA Robotics 🚀 GraspGen: A Diffusion-Based Framework for 6-DOF Grasping Grasping is a foundational challenge in robotics 🤖 — whether for industrial picking or

📢 Call for Papers: 4th Workshop on Dexterous Manipulation at CoRL 2025! Submit your dexterous work and come participate in our workshop! ✋🤖 📅Deadline: Aug 20 dex-manipulation.github.io/corl2025/ There will be a cash prize sponsored by Dexmate or a LEAP Hand up for grabs! 😃

LEAP Hand now supports Isaac Lab! (adding to Gym, Mujoco, Pybullet) This 1-axis reorientation uses purely the proprioception of the LEAP Hand motors to sense the cube. We open‑source both Python or ROS 2 deployment code! Led by Sri Anumakonda github.com/leap-hand/LEAP…

The most consequential breakthrough of our time isn’t an app or a website — it’s a single brain for every robot. Sci-fi? No. Skild AI. Congrats you guys.

Interesting paper....force-based policies will be very important in the future.

Congrats on the release from old friends! Reminds me of the good old times at CMU.

Self-Questioning Language Models: LLMs that learn to generate their own questions and answers via asymmetric self-play RL. There is no external training data – the only input is a single prompt specifying the topic.

Reminder that this is due in 6 days! Get your submissions in for a chance to win a LEAP hand or cash prize! 😄

We have extended our submission deadline to 11:59 PM (PT) on Auguest 27! Please consider submitting your work to our workshop. Submit for a chance to win a LEAP Hand or a cash prize!

Very disappointed that many people I know weren't able to register for CoRL this year. Oh well. 😢