A very well deserved recognition to the pioneers of neural networks! The Nobel prize is timely and marks the acknowledgment of the transformative power of AI.

Applications are open for Robotics Research Scientists at NVIDIA. We are based in Seattle and the Bay Area and are led by Prof. Dieter Fox. A team-wide committee selects candidates. Please consider applying! Priority topics include dexterous, bi-manual, and mobile robot

A few weeks have passed since DeepSeek became an overnight sensation, and I’ve had time to reflect on its impact. DeepSeek has undeniably opened up new possibilities for LLM research—both for researchers and smaller companies. — It’s not easy, but it demonstrates that a small,

Over the last few months, we’ve been thinking about how to learn from “off-domain” data - data from non-robot sources like video or simulation. These data sources are not quite good enough to learn policies (even monolithic VLA models) directly, but they still contain lots of

3D-MVP has been accepted to #CVPR2025! Our research demonstrates that 3D pretraining significantly outperforms other pretraining approaches in robotics. By integrating this pretraining into the Robotic View Transformer (RVT), we enhance downstream policy performance.

🎊 That's a wrap on #ICLR2025. Shout out to all the amazing research in #robotics, machine vision, and more. Missed it? Check out our #NVIDIAResearch paper on hierarchical action models for open-world robot manipulation. 📄 nvda.ws/42OZKcC

Reasoning has taken off in LLMs – how does it translate to Robotics? At RSS 2025, we're organizing the "R³: Reasoning for Robust Robot Manipulation" workshop. Please consider submitting your work and join us. We'd love to hear you! Deadline: May 25 sites.google.com/view/rss2025r3…

VLAs have the potential to generalize over scenes and tasks, but require a ton of data to learn robust policies. We introduce OG-VLA, a novel architecture and learning framework that combines the generalization strengths of VLAs with the robustness of 3D-aware policies. 🧵

Headed to Nashville for #CVPR2025! Excited to present our robot learning work, "3D-MVP," and connect with fellow researchers. I'll be sharing my thoughts on the most exciting papers. Should be a fun week of learning and meeting friends, old and new! #Computervision #robotics