🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Very excited to be co-organizing the #RSS2025 workshop on Out-of-Distribution Generalization in Robotics! We have a wonderful list of speakers and panelists -- looking forward to a stimulating set of talks and discussions.

Data really matters for policy generalizing to diverse environment conditions as seen in pi05 etc. In this work we find strong correlation b/w # data and test performance, enabling targeted data collection. We also find offline metric (policy embedding) to give strong signal!

Great new paper by Lihan Zha, Apurva Badithela, Michael Zhang, Justin Lidard, Anirudha Majumdar, Allen Z. Ren, Dhruv Shah, and team. As we scale data collection for robotics, it must be done intelligently by choosing which data variations to focus resources on. This paper provides a

The 80-year recipe stoking America’s Prosperity: 1) Free-market capital investments in brilliant ideas… 2) enabled by Engineering Innovations… 3) based on Science Research in Universities… 4) funded by Grants from the US Government. It’s time more people understood this.

How can we boost the visual generalization of VLAs 𝑤𝑖𝑡ℎ𝑜𝑢𝑡 𝑎𝑛𝑦 𝑓𝑖𝑛𝑒-𝑡𝑢𝑛𝑖𝑛𝑔? Asher Hancock will be presenting at #ICRA2025 on Wed in the Vision-Language-Action Models session (WeDT21): Run-Time Observation Interventions Make Vision-Language-Action Models More

Excited that our work on Gemini Robotics and Gemini spatial understanding have just been featured on #GoogleIO stage! I believe that a frontier model possessing strong real-world understanding capabilities represents the ultimate path to embodied AGI, and we are making rapid

Check out the Asimov Benchmark and paper on semantic safety for robots here: asimov-benchmark.github.io

"We lead the world in so many ways, including in scientific innovation and economic dynamism. Our great universities are the envy of the world and a crucial national asset." — Federal Reserve chair and Princeton Politics graduate Jerome Powell '75 at #Princeton25 Baccalaureate service.

Foundation models can allow autonomous driving agents to perform commonsense reasoning, but they are also slow to run online. Our new paper distills the reasoning process from a VLM into an end-to-end driving model for fast inference: verdi-driving.github.io

Revoking visas of Chinese students studying in critical fields like AI and Robotics is incredibly short-sighted and harmful to America’s long term prosperity. We want the best from every country to work for team America

Great to have Allen Z. Ren back at Princeton University for the PhD hooding ceremony, so I could ask him a whole bunch of questions about the pi_0.5 paper from Physical Intelligence!

Congratulations to Nate Simon (now at Zoox) and Allen Z. Ren (now at Physical Intelligence) for receiving their PhD degrees from Princeton University!

Can we train robots to 𝒑𝒍𝒂𝒏 𝒘𝒉𝒆𝒓𝒆 𝒕𝒐 𝒍𝒐𝒐𝒌 to find an object described with language? Check out our new paper that combines prior knowledge from a VLM with a world modeling approach for planning: 🌐 WoMAP: World Models For Embodied Open-Vocabulary Object

Robots struggle to find objects like humans. Why? Understanding "behind the box" (semantics) isn't enough – they need to plan precise, efficient actions to get there. Key Insight: VLMs propose where to look ("Maybe behind the box?"). World models evaluate VLM proposals and

Attending RSS at USC next week? We are organizing a workshop on "Statistical Uncertainty Quantification in the Era of AI-Enabled Robots" and have a fantastic lineup of speakers from academia and industry: sites.google.com/view/rss2025-w…. Looking forward to seeing many of you 😎

Join us at two workshops #RSS2025 on 6/21! 📍 Resource Constrained Robotics (RTH109) 🗣️ Oral talk: 11:00–11:15 📍 Continual Robot Learning from Humans (OHE132) 🖼️ Spotlight poster: 10:30–11:00 Come by and chat—we’re excited to share our work!

We’re bringing powerful AI directly onto robots with Gemini Robotics On-Device. 🤖 It’s our first vision-language-action model to help make robots faster, highly efficient, and adaptable to new tasks and environments - without needing a constant internet connection. 🧵

Gemini Robotics zero shot picks a dextrous hand: No prior demos, not even videos. It recognized, failed to grasp (slippery surface), retried with new angles, got help, nailed the pick, adjusted post-pick. Mad respect to DeepMind team. Now I really worry about human labor 😅