Associate Professor @UTCompSci | Director @NVIDIAAI Co-Leading GEAR | CS PhD @Stanford | Building generalist robot autonomy in the wild | Opinions are my own
Can a robot learn more from the same recordings, and can it choose a better next move without more training?
Introducing Grana: a compositional reward model that tracks progress through mistakes and recovery in long-horizon robot manipulation. Its progress feedback supports both learning from recorded experience and guiding action selection during execution.
Even a successful run can contain mistakes and retries. Grana uses its progress estimates to give more training weight to actions that move the task forward, helping robots learn more from that experience. On real-robot airplane assembly, Grana-weighted training achieved 75% success, compared with 50% for unweighted training on the same data.
In a separate tractor assembly test, the same policy succeeded in 2 of 10 trials on its own and 9 of 10 when Grana helped it choose its next move.
Providing this feedback during execution and across many recorded attempts makes both scoring speed and cost important. Grana runs locally using less than 10 GB of GPU memory, with no API fees. In our benchmark, it returned progress estimates over 200× faster than GPT-6 Astra.
Paper, code, and results: https://t.co/BKIFAJdC4n 🧵↓
That’s a wrap! CoRL 2026 was such a blast! Even the FAA wanted to extend it another day.
Loved the energy across the technical program, exhibitions, and social events. Signing off as General Chair. Grateful to everyone who made it happen.
See you in Paris @corl_conf next year!
GR00T 2 code is coming in December.
We have released 100k hours of our human video datasets on Hugging Face: https://t.co/CneKQphAC0
Data collection hardware designs are also open-source here: https://t.co/4xgynxhQPx
Meet GR00T 2, our new generation of world-action models (WAMs): it imagines how the physical world will unfold and generates the actions that get it there. One model runs on parallel grippers, dexterous hands, and humanoids.
https://t.co/32Z1plSGQg
GR00T 2 Turbo, a faster version of GR00T 2, runs onboard a humanoid with NVIDIA Jetson Thor and drives its whole body as it walks, bends, reaches, and carries: serving popcorn, wiping up spills, clearing tables.
Alright, alright, alright…
CoRL registration is completely maxed out, with hundreds of people on the waiting list. Please stop flooding my inbox for tickets 😂
You can still join the fun! Our partners are hosting social events all over town. We gathered the list of public events here:
https://t.co/C48EkgNYbp
Many don’t require a conference badge to attend. Let’s turn Ausitn into a Robotics Party Town!
Introducing Flora, an open model suite for scaling robotics data engines.
It watches robot and human video and annotate what happened (timestamped instructions) and how well it went (rewards and failure reasons).
🔗 https://t.co/yZUS5pHvv9
We use it to train NVIDIA GR00T. 🧵
ASPIRE is now open-source!
Since our initial release, we've made exciting progress:
🤖 Real-world robot manipulation with GPT-6 Astra.
🔄 Continual skill refinement on physical robots.
📈 Saturated simulation benchmarks: 99% on LIBERO-Pro (80 tasks), 100% on Robosuite (7 representative tasks), and 100% on BEHAVIOR-1K (2 representative tasks).
Code: https://t.co/BJGbtQLCpo
Project: https://t.co/GI2Eo2j7bY
🧵 More results in the thread below.
Sharing a copy of my ICRA'26 keynote talk from three months ago. 3 key messages:
1. Building a human-like machine, a dream that has fascinated humankind for centuries, is rapidly becoming a reality.
2. Human data is, by far, the most scalable source of training data to fuel robot foundation models.
3. World models are a "data sponge" that can absorb massive amounts of multimodal data for policy generalization.
Video: https://t.co/WBp7MRKWVx
Slides: https://t.co/kPUfFDazEH
The talk brought together our work over the past year: GR00T, EgoScale, SONIC, WAM, and more. Here’s the same demo I showed on stage: Our (now old!) model learning to assemble the YCB airplane with zero teleop data.
We've made incredible progress since then. What's coming next? 🚀
CoRL 2026 paper decisions are out — check them out on OpenReview!
As General Chair, I'm delighted to welcome you to #CoRL2026 in Austin, TX, this November. We expect tickets to sell out quickly, so please register early!
https://t.co/1Y3fyYOEZf
Today, we're introducing SimFoundry, our real2sim2real framework at NVIDIA GEAR that automatically turns real-world scenes into simulation-ready worlds from a single image or video.
Website: https://t.co/JB3kf3GlYm
Paper: https://t.co/pVhE1qWXtU
This work marks a major step for our team toward leveraging simulations and synthetic data for foundation model training and systematic policy evaluation at scale. Code will be open-sourced soon. Stay tuned!