Congratulations to @berkeley_ai alumnus @pathak2206 who has been awarded the PAMI Young Researcher in Computer Vision Award!
This top award for young researchers in computer vision is given to two recipients yearly.
https://t.co/PuVbUpp6oo
Start your #CVPR2026 with a coffee and some hard truths ☕
Tomorrow morning, we're talking 'Bitter Lessons' -- hard-won wisdom our field has accumulated but rarely discusses
Come be part of a candid conversation👇
https://t.co/P0oJDJG71X
Wed, 8:45am, Four Seasons Ballroom 4
We are presenting WFM-Eval at two @CVPR 2026 workshops in Denver 📍
🗓️ Jun 3, Video World Models
Poster 9:50–10:40 AM, Exhibit Hall A
🗓️ Jun 4, Foundation Models Meet Embodied Agents
Poster 3:55–4:30 PM
Come say hi 👋
Work done with @AmberZhang99@prithvijitch@judyfhoffman
CRAFT hand🫳
1. Achieves all 33/33 dexterous grasps > 2x-20x $$ hands!
2. < $600
3. Handles fragile objects
4. Durable under contact
5. Open-sourced https://t.co/lCBAeklcVn
@leo_lin6 & @shivanshpatel35 (on market; hire him🚀) will happily share anything else that you may need. Details in 🧵
🌟 Big shout out to @kenny__shaw (Leap & v2), @irmakkguzey (RUKA), @orcahand (ORCA), and many others who helped build this open research community. Thank you!
@simar_kareer has grown into a leading researcher in robot learning. From EgoMimic to Human2Robot VLA at Pi, and now leading EgoVerse. Excited to keep building together and see what comes next!
We've wanted to study human to robot transfer at scale, but the right dataset was missing. Introducing EgoVerse!
- EgoVerse is about quantity and quality. The data is vast and directly usable
- EgoVerse is growing. We're excited to onboard labs and startups, reach out!
Excited about the release of EgoVerse and looking forward to seeing what data the community will contribute! Now people can teach robots by passively collecting data as we move about the world. An important step towards scaling demonstration data! 🤖
Introducing EgoVerse: an ecosystem for robot learning from egocentric human data.
Built and tested by 4 research labs + 3 industry partners, EgoVerse enables both science and scaling
1300+ hrs, 240 scenes, 2000+ tasks, and growing
Dataset design, findings, and ecosystem 🧵
Teleop is so 2025. Ever since we unveiled EgoScale and the dexterity scaling law, it's been clear to us and the ecosystem that behavior cloning directly from humans is the way to break the curse of teleop. 2026 is all about scaling robot learning without robots.
Proud advisor moment: Congrats to @ryan_punamiya for winning the Runner-Up (2nd place) of the prestigious CRA Undergraduate Research Award! https://t.co/iPcldCdXZR
Some properties of LLMs only emerge with scale, one of which is the ability to effectively generalize from diverse data.
During my internship @physical_int, we uncovered an emergent property of VLAs: as we scale up pre-training, VLAs can naturally learn from human video data!
At the start of @simar_kareer's internship this year we set out to use human data to make VLAs better.
It turned out that once your VLA is pre-trained on enough diverse robot data...the simple thing just works!
🚀 I’m hiring across multiple levels — AI engineers, senior IC/leads, and interns — to join me at @nvidia .
We’re building the next generation of high-performance, multimodal, and agentic AI systems across the full stack: models, kernels, compilers, and hardware.
You don’t need to be a CUDA expert (yet). If you’re exceptional in AI research, systems, training, RL, or agentic AI, you’re welcome here.
Apply to join our team: https://t.co/O1Bih7FmGB
Welcome to CDS, Associate Professor Greg Durrett (@gregd_nlp)!
Prof Durrett joins us from UT Austin. His research focuses on how to train large language models to reason, reflect, and extrapolate — and how to get them to be more creative.
https://t.co/kFRVlEUssk
EgoBridge (NeurIPS'25) makes human data more useful for training robot policies. We show that the robot can even learn to operate in scenes only shown from the human view.
Check out this thread from lead author @ryan_punamiya -- he's applying for PhD programs this cycle!
Robots struggle to learn new skills from human videos.
Why? We found that naive co-training produces disjoint distributions.
Our EgoBridge (NeurIPS’25) extends Optimal Transport to align human-robot latents, improving success by 44% and generalization to human-only tasks!🧵