Judy Hoffman

Associate Professor @UCIrvine, formerly @GeorgiaTech. Researcher in Computer Vision, Machine Learning, AI. PhD from @berkeley_ai. Views my own.

[Berkeley AI Research @berkeley_ai]

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

[Judy Hoffman @judyfhoffman]

@pathak2206 @CVPR Congratulations 🎉

[Unnat Jain @unnatjain2010]

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

[Sahil Khose @ CVPR 2026 ✈️ @SahilKhose]

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

[Judy Hoffman @judyfhoffman]

@DJiafei @UW @uwcse @fox_dieter17849 @RanjayKrishna @NUSComputing Congratulations 🎉

[Unnat Jain @unnatjain2010]

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!

[Danfei Xu @danfei_xu]

@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!

[Judy Hoffman @judyfhoffman]

A monumental effort that would not have been possible without @simar_kareer and @ryan_punamiya's leadership! Excited to see how this project grows 📈

[Simar Kareer @simar_kareer]

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!

[Judy Hoffman @judyfhoffman]

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! 🤖

[Danfei Xu @danfei_xu]

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 🧵

[Jim Fan @DrJimFan]

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.

[Danfei Xu @danfei_xu]

https://t.co/Y1jBFTAJSf

[Judy Hoffman @judyfhoffman]

Congratulations to @ryan_punamiya and @danfei_xu on this amazing accomplishment!! It's been a pleasure working together.

[Danfei Xu @danfei_xu]

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

[Simar Kareer @simar_kareer]

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!

[Suraj Nair @SurajNair_1]

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!

[Humphrey Shi @humphrey_shi]

🚀 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

[NYU Center for Data Science @NYUDataScience]

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

[Judy Hoffman @judyfhoffman]

@DhruvBatra_ @aagrawalAA @yashgoyal_ @ayshrv @deviparikh Congratulations and well deserved!

[Leena Mathur @lmathur_]

Our organizing team welcomes your participation at our workshop this weekend!

Fiona Ryan @fionakryan (co-lead), Anshul Gupta @anshul624gupta, Evonne Ng, Shiry Ginosar @shiryginosar, Sangmin Lee @sangminlee777, Paul Liang @pliang279, Judy Hoffman @judyfhoffman, Jim Rehg @RehgJim, Louis-Philippe Morency @lpmorency

[Judy Hoffman @judyfhoffman]

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!

[Ryan Punamiya @ryan_punamiya]

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!🧵

[Judy Hoffman @judyfhoffman]

@danfei_xu @ICatGT @gtcomputing @NSF Yay congrats!! 🎉