Ranjay Krishna

Assistant Professor @ University of Washington, Co-Director of RAIVN lab ( Director of PRIOR team (

[Weikai Huang @weikaih04]

What if VLMs could imagine before answering?

IPT supervises visual intermediate states for spatial reasoning:

1. Path tracing → side view
2. Perspective taking → new viewpoint
3. Multiview counting → top-down map

Paper: https://t.co/57KvrXgPFv

[Ranjay Krishna @RanjayKrishna]

@pathak2206 @CVPR Very well deserved 🎉🎉

[Weikai Huang @weikaih04]

What if VLMs could imagine visually before answering spatial questions?

New paper: Imaginative Perception Tokens (IPT) teach multimodal LMs to reason about hidden 3D structure — without generating images at inference time.

Paper: https://t.co/57KvrXgPFv

[Mahtab Bigverdi @MahtabBg]

Picture your living room. If you sat on the sofa, would the TV be on your right or left? You didn't reason in words,you placed yourself in the scene.Imagining in visual space, not text.Exactly what VLMs can't do.Our new paper tackles this with Imaginative Perception Tokens(IPT)🧵

[Jiafei Duan @DJiafei]

Given the strong community adoption and real-world deployment of MolmoAct2 on YAM, we're introducing zero-shot evaluation of MolmoAct2 Bimanual YAM in simulation. Now you can test out our models without a real-world robot and build on them!

Code: https://t.co/ooIbp8BRf9

Simulation built on Maniskill!

[Ishneet Sukhvinder Singh @ishneet0710]

Thrilled to share that VLS received the 🥳 Outstanding Paper Award at the CVPR 2026 Foundation Models Meet Embodied Agents Workshop and the 🏅 Best Paper Runner-Up at the CVPR 2026 3D-LLM/VLA Workshop!

Huge thanks to @liu_shuo42927 for presenting at CVPR, and to @YiqingXu6 @DJiafei @RanjayKrishna for their guidance and support throughout! 🙌

It is truly the right time to work on vision-language steering for embodied agents🚀🚀#CVPR2026 🏆

[Rose Hendrix @rosemhendrix]

And that's a wrap on a fantastic ICRA 2026! 🎉 Incredible run for MolmoBot — clean sweep on workshops, winning Best Paper at all three we entered: Synthetic Data for Robot Learning, Beyond Teleoperation, and VLA Pipelines. 🤖

[Peter Sushko @PeterSushko]

Live demo of MolmoWeb at #cvpr with @zixianma02 @RanjayKrishna @allen_ai

[Jie Wang @JieWang_ZJUI]

MolmoAct2 Deployed at CVPR
Very cool to watch @RanjayKrishna ‘s talk together with his model stacking the cups into a tower
We should have more live demo like this in the future

[Mahtab Bigverdi @MahtabBg]

Ablate to validate poster at @cvpr today in Exhibit Hall A #51

[Ainaz Eftekhar @ainaz_eftekhar]

The One RING 🪐 was presented as an Oral at #ICRA2026 in Vienna! 🎉

I couldn’t make it to Vienna this time, but huge thanks to @rosemhendrix for presenting our work on my behalf ❤️🤖

[Ranjay Krishna @RanjayKrishna]

My students and I will be doing real robot demos at my talk at the Embodied Reasoning workshop #CVPR2026 today at Room 605 from 9:30-10:20am. Come by!

[Jae Sung Park @jjaesungpark]

VideoNet will appear as @CVPR Highlight✨ + 3 workshops TODAY!

Multimodal AI is improving fast, but can it tell apart moves only a domain expert could name?✒️🪀
You probably got a hang of it from clips below😉 — Can models do the same with few-shot examples?

Come find out 👇

🔗 Website: https://t.co/Y9AOF3Rid0
📍 Poster: Fri, Jun 5, 4:00–6:00 PM
🗓️ Workshops (all today, Jun 4):
- KnowledgeMR — 🏆Best Paper Award candidate, talk by @tanushyy
- CVSports
- VidLLMs

[Rose Hendrix @rosemhendrix]

Our paper MolmoB0T won top honor at the SDRL workshop today! Congrats to my co-authors @ab_deshpande, Maya, Snehal, @RanjayKrishna, @shahdhruv_ (plus others, you know how it goes), and we'll see you as well at the VLA Pipelines and Beyond Teleoperation workshops on Friday 🚀

[Abhay Deshpande @ab_deshpande]

MolmoB0T won best paper at the Synthetic Data for Robot Learning workshop at #ICRA2026! Huge thanks to my coauthors including @rosemhendrix, @SnehalJauhri, @mayasguru, @RanjayKrishna, and @shahdhruv_!

Come visit us on Friday at our other workshops, would love to chat!

[Phillip (Yuseung) Lee @yuseungleee]

#CVPR2026 @cvpr If you're interested in the intersection of multimodal and spatial intelligence, join our ✨MUSI workshop✨ on June 3 (Wed)!

We’re bringing together an amazing lineup of speakers to discuss the latest and most exciting topics in multimodal spatial intelligence🧠

[Aishwarya Agrawal @aagrawalAA]

Ranjay Krishna (@RanjayKrishna) talking about Multilingual Pluralism through Dataset Interventions at our MAPS workshop @CVPR in Room 113!

[Gedas Bertasius @gberta227]

The 5th Transformers for Vision and Multimodal AI workshop is happening at #CVPR2026 tomorrow (Wednesday, June 3rd)! We've got a great speaker lineup covering diverse topics across Transformers and Multimodal AI.

When: Wed, June 3rd
Where: Room 607
Website: https://t.co/SD892nEr8z

Schedule:
1:50 - 2:00 Opening Remarks
2:00 - 2:30 Ranjay Krishna
2:30 - 3:00 Jiatao Gu
3:00 - 3:30 Sherry Yang
3:30 - 4:00 Coffee Break
4:00 - 4:30 Juan Carlos Niebles
4:30 - 5:00 Zhuang Liu
5:00 - 5:30 Peter Tong

See you all tomorrow!

@thoma_gu @RanjayKrishna @sherryyangML @jcniebles @liuzhuang1234 @TongPetersb

[Jiafei Duan @DJiafei]

Really blows me away how many people are seeing the power and impact of open-science models like MolmoAct2 being deployed out of the box, without any fine-tuning. That’s exactly the future I envision for robotics foundation models.

[Jie Wang @JieWang_ZJUI]

Today’s release:
I open-sourced our evaluation stacks for DROID / YAM arm on MolmoAct 2, including both the policy server and inference stack! Now it’s easy to test frontier bimanual robot foundation models with it. Check it out!

https://t.co/xVNsjJ1aBa
https://t.co/KVPkOzAkak