Shiry Ginosar (@shiryginosar) 's Twitter Profile
Shiry Ginosar

@shiryginosar

Moving to @shiryginosar.bsky.social
Assistant Professor at TTIC
Visiting Faculty Researcher at Google DeepMind

Understanding intelligence, one pixel at a time.

ID: 1071149963915083776

linkhttps://shiry.ttic.edu calendar_today07-12-2018 21:10:27

179 Tweet

978 Followers

185 Following

TTIC (@ttic_connect) 's Twitter Profile Photo

Just steps from TTIC, Midway Plaisance Skate Park is the perfect spot to enjoy winter! ❄️ Enjoy the charm of Hyde Park and The University of Chicago campus with outdoor ice skating - registration is now open!

Just steps from TTIC, Midway Plaisance Skate Park is the perfect spot to enjoy winter! ❄️ Enjoy the charm of Hyde Park and <a href="/UChicago/">The University of Chicago</a> campus with outdoor ice skating - registration is now open!
Qianqian Wang (@qianqianwang5) 's Twitter Profile Photo

Introducing CUT3R! An online 3D reasoning framework for many 3D tasks directly from just RGB. For static or dynamic scenes. Video or image collections, all in one!

Han Xiao (@hxiao) 's Twitter Profile Photo

Letter-dropping physics comparison: o3-mini vs. deepseek-r1 vs. claude-3.5 in one-shot - which is the best? Prompt: Create a JavaScript animation of falling letters with realistic physics. The letters should: * Appear randomly at the top of the screen with varying sizes * Fall

Hila Chefer (@hila_chefer) 's Twitter Profile Photo

VideoJAM is our new framework for improved motion generation from AI at Meta We show that video generators struggle with motion because the training objective favors appearance over dynamics. VideoJAM directly adresses this **without any extra data or scaling** 👇🧵

Carl Doersch (@carldoersch) 's Twitter Profile Photo

We're very excited to introduce TAPNext: a model that sets a new state-of-art for Tracking Any Point in videos, by formulating the task as Next Token Prediction. For more, see: tap-next.github.io 🧵

Shiry Ginosar (@shiryginosar) 's Twitter Profile Photo

Think LMMs can reason like a 3-year-old? Think again! Our Kid-Inspired Visual Analogies benchmark reveals where young children still win: ey242.github.io/kiva.github.io/ Catch our #ICLR2025 poster today to see where models still fall short! Thurs. April 24 3-5:30 pm Halls 3 + 2B #312

Think LMMs can reason like a 3-year-old?

Think again!

Our Kid-Inspired Visual Analogies benchmark reveals where young children still win: ey242.github.io/kiva.github.io/

Catch our #ICLR2025 poster today to see where models still fall short!

Thurs. April 24
3-5:30 pm
Halls 3 + 2B #312
Shiry Ginosar (@shiryginosar) 's Twitter Profile Photo

The Artificial Social Intelligence Workshop is BACK at #ICCV2025 in Hawaii 🌴! Join us for talks from amazing speakers & submit your papers for oral/poster presentations! 🗓️ Deadlines: Archival: 6/27 Extended Abstracts: 8/1 #AI #ICCV #Research

Shiry Ginosar (@shiryginosar) 's Twitter Profile Photo

Our Poly-Autoregressive prediction framework is at #CVPR2025! Come learn how to use our framework to model your favorite problem as an multi-agent interaction! Talk: Agents in Interaction workshop 4:15pm, Thurs. June 12 Poster #167, ExHall D, 10:30-12:30, Sat. June 14 #CVPR2025

Shiry Ginosar (@shiryginosar) 's Twitter Profile Photo

When it comes to goal-directed work, people prioritize controllable variability (a.k.a. empowerment!). But in undirected play, we shift toward embracing pure variability. Check out our forthcoming Phil. Trans. A (2026) paper!

When it comes to goal-directed work, people prioritize controllable variability (a.k.a. empowerment!).

But in undirected play, we shift toward embracing pure variability.

Check out our forthcoming Phil. Trans. A (2026) paper!
Dima Damen (@dimadamen) 's Twitter Profile Photo

Join us for 3rd Perception Test Workshop &Challenge #ICCV2025 #iccv2025 *NEW* this year: - 3 unified tracks - novel interpretability track - guest tracks: KiVA and Physics-IQ - 4 world-class speakers (see pic) Up to 50K in prizes Google DeepMind 🧵 for details

Join us for 3rd Perception Test Workshop &amp;Challenge <a href="/ICCVConference/">#ICCV2025</a> #iccv2025 
*NEW* this year: 
- 3 unified tracks
- novel interpretability track
- guest tracks: KiVA and Physics-IQ
- 4 world-class speakers (see pic)
Up to 50K in prizes <a href="/GoogleDeepMind/">Google DeepMind</a> 
🧵 for details
Shiry Ginosar (@shiryginosar) 's Twitter Profile Photo

I am giving a talk this morning at 10:40AM PST as part of Workshop on Assessing World Models (ICML) at #ICML2025 Title: "What Do Vision and Vision-Language Models Really Know About the World?" Come join us! worldmodelworkshop.org