Sign in

Shiry Ginosar

@shiryginosar.bsky.social
457 followers 58 following 54 posts

Assistant Professor @tticconnect.bsky.social How should machines represent the world? shiry.ttic.edu

PostsRepliesMedia
Reposted by Shiry Ginosar
TTIC @tticconnect.bsky.social · 27/09/2026
1/4 The Dynamics of Deep Learning. "Trying to understand deep learning...comes down to understanding this interaction of three components that make the deep learning system," said @danielkunin.bsky.social, speaking at TTIC in April last year. Video: www.youtube.com/watch?v=4eMW...
youtube.com
"Learning Mechanics of Neural Networks" - Daniel Kunin, Young Researcher Series Seminar
YouTube video by TTIC
121
Reposted by Shiry Ginosar
TTIC @tticconnect.bsky.social · 17/09/2026
1/5 "Sometimes words are not enough," said Yael Vinker, @yaelvinker.bsky.social, of @csail.mit.edu at TTIC's Young Researcher Seminar Series in Nov '25. "I want to teach machines to speak the language of sketches." This involves using visual means to communicate concepts under a set of constraints.
222
Shiry Ginosar @shiryginosar.bsky.social · 08/09/2026
#ECCV2026 workshop! 🌐 Spatial Intelligence: from Table-top to City-scale The 4th Perception Test Challenge 📅 9 Sep 2026 | 09:00 – 12:30 CEST 🎙 Keynotes by Jack Gallant (UC Berkeley), Laura Leal-Taixé (TUM), and Andrew Davison (Imperial). 🔗 Schedule: perception-test-challenge.github.io
perception-test-challenge.github.io
The Fourth Perception Test Challenge at ECCV 2026
The 4th Perception Test Challenge at ECCV 2026 evaluates models on small scale and large scale spatial intelligence, with 20K EUR in prizes.
151
Shiry Ginosar @shiryginosar.bsky.social · 22/07/2026
Calling all #SIGGRAPH2026 film editing buffs! 🎬 Come check out our FilmGPT talk! 🕝 2:40 PM PDT 📍 Room 408B
020
Shiry Ginosar @shiryginosar.bsky.social · 22/07/2026
Introducing FilmGPT 🎬 (#SIGGRAPH2026) Can we learn the grammar of film directly from movies? We train an autoregressive transformer on feature films to edit raw footage into coherent cinematic sequences, without generating new pixels. Project page: mudtriangle.com/filmgpt Demo below👇
183
Shiry Ginosar @shiryginosar.bsky.social · 17/04/2026
Fans of the Platonic Representation Hypothesis argue that all representations converge. However, we find that the current experimental evidence for the PRH is surprisingly fragile. Instead, models may develop their own “Umwelten” (distinct, model-specific views of the world).
071
Shiry Ginosar @shiryginosar.bsky.social · 13/04/2026
Great to see corroborating evidence to our motion-forecasting.github.io work from other groups! Check out this concurrent great work from @stefanabaumann.bsky.social, @jannik-w.bsky.social, @tommymarto.bsky.social, Mahdi M. Kalayeh, and Björn Ommer (@compvis.bsky.social)
021
Reposted by Shiry Ginosar
Tomer Ullman @tomerullman.bsky.social · 06/04/2026
riddle for kids that combines first/third person perspectives: where are the firefighters on the map?
3195
Shiry Ginosar @shiryginosar.bsky.social · 02/04/2026
We take a step toward behavior modeling in the wild: general non-rigid motion forecasting! The coolest part: training on diverse animal behavior is enough to generalize to completely OOD motion. Amazing work from @neerjathakkar.bsky.social, with @carldoersch.bsky.social's technical know-how!
061
Shiry Ginosar @shiryginosar.bsky.social · 12/03/2026
🚨 Can real-world human experiences shape the future of generative AI and computer vision systems? Find out at Humans of Generative AI (HuG) workshop at #CVPR2026 🚨 Accepting 1-page extended abstracts for lightning talks and posters 🗓 Deadline: April 10, 2026 See: humansofgenerativeai.github.io
020
Shiry Ginosar @shiryginosar.bsky.social · 06/11/2025
💫 I am recruiting exceptional PhD students & postdocs for my lab @tticconnect.bsky.social this year! Application details: www.ttic.edu/studentappli...
073
Shiry Ginosar @shiryginosar.bsky.social · 21/10/2025
TTIC is hiring tenure track faculty! Come join us in Chicago! I am sadly not at ICCV but Greg Shakhnarovich (Vision) home.ttic.edu/~gregory/ and Matt Walter (Robotics) home.ttic.edu/~mwalter/ are around and would be happy to chat.
092
Shiry Ginosar @shiryginosar.bsky.social · 20/10/2025
@alisongopnik.bsky.social's talk happening now!! Ballroom B @iccv.bsky.social
051
Shiry Ginosar @shiryginosar.bsky.social · 19/10/2025
Join us TODAY for the 3rd Perception Test Challenge perception-test-challenge.github.io @iccv.bsky.social Ballroom B, Full day Amazing lineup of speakers: Ali Farhadi, @alisongopnik.bsky.social, Phlipp Krahenbul, @phillipisola.bsky.social
164
Shiry Ginosar @shiryginosar.bsky.social · 19/10/2025
TODAY! Artificial Social Intelligence Workshop @iccv.bsky.social Room 317B, Full day Social reasoning, multimodality, and embodiment! Speakers: Evonne Ng, @tianminshu.bsky.social @hyunwoo-kim.bsky.social, @diyiyang.bsky.social ang.bsky.social, @hokulabs.bsky.social, @michael-j-black.bsky.social
033
Shiry Ginosar @shiryginosar.bsky.social · 03/09/2025
KiVA (Kid-inspired Visual Analogies) Challenge Test Phase is NOW LIVE (Sep 1–Oct 6)! Can your model reason like a child? Can it beat adults? 🥇 $1,000 🥈 $500 for 2 runner-ups Join/submit: t.co/zQwA1Nmohy And join us at @iccv.bsky.social in Hawaii!! 🌴
063
Shiry Ginosar @shiryginosar.bsky.social · 18/07/2025
I am giving a talk this morning at 10:40AM PST as part of the #ICML2025 Workshop on Assessing World Models. Title: "What Do Vision and Vision-Language Models Really Know About the World?" Come join us! www.worldmodelworkshop.org
worldmodelworkshop.org
ICML Workshop on Assessing World Models
Date: Friday, July 18 2025 Time: 8:45am - 5:15pm (Pacific Time) Location: West Ballroom B at ICML 2025 in Vancouver, Canada (Same Floor as Registration)
011
Reposted by Shiry Ginosar
Dima Damen @ECCV 2026 @dimadamen.bsky.social · 16/07/2025
Join us for 3rd Perception Test Workshop &Challenge @iccv.bsky.social #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 sponsored by Google DeepMind 🧵 for details [1/4]
183
Shiry Ginosar @shiryginosar.bsky.social · 15/07/2025
🧠How “old” is your model? Put it to the test with the KiVA Challenge: a new benchmark for abstract visual reasoning, grounded in real developmental data from children and adults. 🏆 Prizes: 🥇$1K to the top model 🥈🥉$500 📅 Deadline: 10/7/25 🔗 kiva-challenge.github.io @iccv.bsky.social
kiva-challenge.github.io
KiVA Challenge @ ICCV 2025
12312
Shiry Ginosar @shiryginosar.bsky.social · 25/06/2025
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!
120
Reposted by Shiry Ginosar
Blake Richards @tyrellturing.bsky.social · 25/04/2025
Check out our new paper at #ICLR2025, where we show that multi-task neural decoding is both possible and beneficial. As well, the latents of a model trained only on neural activity capture information about brain regions and cell-types. Step-by-step, we're gonna scale up folks! 🧠📈 🧪 #NeuroAI
05313
Reposted by Shiry Ginosar
KQED Forum @kqedforum.bsky.social · 26/04/2025
🎧 Listen to the podcast! Professor @alisongopnik.bsky.social and @newamerica.org CEO @slaughteram.bsky.social spoke with @alexis-madrigal.bsky.social about how rethinking our approach to caregiving and how we support care providers could lead to a better society. 🔗:
buff.ly
Alison Gopnik and Anne-Marie Slaughter on Why We’re Not Paying Enough Attention to Caregiving
KQED's Forum · Episode
063
Shiry Ginosar @shiryginosar.bsky.social · 23/04/2025
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.... Catch our #ICLR2025 poster today to see where models still fall short! Thurs. April 24 3-5:30 pm Halls 3 + 2B #312
2257
Shiry Ginosar @shiryginosar.bsky.social · 16/04/2025
Neuroscience is finally taking more and more baby steps towards running experiments at scale!
030
Reposted by Shiry Ginosar
The Transmitter @thetransmitter.bsky.social · 15/04/2025
In his new book, published today, Nachum Ulanovsky calls on the field to embrace naturalistic conditions and move away from overcontrolled experiments. #neuroskyence www.thetransmitter.org/systems-neur...
thetransmitter.org
‘Natural Neuroscience,’ an excerpt
In his new book, Nachum Ulanovsky calls on the field to embrace naturalistic conditions and move away from overcontrolled experiments.
18034
Shiry Ginosar @shiryginosar.bsky.social · 15/04/2025
Welcome to TTIC!! We are so excited to have you join us!!
010
Reposted by Shiry Ginosar
carldoersch.bsky.social @carldoersch.bsky.social · 09/04/2025
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
1259
Shiry Ginosar @shiryginosar.bsky.social · 06/02/2025
This shows the importance of expressive (rather than functional) gesture really nicely in a beautiful non-anthropomorphic robot design machinelearning.apple.com/research/ele...
machinelearning.apple.com
ELEGNT: Expressive and Functional Movement Design for Non-Anthropomorphic Robot
Nonverbal behaviors such as posture, gestures, and gaze are essential for conveying internal states, both consciously and unconsciously, in…
000
Reposted by Shiry Ginosar
Noah Snavely @snavely.bsky.social · 06/02/2025
Did Italo Calvino discover bag of words and topic models in 1979?
She explained to me that a suitably programmed computer can read a novel in a few minutes and record the list of all the words contained in the text, in order of frequency. "That way I can have an already completed reading at hand," Lotaria says, "with an incalculable saving of time. What is the reading of a text, in fact, except the recording of certain thematic recurrences, certain insistences of forms and meanings? An electronic reading supplies me with a list of the frequencies, which I have only to glance at to form an idea of the problems the book suggests to my critical study. Naturally, at the highest frequencies the list records countless articles, pronouns, particles, but I don't pay them any attention. I head straight for the words richest in meaning; they can give me a fairly precise notion of the book."Lotaria brought me some novels electronically transcribed, in the form of words listed in the order of their frequency. "In a novel of fifty to a hundred thousand words," she said to me, "I advise you to observe immediately the words that are repeated about twenty times. Look here. Words that appear nineteen times:

blood, cartridge belt, commander, do, have, im-
mediately, it, life, seen, sentry, shots, spider, teeth,
together, your...   

"Words that appear eighteen times:

boys, cap, come, dead, eat, enough, evening,
French, go, handsome, new, passes, period, po-
tatoes, those, until...   

"Don't you already have a clear idea what it's about?" Lotaria says. "There's no question: it's a war novel, all action, brisk writing, with a certain underlying violence. The narration is entirely on the surface, I would say; but
5392
Reposted by Shiry Ginosar
steven t. piantadosi @spiantado.bsky.social · 05/02/2025
"That's what the people promulgating these horrible policies want - a bored, indifferent public who figures that who cares, nothing matters any more, it's gonna happen no matter what. But it doesn't have to. Never forget that: it doesn't have to happen." www.science.org/content/blog...
science.org
What's Happening Inside the NIH and NSF
02113
Reposted by Shiry Ginosar
Riccardo Fusaroli @fusaroli.eurosky.social · 19/01/2025
Why does Western paleolithic cave art strongly prefer animal side views and often abbreviations? Our new #eSymb preprint (osf.io/preprints/ps... w Pagnotta, Psujek, Mendoza Straffon and Tylén ) challenges long-held assumptions about these artistic choices based on cogsci experiments. 1/
513549
Shiry Ginosar @shiryginosar.bsky.social · 09/01/2025
New paper! A self-supervised object-centric 2.1D image representation using 3D Gaussians, extending MAE with a Gaussian bottleneck. While Gaussian splatting has been used for single-scene reconstruction, we’re the first to apply it to image representation learning! brjathu.github.io/gmae/.
2375
Shiry Ginosar @shiryginosar.bsky.social · 20/12/2024
Can video MAE scale? Yes. Do you need language to scale video models? No. arxiv.org/abs/2412.15212 Great rigorous benchmarking from my colleagues at Google DeepMind.
arxiv.org
Scaling 4D Representations
Scaling has not yet been convincingly demonstrated for pure self-supervised learning from video. However, prior work has focused evaluations on semantic-related tasks $\unicode{x2013}$ action classifi...
0122
Shiry Ginosar @shiryginosar.bsky.social · 02/12/2024
This is a fantastic example of just how different machine's perception of perception still is from human perception...
0124
Shiry Ginosar @shiryginosar.bsky.social · 22/11/2024
Advice for beginning grad students: The Secret of Happiness Story [Sufi, Turkey]. Nasrudin is known as much for his wisdom as his foolishness, and many are those who have sought out his teaching. One devotee tracked him down in the marketplace. 1/3
100
Shiry Ginosar @shiryginosar.bsky.social · 17/11/2024
@ari-holtzman.bsky.social this is for you!
110
Reposted by Shiry Ginosar
Brooke Jarvis @brookejarvis.bsky.social · 15/11/2024
Today in relatable science: Gulls making a mysterious daily trip that turned out to be to a potato chip factory
A map of flight paths emanating from breeding colony of gulls, with this caption: Early on, LifeWatch noticed something odd. Most gulls were making daily trips to Mouscron, a city on the French border 65 km away. They went to investigate and found the birds bingeing on discarded snacks at the Roger & Roger potato factory.
247158984286
Shiry Ginosar @shiryginosar.bsky.social · 15/11/2024
Matt Walter is my new favorite roboticist! In a couple of minutes he is giving a talk about what he has been up to this year. Streaming here via Panopto: buff.ly/3ObJHhX
Talk title: Robots that learn from imitation and reinforcement
Friday Nov 15 at 12:30 CT
TTIC in person Room 530 or via Panopto
010
Shiry Ginosar @shiryginosar.bsky.social · 12/11/2024
I am recruiting exceptional PhD students & postdocs with an adventurous soul for my 💫new TTIC AI lab💫! We aim to understand intelligence, one pixel at a time, inspired by psychology, neuroscience, language, robotics, and the arts. Apply: www.ttic.edu/studentappli... sites.google.com/ttic.edu/ope...
TTIC building. Photo credit, TTIC.
0307
Shiry Ginosar @shiryginosar.bsky.social · 08/11/2024
Excited to give a talk at TTIC this morning! Friday, November 8th at 12:30pm CT: "Behavior prediction for interacting entities from video observations." Please join us in Room 530, or stream via Panopto: buff.ly/4ft8pGf
buff.ly
11/8/2024 - Research at TTIC - Shiry Ginosar, TTIC
030
Shiry Ginosar @shiryginosar.bsky.social · 08/11/2024
Hello Bluesky!!! Apologies in advance... I am going to try an experiment to import all my tweets from twitter... It may create some one-time spam... I should have done this before following folks but I just realized this... 🫣 I will report back if successful! www.wikihow.com/Import-Twitt...
wikihow.com
How To Import Twitter To Bluesky: Follows and Tweets
Seamlessly move from Twitter to Bluesky with this handy guide If you're migrating from Twitter/X to Bluesky, the new platform can feel lonely until you find people to follow. Fortunately, there are to...
110