Efstratios Gavves
@egavves
Associate Professor & Co-Founder - Dynamical Deep Learning
I have not vouched for or promoted any other event in 10 years of existing on twitter. I broke my policy for this one. It’s not the AI part that makes this conference unique. It’s the collective brain power that is off the charts.
If you are in Athens this weekend, there is only one place to be (and no, I’m not referring to the beach). Greeks in AI 2025, the annual gathering of the most amazing Greek AI scientists and practitioners, will take place on 19-20 July. An event not to be missed!
Or later ICCV2025 on temporal self Sorenson, check it out!
New paper out - accepted at @ICCVConference We introduce MoSiC, a self-supervised learning framework that learns temporally consistent representations from video using motion cues. Key idea: leverage long-range point tracks to enforce dense feature coherence across time.🧵
New paper out - accepted at @ICCVConference We introduce MoSiC, a self-supervised learning framework that learns temporally consistent representations from video using motion cues. Key idea: leverage long-range point tracks to enforce dense feature coherence across time.🧵
New paper accepted at @ICCVConference: MoSiC, our new post-pretraining technique for upgrading vision foundation models like DINOv2R using videos, thanks to strong point trackers and Sinkhorn clustering. Check the thread below :)
New paper out - accepted at @ICCVConference We introduce MoSiC, a self-supervised learning framework that learns temporally consistent representations from video using motion cues. Key idea: leverage long-range point tracks to enforce dense feature coherence across time.🧵
An excellent work by @ZadaianchukML , it's not every year that an MSc project gets a CVPR oral!!
How to represent dynamic real-world data both consistently and efficiently, while reflecting the compositional object-centric structure of the world? Contrast your slots! ...with our new SlotContrast method(🚀#CVPR2025 Oral🚀)! 🌐website: slotcontrast.github.io 🧵🧵🧵 1/n
How to represent dynamic real-world data both consistently and efficiently, while reflecting the compositional object-centric structure of the world? Contrast your slots! ...with our new SlotContrast method(🚀#CVPR2025 Oral🚀)! 🌐website: slotcontrast.github.io 🧵🧵🧵 1/n
To all compatriots and friends of Greece: submit your most recent (already) published paper or a new idea to our inaugural Greeks in AI conference. Our first scientific get-together does not count as an archival event and it is a great opportunity to show your work to the rapidly…
🇬🇷 Greeks in AI is gaining traction! ✅ 200+ sign-ups 📄 30+ OpenReview submissions 🤝 Growing sponsor list 🚨 Limited space @ Serafeio — register now: greeksin.ai Stay tuned for updates on program, speakers & more! #GreeksInAI #AI #ML #Research #Greece #OpenReview
🇬🇷 Greeks in AI is gaining traction! ✅ 200+ sign-ups 📄 30+ OpenReview submissions 🤝 Growing sponsor list 🚨 Limited space @ Serafeio — register now: greeksin.ai Stay tuned for updates on program, speakers & more! #GreeksInAI #AI #ML #Research #Greece #OpenReview
I agree, this year the due process didn't make sense. In my case, I got a paper rejected with a single WR, whose reviewer didn't even acknowledge the rebuttal (!!!); what is the point of confirmed then?
We are shut out of ICML with 2 out of 2 submissions rejected. In both cases, the paper will very-obviously get hundreds of citations long term. 4 observations on problematic aspects of the machine learning (submit->review->decision) cycle.
Check out our latest work on Cyberphysical AI, on how well can the latest video generative models simulate the true physics of the world and be reliable world models in that respect.
Preprint of today: Zhang, Cherniavskii, Zadaianchuk, Tragoudaras, et al., "MORPHEUS: Benchmarking Physical Reasoning of Video Generative Models with Real Physical Experiments" -- physics-from-video.github.io/morpheus-bench/ Can we use off-the-shelf video models to simulate physics? Perhaps not yet.
Registrations for the first Greeks in AI 2025 Symposium are now open! Due to space limitations, I suggest that you register as soon as possible if you would like to attend.
Greeks in AI 2025 will be the best 🇬🇷 tech event of the year. The conference will bring together some of the brightest scientists, researchers and techies in the world. Registrations are now officially open. Don’t miss out!
Great speakers and organizers: @papadopouli_m @KostasPenn @egavves @georgiagkioxari @AgoniGrammi @STsaftaris @iassael @pappasg69
Greeks in AI: The new AI place to be in the summer 😀 We got it all! Top scientists, advertising your recent work to colleagues, beautiful islands to blow some steam off just a couple of hours away, one of the best cuisines! greeksin.ai @KostasPenn
Coming this July, the Greeks 🇬🇷 in #AI 2025 Symposium in Athens, Greece.
📢Introducing #AIIndex2025: This year's report highlights the most critical trends in AI – from shifting geopolitical landscape and rapid technological evolution, to AI’s expanding role in science and medicine, business, and public life. Read more: hai.stanford.edu/ai-index/2025-…
🔥Happy to share that our paper on controllable object-centric representations (CTRL-O) has been accepted to #CVPR2025 @CVPR w/ @ZadaianchukML @_rabiulawal @maxseitzer @egavves @aagrawalAA 🔜 Updated paper with downstream experiments and detailed thread coming soon!
🚀 Introducing a novel approach for controllable object-centric learning! By conditioning on language descriptions, we unlock targeted object-language binding in complex scenes—no mask supervision needed! Here's how it works 👇 🧵 #NeurIPS2024