Curious about this AND attending #ICLR 26 🇧🇷?
Come to our poster with @annewzonneveld.bsky.social 📆 Sat Apr 25, Poster session 5, 10:30-13:00 📍Pavillion 3 P3 - #1525, to learn how video models align with dynamic brain representations!
🕸️ sergeantchris.github.io/brain_dynami...
Video
Christina Sartzetaki @ ICLR
sergeylevine.substack.com/p/language-m...
Excited to announce that this has been accepted in ICLR 25!
🚨🚨📄 Check out our new preprint!
Our results reveal novel insights on how continuous visual input is integrated in the human brain💡, beyond the standard temporal processing hierarchy from low to high-level representations
Excited to be presenting this paper at #ICLR2025 this week!
Come to the poster if you want to know more about how human brains and DNNs process video 🧠🤖
📆 Sat 26 Apr, 10:00-12:30 - Poster session 5 (#64)
📄 openreview.net/pdf?id=LM4PY...
🌐 sergeantchris.github.io/hundred_mode...
Excited to be presenting this with @annewzonneveld.bsky.social at #ICLR2026 in Rio 🇧🇷 in a few weeks! Stay tuned for the project page and poster details - dm if you want to chat about brains and video models :)
Why language models succeeded where video models failed, and what that teaches us about AI
Hey video-aficionados #VSS2026, this morning @sargechris.bsky.social presents our recent ICLR paper on benchmarking video ANNs on human EEG, suggesting an extended phase of mid-level video feature processing beyond the feed-forward sweep! (Pavilion 425)
(paper here: openreview.net/pdf?id=bSsNS...)
Christina Sartzetaki @ ICLR
✨ The VIS Lab at the #University of #Amsterdam is proud and excited to announce it has #TWELVE papers 🚀 accepted for the leading #AI-#makers conference on representation learning ( #ICLR2025 ) in Singapore 🇸🇬. 1/n
👇👇👇 @ellisamsterdam.bsky.social
New preprint (#neuroscience #deeplearning doi.org/10.1101/2025...)! We trained 20 DCNNs on 941235 images with varying scene segmentation (original. object-only, silhouette, background-only). Despite object recognition varying (27-53%), all networks showed similar EEG prediction.
