//
sign in
Post
by @danabra.mov
PostEmbed
by @danabra.mov
Record
by @jimpick.com
Record
by @atsui.org
+ new component
Post
Happy to announce that this work has officially been accepted to ICLR 2026! ๐Ÿ‡ง๐Ÿ‡ท Please check it out and let's connect in Rio de Janeiro in April!
3mo
Anne Zonneveld
๐Ÿ“ข New preprint, together with @sargechris.bsky.social! Building on @sargechris.bsky.social's previous work, we benchmark 100+ image and video models ๐Ÿค– on brain representational alignment, this time to EEG data of humans ๐Ÿง  watching videos! ๐Ÿงตโฌ‡๏ธ www.biorxiv.org/content/10.1...
7mo
The human brain is the most efficient and versatile system for processing dynamic visual input. By comparing representations from deep video models to brain activity, we can gain insights into mechani...
www.biorxiv.org
The Human Brain as a Dynamic Mixture of Expert Models in Video Understanding
Anne Zonneveld