Taylor Webb
Studying cognition in humans and machines scholar.google.com/citations?user=WCmr…
- Very excited about this work looking at the emergent mechanisms that vision language models use to perform structured visual processing, mirroring a computational strategy (visual indexing) proposed in cognitive science, but here learned by VLMs. Check out the paper/thread for more details!
- The visual world is composed of objects, and those objects are composed of features. But do VLMs exploit this compositional structure when processing multi-object scenes? In our 🆒🆕 #ICLR2026 paper, we find they do – via emergent symbolic mechanisms for visual binding. 🧵👇
- This was a blast! Thanks for joining us!
- Was a pleasure to discuss the cognitive basis of reasoning at an @ivado.bsky.social workshop with legends like @alisongopnik.bsky.social @lauraruis.bsky.social @taylorwwebb.bsky.social and Andrew Granville!
