Super cool project that I really enjoyed being part of! tl;dr - when a human or model encounters new visual stimuli, how closely is it mapped to other, previously encountered concepts? (Come for weird dog-monster, stay for the science 🙂 )
Gaurav Kamath
Super excited to finally announce my latest research “Would you still call this Dax? Novel Visual References in VLMs and Humans”!
We studied how vision-language models (VLMs) adopt new visual concepts and map them to language compared to humans, and found that…