Pinned
🥳I am incredibly humbled and grateful to share that our work, "Aligning machine and human visual representations across abstraction levels," has been published today in @Nature: nature.com/articles/s4158… For more information see @AndrewLampinen’s post below ⬇️
What aspects of human knowledge do vision models like CLIP fail to capture, and how can we improve them? We suggest models miss key global organization; aligning them makes them more robust. Check out @lukas_mut's work, finally out (in @Nature!?) + our new blogpost! 1/4
