Reposted by @lucaschubu.bsky.socialEric Schulz @ericschulz.bsky.social · 03/11/2025🚀 We are hiring! 🚀 🔍 Join us as a Postdoctoral Researcher (fully-funded) at the Helmholtz Institute for Human-Centered AI in Munich. 13327
Reposted by @lucaschubu.bsky.socialMarcel Binz @marcelbinz.bsky.social · 02/07/2025Excited to see our Centaur project out in @nature.com. TL;DR: Centaur is a computational model that predicts and simulates human behavior for any experiment described in natural language. 64412
lucaschubu.bsky.social @lucaschubu.bsky.social · 02/06/2025Excited to say our paper got accepted to ICML! We added new findings including this: models fine-tuned on a visual counterfactual reasoning task do not generalize to the underlying factual physical reasoning task, even with test images matched to the fine-tuning data set. 161
lucaschubu.bsky.social @lucaschubu.bsky.social · 25/02/2025In previous work we found that VLMs fall short of human visual cognition. To make them better, we fine-tuned them on visual cognition tasks. We find that while this improves performance on the fine-tuning task, it does not lead to models that generalize to other related tasks: 195
