🚨Pre-print alert:🚨 Have we built machines that think like people? In new work, led by Luca Schulze Buschoff and Elif Akata and together with Matthias Bethge, we assess multi-modal #LLMs reasoning abilities in three core domains: intuitive physics, causality, and intuitive psychology.

Come work with Can Demircan and me on semantic label smoothing (it's cool, I promise)!

Object slots are great for compositional generalization, but can models without these inductive biases learn compositional representations without supervision too? Yes! Unsupervised learning on object videos yields entangled, yet compositional latent codes for objects!

Excited to announce Centaur -- the first foundation model of human cognition. Centaur can predict and simulate human behavior in any experiment expressible in natural language. You can readily download the model from Hugging Face and test it yourself: huggingface.co/marcelbinz/Lla…

Our paper (with Elif Akata, Matthias Bethge, Helmholtz Institute for Human-Centered AI) on visual cognition in multimodal large language models is now out in Nature Machine Intelligence. We find that VLMs fall short of human capabilities in intuitive physics, causal reasoning, and intuitive psychology. nature.com/articles/s4225…

Happy to say we made the cover too! (Elif Akata, Helmholtz Institute for Human-Centered AI)

Excited to see our Centaur project out in nature. TL;DR: Centaur is a computational model that predicts and simulates human behavior for any experiment described in natural language.