4 papers
Meta-learning as a principle for human-like visual representations
Can Demircan, Marcel Binz, Alireza Modirshanechi +1
The structure of human visual representations underpins our capacity for adaptive behaviour. While pretrained neural networks model human visual representations with unprecedented…
Post-training makes large language models less human-like
Marcel Binz, Elif Akata, Abdullah Almaatouq +76
Large language models (LLMs) are increasingly used as surrogates for human participants, but it remains unclear which models best capture human behavior and why. To address this, w…
Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
Alireza Modirshanechi, Benjamin Eysenbach, Peter Dayan +1
Unsupervised pretraining has driven empirical advances in goal-conditioned reinforcement learning (GCRL), but its theoretical foundations remain poorly understood. In particular, a…
Centaur: a foundation model of human cognition
Marcel Binz, Elif Akata, Matthias Bethge +37
Establishing a unified theory of cognition has been a major goal of psychology. While there have been previous attempts to instantiate such theories by building computational model…