5 citations · 6 across the 7 of their papers we have counts for
3 papers · 1 filter
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…
Can Vision Language Models Learn Intuitive Physics from Interaction?
Luca M. Schulze Buschoff, Konstantinos Voudouris, Can Demircan +1
Pre-trained vision language models do not have good intuitions about the physical world. Recent work has shown that supervised fine-tuning can improve model performance on simple p…