4 papers · 1 filter
Concept-Guided Interpretability via Neural Chunking
Shuchen Wu, Stephan Alaniz, Shyamgopal Karthik +3
Neural networks are often described as black boxes, reflecting the significant challenge of understanding their internal workings and interactions. We propose a different perspecti…
Discovering Chunks in Neural Embeddings for Interpretability
Shuchen Wu, Stephan Alaniz, Eric Schulz +1
Understanding neural networks is challenging due to their high-dimensional, interacting components. Inspired by human cognition, which processes complex sensory data by chunking it…
Testing the Limits of Fine-Tuning for Improving Visual Cognition in Vision Language Models
Luca M. Schulze Buschoff, Konstantinos Voudouris, Elif Akata +3
Pre-trained vision language models still fall short of human visual cognition. In an effort to improve visual cognition and align models with human behavior, we introduce visual st…
Next state prediction gives rise to entangled, yet compositional representations of objects
Tankred Saanum, Luca M. Schulze Buschoff, Peter Dayan +1
Compositional representations are thought to enable humans to generalize across combinatorially vast state spaces. Models with learnable object slots, which encode information abou…