Arnau Marin-Llobet

Realignment of representational drift in mouse visual cortex via flexible electrode arrays.

Vision-Language Models Suppress Female Representations Under Ambiguous Input

LALS (Latent Association Leaning Score) is introduced, a zero-shot metric that projects visual-token activations into the model's text-embedding space to measure concept associations per token and layer and shows that culturally loaded visual cues further modulate these internal associations.

Individual Parameters in Weight-Sparse Transformers Appear Interpretable

This work introduces an automated LLM pipeline that writes a short, human-readable description of when a weight matters and verifies it on held-out text, crediting a weight only if its description generalizes.