collaborators

8 papers

cs.CY2026

Language Models Embody and Amplify Human Cognitive Distortions: What Is to Be Done?

Arnau Marin-Llobet, Steven A. Lehr, Mahzarin R. Banaji

Human judgment is fundamentally prone to error. A promise of AI is that it will rid decisions of bias and ensure a fairer and safer world for all. Yet research unequivocally demons…

cs.LG2026

Individual Parameters in Weight-Sparse Transformers Appear Interpretable

Arnau Marin-Llobet, Stefan Heimersheim

A central goal of mechanistic interpretability is to understand how neural networks work and what each individual component does. Dominant circuit-finding approaches focus on a spe…

q-bio.NC2026

Can neurons speak? Semantic narration of vision at single-cell resolution

Arnau Marin-Llobet, Richard Hakim, Sara Matias +3

Identifying what individual neurons encode in higher-order visual cortex is an open problem. Responses resist intuitive parameterization, and the deep-network embeddings used in th…

cs.CV2026

Vision-Language Models Suppress Female Representations Under Ambiguous Input

Arnau Marin-Llobet, Simon Henniger, Mahzarin R. Banaji

Alignment teaches vision-language models (VLMs) to avoid expressing demographic biases, and when gender is clearly visible they largely succeed. Far less is known about ambiguous i…

cs.CV2026

LiFT: Lifted Inter-slice Feature Trajectories for 3D Image Generation from 2D Generators

Xinhe Zhang, Yuyang Zhang, Pengfei Jin +3

High-resolution 3D medical image generation remains challenging because fully volumetric models are computationally expensive, while efficient 2D slice generators often fail to pre…

cs.CL2026

Automated Interpretability and Feature Discovery in Language Models with Agents

Arnau Marin-Llobet, Javier Ferrando

We introduce an autonomous multiagent framework for mechanistic interpretability that automates both explaining and finding internal features in large language models. The system r…