22 citations · 36 across the 11 of their papers we have counts for
11 papers
MAPS: A Synthetic Dataset for Probing Vision Models in a Controlled 3D Scene Space
Santiago Galella, Pamela Osuna-Vargas, Maren Wehrheim +3
Modern vision models achieve strong performance on standard benchmarks, yet their aggregate accuracy reveals little about which scene properties drive their predictions. Existing r…
Mechanisms of Object Localization in Vision-Language Models
Timothy Schaumlöffel, Martina G. Vilas, Gemma Roig
Visually-grounded language models (VLMs) are highly effective in linking visual and textual information, yet they often struggle with basic classification and localization tasks. W…
Contextual inference from single objects in Vision-Language models
Martina G. Vilas, Timothy Schaumlöffel, Gemma Roig
How much scene context a single object carries is a well-studied question in human scene perception, yet how this capacity is organized in vision-language models (VLMs) remains poo…
Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning
Martina G. Vilas, Safoora Yousefi, Besmira Nushi +2
Reasoning models improve their problem-solving ability through inference-time scaling, allocating more compute via longer token budgets. Identifying which reasoning traces are like…
The Computational Complexity of Circuit Discovery for Inner Interpretability
Federico Adolfi, Martina G. Vilas, Todd Wareham
Many proposed applications of neural networks in machine learning, cognitive/brain science, and society hinge on the feasibility of inner interpretability via circuit discovery. Th…
Limited but consistent gains in adversarial robustness by co-training object recognition models with human EEG
Manshan Guo, Bhavin Choksi, Sari Sadiya +4
In contrast to human vision, artificial neural networks (ANNs) remain relatively susceptible to adversarial attacks. To address this vulnerability, efforts have been made to transf…
FovEx: Human-Inspired Explanations for Vision Transformers and Convolutional Neural Networks
Mahadev Prasad Panda, Matteo Tiezzi, Martina Vilas +3
Explainability in artificial intelligence (XAI) remains a crucial aspect for fostering trust and understanding in machine learning models. Current visual explanation techniques, su…
Position: An Inner Interpretability Framework for AI Inspired by Lessons from Cognitive Neuroscience
Martina G. Vilas, Federico Adolfi, David Poeppel +1
Inner Interpretability is a promising emerging field tasked with uncovering the inner mechanisms of AI systems, though how to develop these mechanistic theories is still much debat…
Analyzing Vision Transformers for Image Classification in Class Embedding Space
Martina G. Vilas, Timothy Schaumlöffel, Gemma Roig
Despite the growing use of transformer models in computer vision, a mechanistic understanding of these networks is still needed. This work introduces a method to reverse-engineer V…
The Algonauts Project 2023 Challenge: How the Human Brain Makes Sense of Natural Scenes
A. T. Gifford, B. Lahner, S. Saba-Sadiya +6
The sciences of biological and artificial intelligence are ever more intertwined. Neural computational principles inspire new intelligent machines, which are in turn used to advanc…
Net2Brain: A Toolbox to compare artificial vision models with human brain responses
Domenic Bersch, Kshitij Dwivedi, Martina Vilas +2
We introduce Net2Brain, a graphical and command-line user interface toolbox for comparing the representational spaces of artificial deep neural networks (DNNs) and human brain reco…