activity
20242026
collaborators

11 papers

cs.LG2026

A Unifying Framework for Concept-Based Representational Similarity

Grégoire Dhimoïla, Victor Boutin, Agustin Martin Picard +2

Learned representations across models and modalities often exhibit striking structural similarities, suggesting shared underlying concept decompositions. However, concept alignment…

cs.CV2026

Not Too Generative, Not Too Discriminative: The Human Alignment Sweet Spot

Jorge Chang Ortega, Bastien Le Lan, Thomas Serre +1

A central question in computational vision is whether human-like visual representations are better explained by discriminative or generative learning. Existing comparisons, however…

cs.CV2026

Object-Level Explanations for Image Geolocation Models: a GeoGuessr use-case

Emilie Durrieu, Christophe Hurter, Philippe Muller +1

When humans play geolocation games such as GeoGuessr, they rely on concrete visual cues, such as road markings, vegetation, or architectural details, to infer where an image was ca…

cs.CV2026

Choosing the right basis for interpretability: Psychophysical comparison between neuron-based and dictionary-based representations

Julien Colin, Lore Goetschalckx, Thomas Fel +3

Interpretability research often adopts a neuron-centric lens, treating individual neurons as the fundamental units of explanation. However, neuron-level explanations can be undermi…

cs.CV2026

Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings

Grégoire Dhimoïla, Thomas Fel, Victor Boutin +1

Vision-language models (VLMs) align images and text with remarkable success, yet the geometry of their shared embedding space remains poorly understood. To probe this geometry, we…

cs.LG2025

Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models

Louis Béthune, David Vigouroux, Yilun Du +3

What is the shortest path between two data points lying in a high-dimensional space? While the answer is trivial in Euclidean geometry, it becomes significantly more complex when t…