collaborators

7 papers

cs.CV2026

Medical Context Distorts Decisions in Clinical Vision Language Models

David Restrepo, Ira Ktena, Maria Vakalopoulou +2

Vision-language models (VLMs) are increasingly proposed for clinical decision support, yet their reliability in real-world scenarios that require integrating both visual and textua…

cs.CV2026

PVeRA: Probabilistic Vector-Based Random Matrix Adaptation

Leo Fillioux, Enzo Ferrante, Paul-Henry Cournède +2

Large foundation models have emerged in the last years and are pushing performance boundaries for a variety of tasks. Training or even finetuning such models demands vast datasets…

cs.LG2026

On the Cone Effect and Modality Gap in Medical Vision-Language Embeddings

David Restrepo, Miguel L Martins, Chenwei Wu +5

Vision-Language Models (VLMs) exhibit a characteristic "cone effect" in which nonlinear encoders map embeddings into highly concentrated regions of the representation space, contri…

cs.CY2026

Implicit Bias in LLMs for Transgender Populations

Micaela Hirsch, Marina Elichiry, Blas Radi +6

Large language models (LLMs) have been shown to exhibit biases against LGBTQ+ populations. While safety training may lessen explicit expressions of bias, previous work has shown th…

cs.CV2025

On the Risk of Misleading Reports: Diagnosing Textual Biases in Multimodal Clinical AI

David Restrepo, Ira Ktena, Maria Vakalopoulou +2

Clinical decision-making relies on the integrated analysis of medical images and the associated clinical reports. While Vision-Language Models (VLMs) can offer a unified framework…

cs.CV2025

Fairness and Robustness of CLIP-Based Models for Chest X-rays

Théo Sourget, David Restrepo, Céline Hudelot +3

Motivated by the strong performance of CLIP-based models in natural image-text domains, recent efforts have adapted these architectures to medical tasks, particularly in radiology,…