203 citations · 334 across the 22 of their papers we have counts for
22 papers
RadMatch: Auditable Radiology Report Evaluation via Finding-Level Matching
Charles Corbière, Léo Machado, Aubin Charley +3
As AI systems are increasingly used to draft radiology reports, reliably evaluating their clinical quality remains a critical challenge. Large language model (LLM)-based metrics ar…
Curia-MAE: Multi-Modal Multi-Anatomy MAE Pre-Training for 3D Medical Image Segmentation
Théo Danielou, Antoine Saporta, Léo Alberge +1
Radiology foundation models learn transferable representations that can be adapted to new tasks by training only small layers on top of a frozen encoder. Dense prediction tasks suc…
Jolia: Concept-Level Vision-Language Alignment for 3D CT Contrastive Learning
Julien Khlaut, Charles Corbière, Baptiste Callard +9
Vision-language contrastive pretraining has become the dominant recipe for 3D medical foundation models, leveraging the large volumes of paired scans and reports produced in clinic…
Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge
Asbjørn Munk, Stefano Cerri, Vardan Nersesjan +81
Clinical deployment of automated brain MRI analysis faces a fundamental challenge: clinical data is heterogeneous and noisy, and high-quality labels are prohibitively costly to obt…
Curia-2: Scaling Self-Supervised Learning for Radiology Foundation Models
Antoine Saporta, Baptiste Callard, Corentin Dancette +5
The rapid growth of medical imaging has fueled the development of Foundation Models (FMs) to reduce the growing, unsustainable workload on radiologists. While recent FMs have shown…
RadImageNet-VQA: A Large-Scale CT and MRI Dataset for Radiologic Visual Question Answering
Léo Butsanets, Charles Corbière, Julien Khlaut +2
In this work, we introduce RadImageNet-VQA, a large-scale dataset designed to advance radiologic visual question answering (VQA) on CT and MRI exams. Existing medical VQA datasets…
Curia: A Multi-Modal Foundation Model for Radiology
Corentin Dancette, Julien Khlaut, Antoine Saporta +20
AI-assisted radiological interpretation is based on predominantly narrow, single-task models. This approach is impractical for covering the vast spectrum of imaging modalities, dis…
RAPS-3D: Efficient interactive segmentation for 3D radiological imaging
Théo Danielou, Daniel Tordjman, Pierre Manceron +1
Promptable segmentation, introduced by the Segment Anything Model (SAM), is a promising approach for medical imaging, as it enables clinicians to guide and refine model predictions…
RadSAM: Segmenting 3D radiological images with a 2D promptable model
Julien Khlaut, Elodie Ferreres, Daniel Tordjman +4
Medical image segmentation is a crucial and time-consuming task in clinical care, where mask precision is extremely important. The Segment Anything Model (SAM) offers a promising a…
ONCOPILOT: A Promptable CT Foundation Model For Solid Tumor Evaluation
Léo Machado, Hélène Philippe, Élodie Ferreres +12
Carcinogenesis is a proteiform phenomenon, with tumors emerging in various locations and displaying complex, diverse shapes. At the crucial intersection of research and clinical pr…
Efficient Medical Question Answering with Knowledge-Augmented Question Generation
Julien Khlaut, Corentin Dancette, Elodie Ferreres +3
In the expanding field of language model applications, medical knowledge representation remains a significant challenge due to the specialized nature of the domain. Large language…
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning
Mustafa Shukor, Alexandre Rame, Corentin Dancette +1
Following the success of Large Language Models (LLMs), Large Multimodal Models (LMMs), such as the Flamingo model and its subsequent competitors, have started to emerge as natural…
UnIVAL: Unified Model for Image, Video, Audio and Language Tasks
Mustafa Shukor, Corentin Dancette, Alexandre Rame +1
Large Language Models (LLMs) have made the ambitious quest for generalist agents significantly far from being a fantasy. A key hurdle for building such general models is the divers…
Improving Selective Visual Question Answering by Learning from Your Peers
Corentin Dancette, Spencer Whitehead, Rishabh Maheshwary +5
Despite advances in Visual Question Answering (VQA), the ability of models to assess their own correctness remains underexplored. Recent work has shown that VQA models, out-of-the-…
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
Alexandre Ramé, Guillaume Couairon, Mustafa Shukor +4
Foundation models are first pre-trained on vast unsupervised datasets and then fine-tuned on labeled data. Reinforcement learning, notably from human feedback (RLHF), can further a…
eP-ALM: Efficient Perceptual Augmentation of Language Models
Mustafa Shukor, Corentin Dancette, Matthieu Cord
Large Language Models (LLMs) have so far impressed the world, with unprecedented capabilities that emerge in models at large scales. On the vision side, transformer models (i.e., V…
Dynamic Query Selection for Fast Visual Perceiver
Corentin Dancette, Matthieu Cord
Transformers have been matching deep convolutional networks for vision architectures in recent works. Most work is focused on getting the best results on large-scale benchmarks, an…
Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization
Alexandre Rame, Corentin Dancette, Matthieu Cord
Learning robust models that generalize well under changes in the data distribution is critical for real-world applications. To this end, there has been a growing surge of interest…
Beyond Question-Based Biases: Assessing Multimodal Shortcut Learning in Visual Question Answering
Corentin Dancette, Remi Cadene, Damien Teney +1
We introduce an evaluation methodology for visual question answering (VQA) to better diagnose cases of shortcut learning. These cases happen when a model exploits spurious statisti…
Overcoming Statistical Shortcuts for Open-ended Visual Counting
Corentin Dancette, Remi Cadene, Xinlei Chen +1
Machine learning models tend to over-rely on statistical shortcuts. These spurious correlations between parts of the input and the output labels does not hold in real-world setting…
RUBi: Reducing Unimodal Biases in Visual Question Answering
Remi Cadene, Corentin Dancette, Hedi Ben-younes +2
Visual Question Answering (VQA) is the task of answering questions about an image. Some VQA models often exploit unimodal biases to provide the correct answer without using the ima…
Sampling strategies in Siamese Networks for unsupervised speech representation learning
Rachid Riad, Corentin Dancette, Julien Karadayi +3
Recent studies have investigated siamese network architectures for learning invariant speech representations using same-different side information at the word level. Here we invest…