activity
20242026
collaborators

6 papers

math.CO2026

Fast SDP certification of neural networks : towards large multi-class datasets

Margot Boyer, Clément Rambour, Zacharie Alès +1

We present a new quadratic model for the certification problem in adversarial robustness, which simultaneously accounts for all possible target classes. Building on this model, we…

cs.CV2025

DAFTED: Decoupled Asymmetric Fusion of Tabular and Echocardiographic Data for Cardiac Hypertension Diagnosis

Jérémie Stym-Popper, Nathan Painchaud, Clément Rambour +3

Multimodal data fusion is a key approach for enhancing diagnosis in medical applications. We propose an asymmetric fusion strategy starting from a primary modality and integrating…

cs.CV2025

CLIPTTA: Robust Contrastive Vision-Language Test-Time Adaptation

Marc Lafon, Gustavo Adolfo Vargas Hakim, Clément Rambour +2

Vision-language models (VLMs) like CLIP exhibit strong zero-shot capabilities but often fail to generalize under distribution shifts. Test-time adaptation (TTA) allows models to up…

cs.CV2025

ViLU: Learning Vision-Language Uncertainties for Failure Prediction

Marc Lafon, Yannis Karmim, Julio Silva-Rodríguez +6

Reliable Uncertainty Quantification (UQ) and failure prediction remain open challenges for Vision-Language Models (VLMs). We introduce ViLU, a new Vision-Language Uncertainty quant…

cs.LG2025

RT-HCP: Dealing with Inference Delays and Sample Efficiency to Learn Directly on Robotic Platforms

Zakariae El Asri, Ibrahim Laiche, Clément Rambour +2

Learning a controller directly on the robot requires extreme sample efficiency. Model-based reinforcement learning (RL) methods are the most sample efficient, but they often suffer…

cs.CV2024

GalLoP: Learning Global and Local Prompts for Vision-Language Models

Marc Lafon, Elias Ramzi, Clément Rambour +2

Prompt learning has been widely adopted to efficiently adapt vision-language models (VLMs), e.g. CLIP, for few-shot image classification. Despite their success, most prompt learnin…