107 citations · 107 across the 5 of their papers we have counts for
5 papers
On the Inherent Privacy Amplification of Missing Data
Simon Roburin, Rafaël Pinot, Rafa{ë}l Pinot +1
Privacy preservation is critical in many high-stakes domains such as medicine and finance, where sensitive data must be analyzed without compromising individual confidentiality. At…
Retrieval-Based Interleaved Visual Chain-of-Thought in Real-World Driving Scenarios
Charles Corbière, Simon Roburin, Syrielle Montariol +2
While chain-of-thought (CoT) prompting improves reasoning in large language models, its effectiveness in vision-language models (VLMs) remains limited due to over-reliance on textu…
Take One Gram of Neural Features, Get Enhanced Group Robustness
Simon Roburin, Charles Corbière, Gilles Puy +4
Predictive performance of machine learning models trained with empirical risk minimization (ERM) can degrade considerably under distribution shifts. The presence of spurious correl…
Localizing Objects with Self-Supervised Transformers and no Labels
Oriane Siméoni, Gilles Puy, Huy V. Vo +6
Localizing objects in image collections without supervision can help to avoid expensive annotation campaigns. We propose a simple approach to this problem, that leverages the activ…
Spherical Perspective on Learning with Normalization Layers
Simon Roburin, Yann de Mont-Marin, Andrei Bursuc +3
Normalization Layers (NLs) are widely used in modern deep-learning architectures. Despite their apparent simplicity, their effect on optimization is not yet fully understood. This…