Publications (31)
Link and code: Fast indexing with graphs and compact regression codes
Matthijs Douze, Alexandre Sablayrolles, Hervé Jégou
Similarity search approaches based on graph walks have recently attained outstanding speed-accuracy trade-offs, taking aside the memory requirements. In this paper, we revisit thes…
Devstral: Fine-tuning Language Models for Coding Agent Applications
Abhinav Rastogi, Adam Yang, Albert Q. Jiang +100
We introduce Devstral-Small, a lightweight open source model for code agents with the best performance among models below 100B size. In this technical report, we give an overview o…
Large Memory Layers with Product Keys
Guillaume Lample, Alexandre Sablayrolles, Marc'Aurelio Ranzato +2
This paper introduces a structured memory which can be easily integrated into a neural network. The memory is very large by design and significantly increases the capacity of the a…
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning
Samuel Maddock, Alexandre Sablayrolles, Pierre Stock
Federated Learning (FL) is a setting for training machine learning models in distributed environments where the clients do not share their raw data but instead send model updates t…
Radioactive data: tracing through training
Alexandre Sablayrolles, Matthijs Douze, Cordelia Schmid +1
We want to detect whether a particular image dataset has been used to train a model. We propose a new technique, \emph{radioactive data}, that makes imperceptible changes to this d…
Optimal Membership Inference Bounds for Adaptive Composition of Sampled Gaussian Mechanisms
Saeed Mahloujifar, Alexandre Sablayrolles, Graham Cormode +1
Given a trained model and a data sample, membership-inference (MI) attacks predict whether the sample was in the model's training set. A common countermeasure against MI attacks is…