papers

Publications (31)

cs.CV2018

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…

cs.SE2025

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…

cs.CL2019

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…

cs.LG2023

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…

stat.ML2020

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…

cs.CR2022

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…