Francisco Massa — accepted AI-conference papers

2025

Mixture of Languages: Improved Multilingual Encoders Through Language Grouping

Jo{\~a}o Maria Janeiro, Belen Alastruey, Francisco Massa, Maha Elbayad, Benjamin Piwowarski, Patrick Gallinari +1

EMNLP 2025

We propose Mixture of Languages (MoL), a new strategy to pretrain largely multilingual encoders. Recent work in this field has relied on training transformer encoders on a large amount of multilingual data, with all parameters shared across all languages, without studying how to optimally balance la

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2023

Hybrid Transformers for Music Source Separation

Simon Rouard, Francisco Massa, Alexandre Défossez

ICASSP 2023accepted

A natural question arising in Music Source Separation (MSS) is whether long range contextual information is useful, or whether local acoustic features are sufficient. In other fields, attention based Transformers [1] have shown their ability to integrate information over long sequences. In this work…

Cited by 0 Source ↗Scholar ↗

2021

Training data-efficient image transformers & distillation through attention

Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, Herve Jegou

ICML 2021spotlight

Recently, neural networks purely based on attention were shown to address image understanding tasks such as image classification. These high-performing vision transformers are pre-trained with hundreds of millions of images using a large infrastructure, thereby limiting their adoption. In this work,…

Cited by 8716 Source ↗PDF ↗code ↗Scholar ↗

2020

End-to-End Object Detection with Transformers

Nicolas Carion, Francisco Massa, Gabriel Synnaeve, Nicolas Usunier, Alexander Kirillov, Sergey Zagoruyko

ECCV 2020poster

We present a new method that views object detection as a direct set prediction. Our approach streamlines the detection pipeline, effectively removing the need for many hand-designed components like a non-maximum suppression procedure or anchor generation that explicitly encode our prior knowledge ab…

Cited by 17886 Source ↗PDF ↗code ↗Scholar ↗

2019

PyTorch: An Imperative Style, High-Performance Deep Learning Library

Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan +15

NeurIPS 2019poster

Deep learning frameworks have often focused on either usability or speed, but not both. PyTorch is a machine learning library that shows that these two goals are in fact compatible: it was designed from first principles to support an imperative and Pythonic programming style that supports code as a…

Cited by 58109 Source ↗PDF ↗code ↗Scholar ↗

2016

Deep Exemplar 2D-3D Detection by Adapting From Real to Rendered Views

Francisco Massa, Bryan C. Russell, Mathieu Aubry

CVPR 2016accepted

This paper presents an end-to-end convolutional neural network (CNN) for 2D-3D exemplar detection. We demonstrate that the ability to adapt the features of natural images to better align with those of CAD rendered views is critical to the success of our technique. We show that the adaptation can be…

Cited by 121 Source ↗PDF ↗Scholar ↗