Diane Bouchacourt
RESEARCH SCIENTIST | PARIS, FRANCE
Diane is a research scientist at Facebook AI Research (FAIR), focusing on representation learning and unsupervised/weakly supervised learning. She is interested in building robust models by using group theory and disentanglement methods. Diane earned her Ph.D. in machine learning at the University of Oxford.
Diane's Work
Diane's Publications
November 09, 2021
COMPUTER VISION
CORE MACHINE LEARNING
Grounding inductive biases in natural images: invariance stems from variations in data
Diane Bouchacourt, Mark Ibrahim, Ari Morcos
November 09, 2021
July 29, 2020
RESEARCH
Entropy Minimization In Emergent Languages
Evgeny Kharitonov, Diane Bouchacourt, Marco Baroni, Rahma Chaabouni
July 29, 2020
June 25, 2020
RESEARCH
NLP
Compositionality and Generalization in Emergent Languages
Rahma Chaabouni, Diane Bouchacourt, Emmanuel Dupoux, Evgeny Kharitonov, Marco Baroni
June 25, 2020
December 09, 2019
RESEARCH
NLP
EGG: a toolkit for research on Emergence of lanGuage in Games
Evgeny Kharitonov, Diane Bouchacourt, Marco Baroni, Rahma Chaabouni
December 09, 2019
July 28, 2019
RESEARCH
NLP
Miss Tools and Mr Fruit: Emergent communication in agents learning about object affordances
Diane Bouchacourt, Marco Baroni
July 28, 2019
November 01, 2018
RESEARCH
NLP
How agents see things: On visual representations in an emergent language game
Diane Bouchacourt, Marco Baroni
November 01, 2018
Product experiences
Foundational models
Product experiences
Latest news
Foundational models
Meta © 2024