no code implementations • 22 Jan 2024 • Alexandre Ramé, Nino Vieillard, Léonard Hussenot, Robert Dadashi, Geoffrey Cideron, Olivier Bachem, Johan Ferret
We identify two primary challenges when designing RMs to mitigate reward hacking: distribution shifts during the RL process and inconsistencies in human preferences.
1 code implementation • 20 Dec 2022 • Alexandre Ramé, Kartik Ahuja, Jianyu Zhang, Matthieu Cord, Léon Bottou, David Lopez-Paz
In this paper, we thus propose model ratatouille, a new strategy to recycle the multiple fine-tunings of the same foundation model on diverse auxiliary tasks.
Ranked #14 on Domain Generalization on PACS
no code implementations • 20 May 2022 • Rémy Sun, Alexandre Ramé, Clément Masson, Nicolas Thome, Matthieu Cord
To solve this issue, we propose a novel unmixing step in MIMO architectures that allows subnetworks to properly share features.
2 code implementations • 19 May 2022 • Alexandre Ramé, Matthieu Kirchmeyer, Thibaud Rahier, Alain Rakotomamonjy, Patrick Gallinari, Matthieu Cord
Standard neural networks struggle to generalize under distribution shifts in computer vision.
1 code implementation • CVPR 2022 • Arthur Douillard, Alexandre Ramé, Guillaume Couairon, Matthieu Cord
Our strategy scales to a large number of tasks while having negligible memory and time overheads due to strict control of the parameters expansion.
Ranked #2 on Incremental Learning on ImageNet - 10 steps
no code implementations • 27 Sep 2017 • Charles Corbière, Hedi Ben-Younes, Alexandre Ramé, Charles Ollion
In this paper, we present a method to learn a visual representation adapted for e-commerce products.