Jean-Baptiste Gaya
Jean-Baptiste Gaya
Sorbonne Université
Verified email at
Cited by
Cited by
Rewarded soups: towards pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards
A Rame, G Couairon, C Dancette, JB Gaya, M Shukor, L Soulier, M Cord
Advances in Neural Information Processing Systems 36, 2024
Building a subspace of policies for scalable continual learning
JB Gaya, T Doan, L Caccia, L Soulier, L Denoyer, R Raileanu
11th International Conference on Learning Representations (Spotlight), 2022
Learning a subspace of policies for online adaptation in reinforcement learning
JB Gaya, L Soulier, L Denoyer
10th International Conference on Learning Representations, 2021
Salina: Sequential learning of agents
L Denoyer, A De la Fuente, S Duong, JB Gaya, PA Kamienny, ...
arXiv preprint arXiv:2110.07910, 2021
Worldsense: A synthetic benchmark for grounded reasoning in large language models
Y Benchekroun, M Dervishi, M Ibrahim, JB Gaya, X Martinet, G Mialon, ...
arXiv preprint arXiv:2311.15930, 2023
The system can't perform the operation now. Try again later.
Articles 1–5