Suivre
Timothee Lesort
Timothee Lesort
Mila - Quebec AI Institute
Adresse e-mail validée de ensta-paris.fr - Page d'accueil
Titre
Citée par
Citée par
Année
Continual learning for robotics: Definition, framework, learning strategies, opportunities and challenges
T Lesort, V Lomonaco, A Stoian, D Maltoni, D Filliat, N Díaz-Rodríguez
Information Fusion 58, 52-68, 2020
5762020
State representation learning for control: An overview
T Lesort, N Díaz-Rodríguez, JF Goudou, D Filliat
Neural Networks 108, 379-392, 2018
4072018
Generative models from the perspective of continual learning
T Lesort, H Caselles-Dupré, M Garcia-Ortiz, A Stoian, D Filliat
2019 International Joint Conference on Neural Networks (IJCNN), 1-8, 2019
1952019
DisCoRL: Continual Reinforcement Learning via Policy Distillation
R Traoré, H Caselles-Dupré, T Lesort, T Sun, G Cai, N Díaz-Rodríguez, ...
International Conference on Neural Information Processing Systems (NeurIPS …, 2019
742019
Foundational Models for Continual Learning: An Empirical Study of Latent Replay
O Ostapenko, T Lesort, P Rodríguez, MR Arefin, A Douillard, I Rish, ...
CoLLas 2022, Oral, 2022
71*2022
Continual Pre-Training of Large Language Models: How to (re) warm your model?
K Gupta, B Thérien, A Ibrahim, ML Richter, Q Anthony, E Belilovsky, I Rish, ...
692023
Decoupling feature extraction from policy learning: assessing benefits of state representation learning in goal based robotics
A Raffin, A Hill, KR Traoré, T Lesort, N Díaz-Rodríguez, D Filliat
International Conference on Learning Representations (ICLR) 2019, Structure …, 2019
662019
Understanding Continual Learning Settings with Data Distribution Drift Analysis
T Lesort, M Caccia, I Rish
International Conference of Machine Learning 2021 (ICML) Workshop on Theory …, 2021
642021
Deep unsupervised state representation learning with robotic priors: a robustness analysis
T Lesort, M Seurin, X Li, N Díaz-Rodríguez, D Filliat
2019 International Joint Conference on Neural Networks (IJCNN), 1-8, 2019
60*2019
Simple and scalable strategies to continually pre-train large language models
A Ibrahim, B Thérien, K Gupta, ML Richter, Q Anthony, T Lesort, ...
arXiv preprint arXiv:2403.08763, 2024
572024
Regularization shortcomings for continual learning
T Lesort, A Stoian, D Filliat
arXiv preprint arXiv:1912.03049, 2019
502019
Continual reinforcement learning deployed in real-life using policy distillation and sim2real transfer
R Traoré, H Caselles-Dupré, T Lesort, T Sun, N Díaz-Rodríguez, D Filliat
arXiv preprint arXiv:1906.04452, 2019
442019
Continual learning for robotics
T Lesort, V Lomonaco, A Stoian, D Maltoni, D Filliat, N Dıaz-Rodrıguez
arXiv preprint arXiv:1907.00182, 1-34, 2019
422019
S-RL Toolbox: Environments, Datasets and Evaluation Metrics for State Representation Learning
DF Antonin Raffin, Ashley Hill, René Traoré, Timothée Lesort, Natalia Díaz ...
International Conference on Neural Information Processing Systems (NeurIPS …, 2018
40*2018
Marginal replay vs conditional replay for continual learning
T Lesort, A Gepperth, A Stoian, D Filliat
International Conference on Artificial Neural Networks, 466-480, 2019
392019
Continuum: Simple management of complex continual learning scenarios
A Douillard, T Lesort
arXiv preprint arXiv:2102.06253, 2021
36*2021
Continual learning: Tackling catastrophic forgetting in deep neural networks with replay processes
T Lesort
arXiv preprint arXiv:2007.00487, 2020
33*2020
Sequoia: A Software Framework to Unify Continual Learning Research
F Normandin, F Golemo, O Ostapenko, P Rodriguez, MD Riemer, ...
arXiv preprint arXiv:2108.01005, 2021
27*2021
Training Discriminative Models to Evaluate Generative Ones
T Lesort, JF Goudou, D Filliat
International Conference on Artificial Neural Networks, 604--619, 2018
222018
Continual feature selection: Spurious features in continual learning
T Lesort
arXiv preprint arXiv:2203.01012, 2022
21*2022
Le système ne peut pas réaliser cette opération maintenant. Veuillez réessayer plus tard.
Articles 1–20