Følg
Michal Valko
Michal Valko
Chief Models Officer @ Stealth Startup, Inria & MVA - Ex: Llama at Meta; Gemini and BYOL @ Deepmind
Verifisert e-postadresse på meta.com - Startside
Tittel
Sitert av
Sitert av
År
Bootstrap your own latent: A new approach to self-supervised learning
JB Grill, F Strub, F Altché, C Tallec, PH Richemond, E Buchatskaya, ...
Neural Information Processing Systems, 2020
76432020
The Llama 3 herd of models
A Dubey, A Jauhri, A Pandey, A Kadian, A Al-Dahle, A Letman, A Mathur, ...
arXiv preprint arXiv:2407.21783, 2025
3791*2025
Large-scale representation learning on graphs via bootstrapping
S Thakoor, C Tallec, MG Azar, R Munos, P Veličković, M Valko
International Conference on Learning Representations, 2022
557*2022
A general theoretical paradigm to understand learning from human preferences
MG Azar, M Rowland, B Piot, D Guo, D Calandriello, M Valko, R Munos
International Conference on Artificial Intelligence and Statistics, 2024
4522024
Finite-time analysis of kernelised contextual bandits
M Valko, N Korda, R Munos, I Flaounas, N Cristianini
Uncertainty in Artificial Intelligence, 2013
3082013
Outlier detection for patient monitoring and alerting
M Hauskrecht, I Batal, M Valko, S Visweswaran, GF Cooper, G Clermont
Journal of Biomedical Informatics, 2013
1842013
Online influence maximization under independent cascade model with semi-bandit feedback
Z Wen, B Kveton, M Valko, S Vaswani
Neural Information Processing Systems, 2017
168*2017
Broaden your views for self-supervised video learning
A Recasens, P Luc, JB Alayrac, L Wang, F Strub, C Tallec, M Malinowski, ...
International Conference on Computer Vision, 2021
1482021
Efficient learning by implicit exploration in bandit problems with side observations
T Kocák, G Neu, M Valko, R Munos
Neural Information Processing Systems, 2014
1412014
Stochastic simultaneous optimistic optimization
M Valko, A Carpentier, R Munos
International Conference on Machine Learning, 2013
1402013
Spectral bandits for smooth graph functions
M Valko, R Munos, B Kveton, T Kocák
International Conference on Machine Learning, 2014
1392014
Episodic reinforcement learning in finite MDPs: Minimax lower bounds revisited
O Darwiche Domingues, P Ménard, E Kaufmann, M Valko
Algorithmic Learning Theory, 2021
1312021
Nash learning from human feedback
R Munos, M Valko, D Calandriello, MG Azar, M Rowland, D Guo, Y Tang, ...
International Conference on Machine Learning, 2024
1212024
Black-box optimization of noisy functions with unknown smoothness
JB Grill, M Valko, R Munos
Neural Information Processing Systems, 2015
1162015
Game Plan: What AI can do for Football, and What Football can do for AI
K Tuyls, S Omidshafiei, P Muller, Z Wang, J Connor, D Hennes, I Graham, ...
Journal of Artificial Intelligence Research 71, 41-88, 2021
1152021
BYOL works even without batch statistics
PH Richemond, JB Grill, F Altché, C Tallec, F Strub, A Brock, S Smith, ...
NeurIPS 2020 Workshop: Self-Supervised Learning - Theory and Practice, 2020
1142020
Simple regret for infinitely many armed bandits
A Carpentier, M Valko
International Conference on Machine Learning, 2015
1132015
Gamification of pure exploration for linear bandits
R Degenne, P Ménard, X Shang, M Valko
International Conference on Machine Learning, 2020
1052020
Adaptive reward-free exploration
E Kaufmann, P Ménard, OD Domingues, A Jonsson, E Leurent, M Valko
Algorithmic Learning Theory, 2021
1012021
Fast active learning for pure exploration in reinforcement learning
P Ménard, OD Domingues, A Jonsson, E Kaufmann, E Leurent, M Valko
International Conference on Machine Learning, 2021
952021
Systemet kan ikke utføre handlingen. Prøv på nytt senere.
Artikler 1–20