Следене
Jovana Mitrovic
Jovana Mitrovic
Research Scientist at DeepMind
Потвърден имейл адрес: google.com
Заглавие
Позовавания
Позовавания
Година
Representation learning via invariant causal mechanisms
J Mitrovic, B McWilliams, J Walker, L Buesing, C Blundell
arXiv preprint arXiv:2010.07922, 2020
2122020
Causal reasoning from meta-reinforcement learning
I Dasgupta, J Wang, S Chiappa, J Mitrovic, P Ortega, D Raposo, ...
arXiv preprint arXiv:1901.08162, 2019
1212019
Pushing the limits of self-supervised resnets: Can we outperform supervised learning without labels on imagenet?
N Tomasev, I Bica, B McWilliams, L Buesing, R Pascanu, C Blundell, ...
arXiv preprint arXiv:2201.05119, 2022
692022
Causal inference via kernel deviance measures
J Mitrovic, D Sejdinovic, YW Teh
Advances in neural information processing systems 31, 2018
622018
Robust and data-efficient generalization of self-supervised machine learning for diagnostic imaging
S Azizi, L Culp, J Freyberg, B Mustafa, S Baur, S Kornblith, T Chen, ...
Nature Biomedical Engineering 7 (6), 756-779, 2023
502023
DR-ABC: Approximate Bayesian computation with kernel-based distribution regression
J Mitrovic, D Sejdinovic, YW Teh
International Conference on Machine Learning, 1482-1491, 2016
342016
Coberl: Contrastive bert for reinforcement learning
A Banino, AP Badia, J Walker, T Scholtes, J Mitrovic, C Blundell
arXiv preprint arXiv:2107.05431, 2021
322021
Causally correct partial models for reinforcement learning
DJ Rezende, I Danihelka, G Papamakarios, NR Ke, R Jiang, T Weber, ...
arXiv preprint arXiv:2002.02836, 2020
272020
Hierarchical adversarially learned inference
MI Belghazi, S Rajeswar, O Mastropietro, N Rostamzadeh, J Mitrovic, ...
arXiv preprint arXiv:1802.01071, 2018
232018
Less can be more in contrastive learning
J Mitrovic, B McWilliams, M Rey
PMLR, 2020
192020
Neural algorithmic reasoning with causal regularisation
B Bevilacqua, K Nikiforou, B Ibarz, I Bica, M Paganini, C Blundell, ...
International Conference on Machine Learning, 2272-2288, 2023
172023
Amortized learning of neural causal representations
NR Ke, J Wang, J Mitrovic, M Szummer, DJ Rezende
arXiv preprint arXiv:2008.09301, 2020
172020
Encoders and ensembles for task-free continual learning
M Shanahan, C Kaplanis, J Mitrović
arXiv preprint arXiv:2105.13327, 2021
162021
Semppl: Predicting pseudo-labels for better contrastive representations
M Bošnjak, PH Richemond, N Tomasev, F Strub, JC Walker, F Hill, ...
arXiv preprint arXiv:2301.05158, 2023
92023
Deep Kernel Machines via the Kernel Reparametrization Trick
J Mitrovic, D Sejdinovic, YW Teh
22017
Meta-reinforcement learning of causal strategies
I Dasgupta, Z Kurth-Nelson, S Chiappa, J Mitrovic, P Ortega, E Hughes, ...
The Meta-Learning Workshop at the Neural Information Processing Systems …, 2019
12019
Attention neural networks with short-term memory units
A Banino, AP Badia, JC Walker, TAJ Scholtes, J Mitrovic, C Blundell
US Patent App. 18/275,052, 2024
2024
Synth: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings
S Sharifzadeh, C Kaplanis, S Pathak, D Kumaran, A Ilic, J Mitrovic, ...
arXiv preprint arXiv:2403.07750, 2024
2024
Improving fine-grained understanding in image-text pre-training
I Bica, A Ilić, M Bauer, G Erdogan, M Bošnjak, C Kaplanis, AA Gritsenko, ...
arXiv preprint arXiv:2401.09865, 2024
2024
Continually learning representations at scale
A Galashov, J Mitrovic, D Tirumala, YW Teh, T Nguyen, A Chaudhry, ...
Conference on Lifelong Learning Agents, 534-547, 2023
2023
Системата не може да изпълни операцията сега. Опитайте отново по-късно.
Статии 1–20