Folgen
Eugene Belilovsky
Eugene Belilovsky
Assistant Professor, Concordia University and Mila Quebec AI Institute
Bestätigte E-Mail-Adresse bei concordia.ca - Startseite
Titel
Zitiert von
Zitiert von
Jahr
Online Continual Learning with Maximally Interfered Retrieval
R Aljundi, L Caccia, E Belilovsky, M Caccia, M Lin, L Charlin, T Tuytelaars
Advances In neural Information Processing Systems (NeurIPS), 2019
6152019
CLIP-Mesh: Generating textured meshes from text using pretrained image-text models
N Mohammad Khalid, T Xie, E Belilovsky, T Popa
SIGGRAPH Asia 2022 Conference Papers, 1-8, 2022
2622022
Greedy Layerwise Learning Can Scale to ImageNet
E Belilovsky, M Eickenberg, E Oyallon
Proceedings of the 36th International Conference on Machine Learning (ICML …, 2019
2142019
Scaling the Scattering Transform: Deep Hybrid Networks
E Oyallon, E Belilovsky, S Zagoruyko
International Conference on Computer Vision (ICCV), 5618-5627, 2017
2062017
New Insights on Reducing Abrupt Representation Change in Online Continual Learning
L Caccia, R Aljundi, N Asadi, T Tuytelaars, J Pineau, E Belilovsky
International Conference on Learning Representations (ICLR), 2022
1962022
Kymatio: Scattering transforms in python
M Andreux, T Angles, G Exarchakis, R Leonarduzzi, G Rochette, L Thiry, ...
Journal of Machine Learning Research 21 (60), 1-6, 2020
1962020
Decoupled greedy learning of cnns
E Belilovsky, M Eickenberg, E Oyallon
Proceedings of the 37th International Conference on Machine Learning (ICML …, 2019
1252019
Scattering networks for hybrid representation learning
E Oyallon, S Zagoruyko, G Huang, N Komodakis, S Lacoste-Julien, ...
IEEE transactions on pattern analysis and machine intelligence 41 (9), 2208-2221, 2018
1032018
Probing Representation Forgetting in Supervised and Unsupervised Continual Learning
MR Davari, N Asadi, S Mudur, R Aljundi, E Belilovsky
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022
962022
Online Learned Continual Compression with Adaptive Quantization Modules
L Caccia, E Belilovsky, M Caccia, J Pineau
International Conference on Machine Learning (ICML), 2020
942020
A Test of Relative Similarity for Model Selection in Generative Models
E Belilovsky, W Bounliphone, MB Blaschko, I Antonoglou, A Gretton
International Conference on Learning Representations (ICLR), 2016
88*2016
Testing for Differences in Gaussian Graphical Models: Applications to Brain Connectivity
E Belilovsky, G Varoquaux, MB Blaschko
Advances In neural Information Processing Systems (NIPS), 2016
732016
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, ...
ICML Workshop on Efficient Foundational Models 2023, 2023
622023
Blindfold Baselines for Embodied QA
A Anand, E Belilovsky, K Kastner, H Larochelle, A Courville
NIPS VIGIL Workshop arXiv preprint arXiv:1811.05013, 2018
522018
Graph Density-Aware Losses for Novel Compositions in Scene Graph Generation
B Knyazev, H de Vries, C Cangea, GW Taylor, A Courville, E Belilovsky
British Machine Vision Conference (BMVC), 2020
432020
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
412024
Compressing the Input for CNNs with the First-Order Scattering Transform
E Oyallon, E Belilovsky, S Zagoruyko, M Valko
European Conference on Computer Vision (ECCV), 2018
412018
Reliability of CKA as a Similarity Measure in Deep Learning
MR Davari, S Horoi, A Natik, G Lajoie, G Wolf, E Belilovsky
International Conference on Learning Representations (ICLR) 2023, 2022
382022
Learning to Discover Sparse Graphical Models
E Belilovsky, K Kastner, G Varoquaux, MB Blaschko
International Conference on Machine Learning (ICML), 2017
372017
Graph density-aware losses for novel compositions in scene graph generation
EB Knyazev, Boris, Harm de Vries, Catalina Cangea, Graham W Taylor, Aaron ...
arXiv preprint arXiv:2005.08230 2 (3), 2020
32*2020
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–20