| Online Continual Learning with Maximally Interfered Retrieval R Aljundi*, L Caccia*, E Belilovsky*, M Caccia*, L Charlin, T Tuytelaars NeurIPS 2019, 2019 | 799 | 2019 |
| New Insights on Reducing Abrupt Representation Change in Online Continual Learning L Caccia, R Aljundi, N Asadi, T Tuytelaars, J Pineau, E Belilovsky ICLR 2022, 2021 | 346 | 2021 |
| Language GANs Falling Short M Caccia*, L Caccia*, W Fedus, H Larochelle, J Pineau, L Charlin ICLR 2020, 2018 | 291 | 2018 |
| Online Fast Adaptation and Knowledge Accumulation: a New Approach to Continual Learning M Caccia, P Rodriguez, O Ostapenko, F Normandin, M Lin, L Caccia, ... NeurIPS 2020, 2020 | 192* | 2020 |
| Online Learned Continual Compression with Adaptive Quantization Modules L Caccia, E Belilovsky, M Caccia, J Pineau ICML 2020, 2019 | 130 | 2019 |
| Deep Generative Modeling of LiDAR Data L Caccia, H van Hoof, A Courville, J Pineau IROS 2019, 2018 | 107* | 2018 |
| Towards Modular LLMs by Building and Reusing a Library of LoRAs O Ostapenko*, Z Su*, EM Ponti, L Charlin, NL Roux, M Pereira, L Caccia*, ... ICML 2024, 2024 | 58 | 2024 |
| Building a subspace of policies for scalable continual learning JB Gaya, T Doan, L Caccia, L Soulier, L Denoyer, R Raileanu ICLR 2023, 2022 | 53 | 2022 |
| Guiding language model reasoning with planning tokens X Wang, L Caccia, O Ostapenko, X Yuan, A Sordoni COLM 2024, 2023 | 51 | 2023 |
| A survey on model MoErging: Recycling and routing among specialized experts for collaborative learning P Yadav, C Raffel, M Muqeeth, L Caccia, H Liu, T Chen, M Bansal, ... TMLR, 2024 | 47 | 2024 |
| Multi-Head Adapter Routing for Cross-Task Generalization L Caccia, EM Ponti, Z Su, M Pereira, N Le Roux, A Sordoni NeurIPS 2023, 2023 | 42* | 2023 |
| Guiding The Last Layer in Federated Learning with Pre-Trained Models G Legate, N Bernier, L Caccia, E Oyallon, E Belilovsky NeurIPS 2023, 2023 | 35 | 2023 |
| On Anytime Learning at Macroscale L Caccia, J Xu, M Ott, MA Ranzato, L Denoyer CoLLAs 2022, 2021 | 31 | 2021 |
| Re-Weighted Softmax Cross-Entropy to Control Forgetting in Federated Learning G Legate, L Caccia, E Belilovsky CoLLAs 2023, 2022 | 22 | 2022 |
| SPeCiaL: Self-Supervised Pretraining for Continual Learning L Caccia, J Pineau IJCAI 2021, Workshop on Continual Semi-Supervised Learning, Best Paper Award, 2021 | 21 | 2021 |
| Clustering-Oriented Representation Learning with Attractive-Repulsive Loss K Kenyon-Dean, A Cianflone, L Caccia, G Rabusseau, JCK Cheung, ... AAAI 2019 Workshop on Network Interpretability for Deep Learning, 2018 | 19 | 2018 |
| A case study of instruction tuning with mixture of parameter-efficient experts O Ostapenko, L Caccia, Z Su, N Le Roux, L Charlin, A Sordoni NeurIPS 2023 Workshop on Instruction Tuning and Instruction Following, 2023 | 16 | 2023 |
| Decoupled greedy learning of cnns for synchronous and asynchronous distributed learning E Belilovsky, L Leconte, L Caccia, M Eickenberg, E Oyallon arXiv preprint arXiv:2106.06401, 2021 | 12 | 2021 |
| A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment JP Corbeil, A Dada, JM Attendu, AB Abacha, A Sordoni, L Caccia, ... ACL 2025, 2025 | 11 | 2025 |
| debug-gym: A Text-Based Environment for Interactive Debugging X Yuan, MM Moss, CE Feghali, C Singh, D Moldavskaya, D MacPhee, ... arXiv preprint arXiv:2503.21557, 2025 | 7 | 2025 |
Eugene BelilovskyAssociate Professor, Concordia University and Mila Quebec AI InstituteVerified email at concordia.ca
