DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion A Douillard, A Ramé, G Couairon, M Cord CVPR 2022, 2021 | 331 | 2021 |
Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization A Ramé, C Dancette, M Cord ICML 2022, 2021 | 221 | 2021 |
Gemma 2: Improving open language models at a practical size G Team, M Riviere, S Pathak, PG Sessa, C Hardin, S Bhupatiraju, ... arXiv preprint arXiv:2408.00118, 2024 | 203 | 2024 |
Diverse Weight Averaging for Out-of-Distribution Generalization A Ramé, M Kirchmeyer, T Rahier, A Rakotomamonjy, P Gallinari, M Cord NeurIPS 2022, 2022 | 118 | 2022 |
Leveraging weakly annotated data for fashion image retrieval and label prediction C Corbiere, H Ben-Younes, A Ramé, C Ollion ICCV 2017 Workshop, 2017 | 118 | 2017 |
Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards A Ramé, G Couairon, M Shukor, C Dancette, JB Gaya, L Soulier, M Cord NeurIPS 2023, 2023 | 92 | 2023 |
Direct Language Model Alignment from Online AI Feedback S Guo, B Zhang, T Liu, T Liu, M Khalman, F Llinares, A Ramé, T Mesnard, ... arXiv preprint arXiv:2402.04792, 2024 | 80 | 2024 |
Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization A Ramé, K Ahuja, J Zhang, M Cord, L Bottou, D Lopez-Paz ICML 2023, 2023 | 79* | 2023 |
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks A Ramé, R Sun, M Cord ICCV 2021, 2021 | 76 | 2021 |
DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation A Ramé, M Cord ICLR 2021, 2021 | 69 | 2021 |
WARM: On the Benefits of Weight Averaged Reward Models A Ramé, N Vieillard, L Hussenot, R Dadashi, G Cideron, O Bachem, ... ICML 2024, 2024 | 47 | 2024 |
Unified Model for Image, Video, Audio and Language Tasks M Shukor, C Dancette, A Ramé, M Cord TMLR 2023, 2023 | 28* | 2023 |
OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation A Ramé, E Garreau, H Ben-Younes, C Ollion arXiv preprint arXiv:1812.02611, 2018 | 16 | 2018 |
BOND: Aligning LLMs with Best-of-N Distillation PG Sessa, R Dadashi, L Hussenot, J Ferret, N Vieillard, A Ramé, ... arXiv preprint arXiv:2407.14622, 2024 | 15 | 2024 |
Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning M Shukor, A Ramé, C Dancette, M Cord ICLR 2024, 2023 | 12 | 2023 |
Towards efficient feature sharing in MIMO architectures R Sun, A Ramé, C Masson, N Thome, M Cord CVPR 2022 ECV Workshop, 2022 | 9 | 2022 |
Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning K Wang, R Kidambi, R Sullivan, A Agarwal, C Dann, A Michi, M Gelmi, ... arXiv preprint arXiv:2407.15762, 2024 | 7 | 2024 |
WARP: On the Benefits of Weight Averaged Rewarded Policies A Ramé, J Ferret, N Vieillard, R Dadashi, L Hussenot, PL Cedoz, ... arXiv preprint arXiv:2406.16768, 2024 | 6 | 2024 |
CORE: Color Regression for Multiple Colors Fashion Garments A Ramé, A Douillard, C Ollion CVPR 2022 Workshop on Computer Vision for Fashion, Art, and Design, 2020 | 5* | 2020 |
Pre-train, fine-tune, interpolate: a three-stage strategy for domain generalization A Ramé, J Zhang, L Bottou, D Lopez-Paz NeurIPS 2022 Interpolation Workshop, 0 | 4* | |