Alexandre Ramé

39 papers A* 12Journal 22Unranked 4

Year	Rank	Type	Title / Venue / Authors
2025	A*	`conf`	BOND: Aligning LLMs with Best-of-N Distillation. ICLR Pier Giuseppe Sessa, Robert Dadashi-Tazehozi, Léonard Hussenot, Johan Ferret, Nino Vieillard, Alexandre Ramé, Bobak Shahriari, Sarah Perrin, Abram L. Friesen, Geoffrey Cideron, Sertan Girgin, Piotr Stanczyk, Andrea Michi, Danila Sinopalnikov, Sabela Ramos Garea, Amélie Héliou, Aliaksei Severyn, Matthew Hoffman, Nikola Momchev, Olivier Bachem
2025	A*	`conf`	Diversity-Rewarded CFG Distillation. ICLR Geoffrey Cideron, Andrea Agostinelli, Johan Ferret, Sertan Girgin, Romuald Elie, Olivier Bachem, Sarah Perrin, Alexandre Ramé
2025	A*	`conf`	On Teacher Hacking in Language Model Distillation. ICML Daniil Tiapkin, Daniele Calandriello, Johan Ferret, Sarah Perrin, Nino Vieillard, Alexandre Ramé, Mathieu Blondel
2025	J	`jnl`	On Teacher Hacking in Language Model Distillation. CoRR Daniil Tiapkin, Daniele Calandriello, Johan Ferret, Sarah Perrin, Nino Vieillard, Alexandre Ramé, Mathieu Blondel
2025	J	`jnl`	Streaming DiLoCo with overlapping communication: Towards a Distributed Free Lunch. CoRR Arthur Douillard, Yanislav Donchev, Keith Rush, Satyen Kale, Zachary Charles, Zachary Garrett, Gabriel Teston, Dave Lacey, Ross McIlroy, Jiajun Shen, Alexandre Ramé, Arthur Szlam, Marc'Aurelio Ranzato, Paul Barham
2024	J	`jnl`	BOND: Aligning LLMs with Best-of-N Distillation. CoRR Pier Giuseppe Sessa, Robert Dadashi, Léonard Hussenot, Johan Ferret, Nino Vieillard, Alexandre Ramé, Bobak Shahriari, Sarah Perrin, Abe Friesen, Geoffrey Cideron, Sertan Girgin, Piotr Stanczyk, Andrea Michi, Danila Sinopalnikov, Sabela Ramos, Amélie Héliou, Aliaksei Severyn, Matt Hoffman, Nikola Momchev, Olivier Bachem
2024	A*	`conf`	Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning. ICLR Mustafa Shukor, Alexandre Ramé, Corentin Dancette, Matthieu Cord
2024	—	`conf`	Conditional Language Policy: A General Framework For Steerable Multi-Objective Finetuning. EMNLP (Findings) Kaiwen Wang, Rahul Kidambi, Ryan Sullivan, Alekh Agarwal, Christoph Dann, Andrea Michi, Marco Gelmi, Yunxuan Li, Raghav Gupta, Avinava Dubey, Alexandre Ramé, Johan Ferret, Geoffrey Cideron, Le Hou, Hongkun Yu, Amr Ahmed, Aranyak Mehta, Léonard Hussenot, Olivier Bachem, Edouard Leurent
2024	J	`jnl`	Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning. CoRR Kaiwen Wang, Rahul Kidambi, Ryan Sullivan, Alekh Agarwal, Christoph Dann, Andrea Michi, Marco Gelmi, Yunxuan Li, Raghav Gupta, Avinava Dubey, Alexandre Ramé, Johan Ferret, Geoffrey Cideron, Le Hou, Hongkun Yu, Amr Ahmed, Aranyak Mehta, Léonard Hussenot, Olivier Bachem, Edouard Leurent
2024	J	`jnl`	Direct Language Model Alignment from Online AI Feedback. CoRR Shangmin Guo, Biao Zhang, Tianlin Liu, Tianqi Liu, Misha Khalman, Felipe Llinares, Alexandre Ramé, Thomas Mesnard, Yao Zhao, Bilal Piot, Johan Ferret, Mathieu Blondel
2024	J	`jnl`	Diversity-Rewarded CFG Distillation. CoRR Geoffrey Cideron, Andrea Agostinelli, Johan Ferret, Sertan Girgin, Romuald Elie, Olivier Bachem, Sarah Perrin, Alexandre Ramé
2024	A*	`conf`	WARM: On the Benefits of Weight Averaged Reward Models. ICML Alexandre Ramé, Nino Vieillard, Léonard Hussenot, Robert Dadashi, Geoffrey Cideron, Olivier Bachem, Johan Ferret
2024	J	`jnl`	WARM: On the Benefits of Weight Averaged Reward Models. CoRR Alexandre Ramé, Nino Vieillard, Léonard Hussenot, Robert Dadashi, Geoffrey Cideron, Olivier Bachem, Johan Ferret
2024	J	`jnl`	WARP: On the Benefits of Weight Averaged Rewarded Policies. CoRR Alexandre Ramé, Johan Ferret, Nino Vieillard, Robert Dadashi, Léonard Hussenot, Pierre-Louis Cedoz, Pier Giuseppe Sessa, Sertan Girgin, Arthur Douillard, Olivier Bachem
2023	J	`jnl`	Beyond Task Performance: Evaluating and Reducing the Flaws of Large Multimodal Models with In-Context Learning. CoRR Mustafa Shukor, Alexandre Ramé, Corentin Dancette, Matthieu Cord
2023	—	`—`	Diverse and efficient ensembling of deep networks. (De la diversification et combinaison efficace des réseaux profonds). Alexandre Ramé
2023	A*	`conf`	Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization. ICML Alexandre Ramé, Kartik Ahuja, Jianyu Zhang, Matthieu Cord, Léon Bottou, David Lopez-Paz
2023	A*	`conf`	Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards. NeurIPS Alexandre Ramé, Guillaume Couairon, Corentin Dancette, Jean-Baptiste Gaya, Mustafa Shukor, Laure Soulier, Matthieu Cord
2023	J	`jnl`	Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards. CoRR Alexandre Ramé, Guillaume Couairon, Mustafa Shukor, Corentin Dancette, Jean-Baptiste Gaya, Laure Soulier, Matthieu Cord
2023	J	`jnl`	UnIVAL: Unified Model for Image, Video, Audio and Language Tasks. Trans. Mach. Learn. Res. Mustafa Shukor, Corentin Dancette, Alexandre Ramé, Matthieu Cord
2023	J	`jnl`	Unified Model for Image, Video, Audio and Language Tasks. CoRR Mustafa Shukor, Corentin Dancette, Alexandre Ramé, Matthieu Cord
2022	—	`conf`	CoRe: Color Regression for Multicolor Fashion Garments. CVPR Workshops Alexandre Ramé, Arthur Douillard, Charles Ollion
2022	A*	`conf`	Diverse Weight Averaging for Out-of-Distribution Generalization. NeurIPS Alexandre Ramé, Matthieu Kirchmeyer, Thibaud Rahier, Alain Rakotomamonjy, Patrick Gallinari, Matthieu Cord
2022	J	`jnl`	Diverse Weight Averaging for Out-of-Distribution Generalization. CoRR Alexandre Ramé, Matthieu Kirchmeyer, Thibaud Rahier, Alain Rakotomamonjy, Patrick Gallinari, Matthieu Cord
2022	A*	`conf`	DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion. CVPR Arthur Douillard, Alexandre Ramé, Guillaume Couairon, Matthieu Cord
2022	A*	`conf`	Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization. ICML Alexandre Ramé, Corentin Dancette, Matthieu Cord
2022	J	`jnl`	Recycling diverse models for out-of-distribution generalization. CoRR Alexandre Ramé, Kartik Ahuja, Jianyu Zhang, Matthieu Cord, Léon Bottou, David Lopez-Paz
2022	—	`conf`	Towards efficient feature sharing in MIMO architectures. CVPR Workshops Rémy Sun, Alexandre Ramé, Clément Masson, Nicolas Thome, Matthieu Cord
2022	J	`jnl`	Towards efficient feature sharing in MIMO architectures. CoRR Rémy Sun, Alexandre Ramé, Clément Masson, Nicolas Thome, Matthieu Cord
2021	A*	`conf`	DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation. ICLR Alexandre Ramé, Matthieu Cord
2021	J	`jnl`	DICE: Diversity in Deep Ensembles via Conditional Redundancy Adversarial Estimation. CoRR Alexandre Ramé, Matthieu Cord
2021	J	`jnl`	DyTox: Transformers for Continual Learning with DYnamic TOken eXpansion. CoRR Arthur Douillard, Alexandre Ramé, Guillaume Couairon, Matthieu Cord
2021	J	`jnl`	Fishr: Invariant Gradient Variances for Out-of-distribution Generalization. CoRR Alexandre Ramé, Corentin Dancette, Matthieu Cord
2021	A*	`conf`	MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks. ICCV Alexandre Ramé, Rémy Sun, Matthieu Cord
2021	J	`jnl`	MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks. CoRR Alexandre Ramé, Rémy Sun, Matthieu Cord
2020	J	`jnl`	CORE: Color Regression for Multiple Colors Fashion Garments. CoRR Alexandre Ramé, Arthur Douillard, Charles Ollion
2018	J	`jnl`	OMNIA Faster R-CNN: Detection in the wild through dataset merging and soft distillation. CoRR Alexandre Ramé, Emilien Garreau, Hedi Ben-Younes, Charles Ollion
2017	—	`conf`	Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction. ICCV Workshops Charles Corbière, Hédi Ben-Younes, Alexandre Ramé, Charles Ollion
2017	J	`jnl`	Leveraging Weakly Annotated Data for Fashion Image Retrieval and Label Prediction. CoRR Charles Corbière, Hédi Ben-Younes, Alexandre Ramé, Charles Ollion