David Grangier

125 papers A* 18A 8C 1Misc 2Journal 72Unranked 24

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Optimal Splitting of Language Models from Mixtures to Specialized Domains. CoRR Skyler Seto, Pierre Ablin, Anastasiia Filippova, Jiayuan Ye, Louis Béthune, Angelos Katharopoulos, David Grangier
2026	J	`jnl`	Which Data Matter? Embedding-Based Data Selection for Speech Recognition. CoRR Zakaria Aldeneh, Skyler Seto, Maureen de Seyssel, Jie Chi, Zijin Gu, Takuya Higuchi, Jee-weon Jung, Shinji Watanabe, David Grangier, Barry-John Theobald, Tatiana Likhomanenko
2025	—	`conf`	Assessing the Role of Data Quality in Training Bilingual Language Models. EMNLP (Findings) Skyler Seto, Maartje ter Hoeve, Maureen de Seyssel, David Grangier
2025	J	`jnl`	Assessing the Role of Data Quality in Training Bilingual Language Models. CoRR Skyler Seto, Maartje ter Hoeve, Maureen de Seyssel, David Grangier
2025	J	`jnl`	Compute-Optimal Quantization-Aware Training. CoRR Aleksandr Dremov, David Grangier, Angelos Katharopoulos, Awni Hannun
2025	A*	`conf`	No Need to Talk: Asynchronous Mixture of Language Models. ICLR Anastasiia Filippova, Angelos Katharopoulos, David Grangier, Ronan Collobert
2025	J	`jnl`	Partial Parameter Updates for Efficient Distributed Training. CoRR Anastasiia Filippova, Angelos Katharopoulos, David Grangier, Ronan Collobert
2025	J	`jnl`	Pretraining with hierarchical memories: separating long-tail and common knowledge. CoRR Hadi Pouransari, David Grangier, C. Thomas, Michael Kirchhof, Oncel Tuzel
2025	A*	`conf`	Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection. ICML Louis Béthune, David Grangier, Dan Busbridge, Eleonora Gualdoni, Marco Cuturi, Pierre Ablin
2025	J	`jnl`	Scaling Laws for Forgetting during Finetuning with Pretraining Data Injection. CoRR Louis Béthune, David Grangier, Dan Busbridge, Eleonora Gualdoni, Marco Cuturi, Pierre Ablin
2025	J	`jnl`	Scaling Laws for Optimal Data Mixtures. CoRR Mustafa Shukor, Louis Béthune, Dan Busbridge, David Grangier, Enrico Fini, Alaaeldin El-Nouby, Pierre Ablin
2025	A*	`conf`	Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging. ICML Pierre Ablin, Angelos Katharopoulos, Skyler Seto, David Grangier
2025	J	`jnl`	Soup-of-Experts: Pretraining Specialist Models via Parameters Averaging. CoRR Pierre Ablin, Angelos Katharopoulos, Skyler Seto, David Grangier
2025	A*	`conf`	Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling. ICLR David Grangier, Simin Fan, Skyler Seto, Pierre Ablin
2025	A*	`conf`	The AdEMAMix Optimizer: Better, Faster, Older. ICLR Matteo Pagliardini, Pierre Ablin, David Grangier
2025	J	`jnl`	The Data-Quality Illusion: Rethinking Classifier-Based Quality Filtering for LLM Pretraining. CoRR Thiziri Nait Saada, Louis Béthune, Michal Klein, David Grangier, Marco Cuturi, Pierre Ablin
2025	—	`conf`	Training Bilingual LMs with Data Constraints in the Targeted Language. ACL (Findings) Skyler Seto, Maartje ter Hoeve, Richard He Bai, Natalie Schluter, David Grangier
2024	J	`jnl`	Adaptive Training Distributions with Scalable Online Bilevel Optimization. Trans. Mach. Learn. Res. David Grangier, Pierre Ablin, Awni Hannun
2024	A*	`conf`	Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP. NeurIPS Chen Huang, Skyler Seto, Samira Abnar, David Grangier, Navdeep Jaitly, Joshua M. Susskind
2024	J	`jnl`	Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP. CoRR Chen Huang, Skyler Seto, Samira Abnar, David Grangier, Navdeep Jaitly, Josh M. Susskind
2024	J	`jnl`	Dynamic Gradient Alignment for Online Data Mixing. CoRR Simin Fan, David Grangier, Pierre Ablin
2024	J	`jnl`	No Need to Talk: Asynchronous Mixture of Language Models. CoRR Anastasiia Filippova, Angelos Katharopoulos, David Grangier, Ronan Collobert
2024	—	`conf`	Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling. ACL (1) Pratyush Maini, Skyler Seto, Richard He Bai, David Grangier, Yizhe Zhang, Navdeep Jaitly
2024	J	`jnl`	Rephrasing the Web: A Recipe for Compute and Data-Efficient Language Modeling. CoRR Pratyush Maini, Skyler Seto, He Bai, David Grangier, Yizhe Zhang, Navdeep Jaitly
2024	J	`jnl`	Specialized Language Models with Cheap Inference from Limited Domain Data. CoRR David Grangier, Angelos Katharopoulos, Pierre Ablin, Awni Hannun
2024	J	`jnl`	Task-Adaptive Pretrained Language Models via Clustered-Importance Sampling. CoRR David Grangier, Simin Fan, Skyler Seto, Pierre Ablin
2024	J	`jnl`	The AdEMAMix Optimizer: Better, Faster, Older. CoRR Matteo Pagliardini, Pierre Ablin, David Grangier
2024	J	`jnl`	Training Bilingual LMs with Data Constraints in the Targeted Language. CoRR Skyler Seto, Maartje ter Hoeve, He Bai, Natalie Schluter, David Grangier
2023	J	`jnl`	Adaptive Training Distributions with Scalable Online Bilevel Optimization. CoRR David Grangier, Pierre Ablin, Awni Hannun
2023	J	`jnl`	AudioLM: A Language Modeling Approach to Audio Generation. IEEE ACM Trans. Audio Speech Lang. Process. Zalán Borsos, Raphaël Marinier, Damien Vincent, Eugene Kharitonov, Olivier Pietquin, Matthew Sharifi, Dominik Roblek, Olivier Teboul, David Grangier, Marco Tagliasacchi, Neil Zeghidour
2023	J	`jnl`	Transfer Learning for Structured Pruning under Limited Task Data. CoRR Lucio M. Dery, David Grangier, Awni Hannun
2022	—	`conf`	A Natural Diet: Towards Improving Naturalness of Machine Translation Output. ACL (Findings) Markus Freitag, David Vilar, David Grangier, Colin Cherry, George F. Foster
2022	J	`jnl`	AudioLM: a Language Modeling Approach to Audio Generation. CoRR Zalán Borsos, Raphaël Marinier, Damien Vincent, Eugene Kharitonov, Olivier Pietquin, Matthew Sharifi, Olivier Teboul, David Grangier, Marco Tagliasacchi, Neil Zeghidour
2022	J	`jnl`	High Quality Rather than High Model Probability: Minimum Bayes Risk Decoding with Neural Metrics. Trans. Assoc. Comput. Linguistics Markus Freitag, David Grangier, Qijun Tan, Bowen Liang
2022	J	`jnl`	High-Resource Methodological Bias in Low-Resource Investigations. CoRR Maartje ter Hoeve, David Grangier, Natalie Schluter
2022	A*	`conf`	Learning Strides in Convolutional Neural Networks. ICLR Rachid Riad, Olivier Teboul, David Grangier, Neil Zeghidour
2022	J	`jnl`	Learning strides in convolutional neural networks. CoRR Rachid Riad, Olivier Teboul, David Grangier, Neil Zeghidour
2022	—	`conf`	On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translation. NAACL-HLT Kelly Marchisio, Markus Freitag, David Grangier
2022	—	`conf`	The Trade-offs of Domain Adaptation for Neural Language Models. ACL (1) David Grangier, Dan Iter
2021	J	`jnl`	Auxiliary Task Update Decomposition: The Good, The Bad and The Neutral. CoRR Lucio M. Dery, Yann N. Dauphin, David Grangier
2021	A*	`conf`	Auxiliary Task Update Decomposition: the Good, the Bad and the neutral. ICLR Lucio M. Dery, Yann N. Dauphin, David Grangier
2021	Misc	`conf`	Contrastive Learning of General-Purpose Audio Representations. ICASSP Aaqib Saeed, David Grangier, Neil Zeghidour
2021	J	`jnl`	DIVE: End-to-end Speech Diarization via Iterative Speaker Embedding. CoRR Neil Zeghidour, Olivier Teboul, David Grangier
2021	C	`conf`	Dive: End-to-End Speech Diarization Via Iterative Speaker Embedding. ASRU Neil Zeghidour, Olivier Teboul, David Grangier
2021	J	`jnl`	Efficient Content-Based Sparse Attention with Routing Transformers. Trans. Assoc. Comput. Linguistics Aurko Roy, Mohammad Saffar, Ashish Vaswani, David Grangier
2021	J	`jnl`	Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation. CoRR Markus Freitag, George F. Foster, David Grangier, Viresh Ratnakar, Qijun Tan, Wolfgang Macherey
2021	J	`jnl`	Experts, Errors, and Context: A Large-Scale Study of Human Evaluation for Machine Translation. Trans. Assoc. Comput. Linguistics Markus Freitag, George F. Foster, David Grangier, Viresh Ratnakar, Qijun Tan, Wolfgang Macherey
2021	Misc	`conf`	Learning From Heterogeneous Eeg Signals with Differentiable Channel Reordering. ICASSP Aaqib Saeed, David Grangier, Olivier Pietquin, Neil Zeghidour
2021	J	`jnl`	Minimum Bayes Risk Decoding with Neural Metrics of Translation Quality. CoRR Markus Freitag, David Grangier, Qijun Tan, Bowen Liang
2021	J	`jnl`	On the Complementarity of Data Selection and Fine Tuning for Domain Adaptation. CoRR Dan Iter, David Grangier
2021	J	`jnl`	The Trade-offs of Domain Adaptation for Neural Language Models. CoRR Dan Iter, David Grangier
2021	J	`jnl`	Wavesplit: End-to-End Speech Separation by Speaker Clustering. IEEE ACM Trans. Audio Speech Lang. Process. Neil Zeghidour, David Grangier
2021	J	`jnl`	What Can Unsupervised Machine Translation Contribute to High-Resource Language Pairs? CoRR Kelly Marchisio, Markus Freitag, David Grangier
2020	—	`conf`	BLEU might be Guilty but References are not Innocent. EMNLP (1) Markus Freitag, David Grangier, Isaac Caswell
2020	J	`jnl`	BLEU might be Guilty but References are not Innocent. CoRR Markus Freitag, David Grangier, Isaac Caswell
2020	J	`jnl`	Contrastive Learning of General-Purpose Audio Representations. CoRR Aaqib Saeed, David Grangier, Neil Zeghidour
2020	J	`jnl`	Efficient Content-Based Sparse Attention with Routing Transformers. CoRR Aurko Roy, Mohammad Saffar, Ashish Vaswani, David Grangier
2020	—	`conf`	Human-Paraphrased References Improve Neural Machine Translation. WMT@EMNLP Markus Freitag, George F. Foster, David Grangier, Colin Cherry
2020	J	`jnl`	Human-Paraphrased References Improve Neural Machine Translation. CoRR Markus Freitag, George F. Foster, David Grangier, Colin Cherry
2020	J	`jnl`	Learning from Heterogeneous EEG Signals with Differentiable Channel Reordering. CoRR Aaqib Saeed, David Grangier, Olivier Pietquin, Neil Zeghidour
2020	J	`jnl`	Modeling Human Motion with Quaternion-Based Neural Networks. Int. J. Comput. Vis. Dario Pavllo, Christoph Feichtenhofer, Michael Auli, David Grangier
2020	A*	`conf`	Toward Better Storylines with Sentence-Level Language Models. ACL Daphne Ippolito, David Grangier, Douglas Eck, Chris Callison-Burch
2020	J	`jnl`	Toward Better Storylines with Sentence-Level Language Models. CoRR Daphne Ippolito, David Grangier, Douglas Eck, Chris Callison-Burch
2020	A*	`conf`	Translationese as a Language in "Multilingual" NMT. ACL Parker Riley, Isaac Caswell, Markus Freitag, David Grangier
2020	J	`jnl`	Wavesplit: End-to-End Speech Separation by Speaker Clustering. CoRR Neil Zeghidour, David Grangier
2019	A*	`conf`	3D Human Pose Estimation in Video With Temporal Convolutions and Semi-Supervised Training. CVPR Dario Pavllo, Christoph Feichtenhofer, David Grangier, Michael Auli
2019	—	`conf`	ELI5: Long Form Question Answering. ACL (1) Angela Fan, Yacine Jernite, Ethan Perez, David Grangier, Jason Weston, Michael Auli
2019	J	`jnl`	ELI5: Long Form Question Answering. CoRR Angela Fan, Yacine Jernite, Ethan Perez, David Grangier, Jason Weston, Michael Auli
2019	J	`jnl`	Modeling Human Motion with Quaternion-based Neural Networks. CoRR Dario Pavllo, Christoph Feichtenhofer, Michael Auli, David Grangier
2019	—	`conf`	Tagged Back-Translation. WMT (1) Isaac Caswell, Ciprian Chelba, David Grangier
2019	J	`jnl`	Tagged Back-Translation. CoRR Isaac Caswell, Ciprian Chelba, David Grangier
2019	J	`jnl`	Translationese as a Language in "Multilingual" NMT. CoRR Parker Riley, Isaac Caswell, Markus Freitag, David Grangier
2019	—	`conf`	Unsupervised Paraphrasing without Translation. ACL (1) Aurko Roy, David Grangier
2019	J	`jnl`	Unsupervised Paraphrasing without Translation. CoRR Aurko Roy, David Grangier
2019	—	`conf`	fairseq: A Fast, Extensible Toolkit for Sequence Modeling. NAACL-HLT (Demonstrations) Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, Michael Auli
2019	J	`jnl`	fairseq: A Fast, Extensible Toolkit for Sequence Modeling. CoRR Myle Ott, Sergey Edunov, Alexei Baevski, Angela Fan, Sam Gross, Nathan Ng, David Grangier, Michael Auli
2018	J	`jnl`	3D human pose estimation in video with temporal convolutions and semi-supervised training. CoRR Dario Pavllo, Christoph Feichtenhofer, David Grangier, Michael Auli
2018	A*	`conf`	Analyzing Uncertainty in Neural Machine Translation. ICML Myle Ott, Michael Auli, David Grangier, Marc'Aurelio Ranzato
2018	J	`jnl`	Analyzing Uncertainty in Neural Machine Translation. CoRR Myle Ott, Michael Auli, David Grangier, Marc'Aurelio Ranzato
2018	—	`conf`	Classical Structured Prediction Losses for Sequence to Sequence Learning. NAACL-HLT Sergey Edunov, Myle Ott, Michael Auli, David Grangier, Marc'Aurelio Ranzato
2018	—	`conf`	Controllable Abstractive Summarization. NMT@ACL Angela Fan, David Grangier, Michael Auli
2018	A	`conf`	QuaterNet: A Quaternion-based Recurrent Model for Human Motion. BMVC Dario Pavllo, David Grangier, Michael Auli
2018	J	`jnl`	QuaterNet: A Quaternion-based Recurrent Model for Human Motion. CoRR Dario Pavllo, David Grangier, Michael Auli
2018	—	`conf`	QuickEdit: Editing Text & Translations by Crossing Words Out. NAACL-HLT David Grangier, Michael Auli
2018	—	`conf`	Scaling Neural Machine Translation. WMT Myle Ott, Sergey Edunov, David Grangier, Michael Auli
2018	J	`jnl`	Scaling Neural Machine Translation. CoRR Myle Ott, Sergey Edunov, David Grangier, Michael Auli
2018	A*	`conf`	Understanding Back-Translation at Scale. EMNLP Sergey Edunov, Myle Ott, Michael Auli, David Grangier
2018	J	`jnl`	Understanding Back-Translation at Scale. CoRR Sergey Edunov, Myle Ott, Michael Auli, David Grangier
2017	—	`conf`	A Convolutional Encoder Model for Neural Machine Translation. ACL (1) Jonas Gehring, Michael Auli, David Grangier, Yann N. Dauphin
2017	J	`jnl`	Classical Structured Prediction Losses for Sequence to Sequence Learning. CoRR Sergey Edunov, Myle Ott, Michael Auli, David Grangier, Marc'Aurelio Ranzato
2017	J	`jnl`	Controllable Abstractive Summarization. CoRR Angela Fan, David Grangier, Michael Auli
2017	A*	`conf`	Convolutional Sequence to Sequence Learning. ICML Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N. Dauphin
2017	J	`jnl`	Convolutional Sequence to Sequence Learning. CoRR Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N. Dauphin
2017	A*	`conf`	Efficient softmax approximation for GPUs. ICML Edouard Grave, Armand Joulin, Moustapha Cissé, David Grangier, Hervé Jégou
2017	A*	`conf`	Language Modeling with Gated Convolutional Networks. ICML Yann N. Dauphin, Angela Fan, Michael Auli, David Grangier
2017	J	`jnl`	QuickEdit: Editing Text & Translations via Simple Delete Actions. CoRR David Grangier, Michael Auli
2016	J	`jnl`	A Convolutional Encoder Model for Neural Machine Translation. CoRR Jonas Gehring, Michael Auli, David Grangier, Yann N. Dauphin
2016	J	`jnl`	Efficient softmax approximation for GPUs. CoRR Edouard Grave, Armand Joulin, Moustapha Cissé, David Grangier, Hervé Jégou
2016	J	`jnl`	Generating Text from Structured Data with Application to the Biography Domain. CoRR Rémi Lebret, David Grangier, Michael Auli
2016	J	`jnl`	Interactive Semantic Featuring for Text Classification. CoRR Camille Jandot, Patrice Y. Simard, Max Chickering, David Grangier, Jina Suh
2016	J	`jnl`	Iterative Refinement for Machine Translation. CoRR Roman Novak, Michael Auli, David Grangier
2016	J	`jnl`	Language Modeling with Gated Convolutional Networks. CoRR Yann N. Dauphin, Angela Fan, Michael Auli, David Grangier
2016	A*	`conf`	Neural Text Generation from Structured Data with Application to the Biography Domain. EMNLP Rémi Lebret, David Grangier, Michael Auli
2016	A*	`conf`	Predicting distributions with Linearizing Belief Networks. ICLR (Poster) Yann N. Dauphin, David Grangier
2016	—	`conf`	Strategies for Training Large Vocabulary Neural Language Models. ACL (1) Wenlin Chen, David Grangier, Michael Auli
2016	J	`jnl`	Vocabulary Selection Strategies for Neural Machine Translation. CoRR Gurvan L'Hostis, David Grangier, Michael Auli
2015	J	`jnl`	Strategies for Training Large Vocabulary Neural Language Models. CoRR Wenlin Chen, David Grangier, Michael Auli
2014	J	`jnl`	GBC: Gradient boosting consensus model for heterogeneous data. Stat. Anal. Data Min. Xiaoxiao Shi, Jean-François Paiement, David Grangier, Philip S. Yu
2014	J	`jnl`	ICE: Enabling Non-Experts to Build Models Interactively for Large-Scale Lopsided Problems. CoRR Patrice Y. Simard, David Maxwell Chickering, Aparna Lakshmiratan, Denis Xavier Charles, Léon Bottou, Carlos Garcia Jurado Suarez, David Grangier, Saleema Amershi, Johan Verwey, Jina Suh
2012	A	`conf`	Learning from Heterogeneous Sources via Gradient Boosting Consensus. SDM Xiaoxiao Shi, Jean-François Paiement, David Grangier, Philip S. Yu
2010	—	`conf`	Feature Set Embedding for Incomplete Data. NIPS David Grangier, Iain Melvin
2010	A	`conf`	Half Transductive Ranking. AISTATS Bing Bai, Jason Weston, David Grangier, Ronan Collobert, Corinna Cortes, Mehryar Mohri
2010	—	`conf`	Label Embedding Trees for Large Multi-Class Tasks. NIPS Samy Bengio, Jason Weston, David Grangier
2010	J	`jnl`	Learning to rank with (a lot of) word features. Inf. Retr. Bing Bai, Jason Weston, David Grangier, Ronan Collobert, Kunihiko Sadamasa, Yanjun Qi, Olivier Chapelle, Kilian Q. Weinberger
2009	J	`jnl`	Discriminative keyword spotting. Speech Commun. Joseph Keshet, David Grangier, Samy Bengio
2009	—	`conf`	Polynomial Semantic Indexing. NIPS Bing Bai, Jason Weston, David Grangier, Ronan Collobert, Kunihiko Sadamasa, Yanjun Qi, Corinna Cortes, Mehryar Mohri
2009	A	`conf`	Supervised Semantic Indexing. ECIR Bing Bai, Jason Weston, Ronan Collobert, David Grangier
2009	A	`conf`	Supervised semantic indexing. CIKM Bing Bai, Jason Weston, David Grangier, Ronan Collobert, Kunihiko Sadamasa, Yanjun Qi, Olivier Chapelle, Kilian Q. Weinberger
2008	J	`jnl`	A Discriminative Kernel-Based Approach to Rank Images from Text Queries. IEEE Trans. Pattern Anal. Mach. Intell. David Grangier, Samy Bengio
2007	A	`conf`	Learning the inter-frame distance for discriminative template-based keyword detection. INTERSPEECH David Grangier, Samy Bengio
2006	—	`conf`	A Discriminative Approach for the Retrieval of Images from Text Queries. ECML David Grangier, Florent Monay, Samy Bengio
2006	—	`conf`	A Neural Network to Retrieve Images from Text Queries. ICANN (2) David Grangier, Samy Bengio
2006	—	`conf`	Learning to Retrieve Images from Text Queries with a Discriminative Model. Adaptive Multimedia Retrieval David Grangier, Florent Monay, Samy Bengio
2005	A	`conf`	Effect of segmentation method on video retrieval performance. ICME David Grangier, Alessandro Vinciarelli
2005	A	`conf`	Inferring document similarity from hyperlinks. CIKM David Grangier, Samy Bengio