Maha Elbayad

40 papers A* 2A 2B 2C 1Journal 23Unranked 9
YearRankTypeTitle / Venue / Authors
2025 J jnl
Interference Matrix: Quantifying Cross-Lingual Interference in Transformer Encoders.
CoRR
Belen Alastruey, João Maria Janeiro, Alexandre Allauzen, Maha Elbayad, Loïc Barrault, Marta R. Costa-jussà
2025 — conf
Less Mature is More Adaptable for Sentence-level Language Modeling.
ACL (1)
Abhilasha Sancheti, David Dale, Artyom Kozhevnikov, Maha Elbayad
2025 A* conf
Mixture of Languages: Improved Multilingual Encoders Through Language Grouping.
EMNLP
João Maria Janeiro, Belen Alastruey, Francisco Massa, Maha Elbayad, Benjamin Piwowarski, Patrick Gallinari, Loïc Barrault
2025 J jnl
TV2TV: A Unified Framework for Interleaved Language and Video Generation.
CoRR
Xiaochuang Han, Youssef Emad, Melissa Hall, John Nguyen, Karthik Padthe, Liam Robbins, Amir Bar, Delong Chen, Michal Drozdzal, Maha Elbayad, Yushi Hu, Shang-wen Li, Sreya Dutta Roy, Jakob Verbeek, Xudong Wang, Marjan Ghazvininejad, Luke Zettlemoyer, Emily Dinan
2025 J jnl
Text-Guided Semantic Image Encoder.
CoRR
Raghuveer Thirukovalluru, Xiaochuang Han, Bhuwan Dhingra, Emily Dinan, Maha Elbayad
2025 J jnl
VUGEN: Visual Understanding priors for GENeration.
CoRR
Xiangyi Chen, Théophane Vallaeys, Maha Elbayad, John Nguyen, Jakob Verbeek
2024 — conf
Added Toxicity Mitigation at Inference Time for Multimodal and Massively Multilingual Translation.
EAMT (1)
Marta R. Costa-jussà, David Dale, Maha Elbayad, Bokai Yu
2024 J jnl
Large Concept Models: Language Modeling in a Sentence Representation Space.
CoRR
LCM team, Loïc Barrault, Paul-Ambroise Duquenne, Maha Elbayad, Artyom Kozhevnikov, Belen Alastruey, Pierre Andrews, Mariano Coria, Guillaume Couairon, Marta R. Costa-jussà, David Dale, Hady Elsahar, Kevin Heffernan, João Maria Janeiro, Tuan Tran, Christophe Ropers, Eduardo Sánchez, Robin San Roman, Alexandre Mourachko, Safiyyah Saleem, Holger Schwenk
2024 J jnl
Merging Text Transformer Models from Different Initializations.
CoRR
Neha Verma, Maha Elbayad
2024 J jnl
Merging Text Transformer Models from Different Initializations.
Trans. Mach. Learn. Res.
Neha Verma, Maha Elbayad
2024 J jnl
SpiRit-LM: Interleaved Spoken and Written Language Model.
CoRR
Tu Anh Nguyen, Benjamin Muller, Bokai Yu, Marta R. Costa-jussà, Maha Elbayad, Sravya Popuri, Paul-Ambroise Duquenne, Robin Algayres, Ruslan Mavlyutov, Itai Gat, Gabriel Synnaeve, Juan Pino, Benoît Sagot, Emmanuel Dupoux
2023 J jnl
Added Toxicity Mitigation at Inference Time for Multimodal and Massively Multilingual Translation.
CoRR
Marta R. Costa-jussà, David Dale, Maha Elbayad, Bokai Yu
2023 — conf
Causes and Cures for Interference in Multilingual Translation.
ACL (1)
Uri Shaham, Maha Elbayad, Vedanuj Goswami, Omer Levy, Shruti Bhosale
2023 A conf
Efficiently Upgrading Multilingual Machine Translation Models to Support More Languages.
EACL
Simeng Sun, Maha Elbayad, Anna Y. Sun, James Cross
2023 J jnl
Efficiently Upgrading Multilingual Machine Translation Models to Support More Languages.
CoRR
Simeng Sun, Maha Elbayad, Anna Y. Sun, James Cross
2023 — conf
Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation.
ACL (Findings)
Maha Elbayad, Anna Y. Sun, Shruti Bhosale
2023 J jnl
Seamless: Multilingual Expressive and Streaming Speech Translation.
CoRR
Loïc Barrault, Yu-An Chung, Mariano Coria Meglioli, David Dale, Ning Dong, Mark Duppenthaler, Paul-Ambroise Duquenne, Brian Ellis, Hady Elsahar, Justin Haaheim, John Hoffman, Min-Jae Hwang, Hirofumi Inaguma, Christopher Klaiber, Ilia Kulikov, Pengwei Li, Daniel Licht, Jean Maillard, Ruslan Mavlyutov, Alice Rakotoarison, Kaushik Ram Sadagopan, Abinesh Ramakrishnan, Tuan Tran, Guillaume Wenzek, Yilin Yang, Ethan Ye, Ivan Evtimov, Pierre Fernandez, Cynthia Gao, Prangthip Hansanti, Elahe Kalbassi, Amanda Kallet, Artyom Kozhevnikov, Gabriel Mejia Gonzalez, Robin San Roman, Christophe Touret, Corinne Wong, Carleigh Wood, Bokai Yu, Pierre Andrews, Can Balioglu, Peng-Jen Chen, Marta R. Costa-jussà, Maha Elbayad, Hongyu Gong, Francisco Guzmán, Kevin Heffernan, Somya Jain, Justine Kao, Ann Lee, Xutai Ma, Alexandre Mourachko, Benjamin N. Peloquin, Juan Pino, Sravya Popuri, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Anna Y. Sun, Paden Tomasello, Changhan Wang, Jeff Wang, Skyler Wang, Mary Williamson
2023 J jnl
SeamlessM4T-Massively Multilingual & Multimodal Machine Translation.
CoRR
Seamless Communication, Loïc Barrault, Yu-An Chung, Mariano Coria Meglioli, David Dale, Ning Dong, Paul-Ambroise Duquenne, Hady Elsahar, Hongyu Gong, Kevin Heffernan, John Hoffman, Christopher Klaiber, Pengwei Li, Daniel Licht, Jean Maillard, Alice Rakotoarison, Kaushik Ram Sadagopan, Guillaume Wenzek, Ethan Ye, Bapi Akula, Peng-Jen Chen, Naji El Hachem, Brian Ellis, Gabriel Mejia Gonzalez, Justin Haaheim, Prangthip Hansanti, Russ Howes, Bernie Huang, Min-Jae Hwang, Hirofumi Inaguma, Somya Jain, Elahe Kalbassi, Amanda Kallet, Ilia Kulikov, Janice Lam, Daniel Li, Xutai Ma, Ruslan Mavlyutov, Benjamin N. Peloquin, Mohamed Ramadan, Abinesh Ramakrishnan, Anna Y. Sun, Kevin Tran, Tuan Tran, Igor Tufanov, Vish Vogeti, Carleigh Wood, Yilin Yang, Bokai Yu, Pierre Andrews, Can Balioglu, Marta R. Costa-jussà, Onur Celebi, Maha Elbayad, Cynthia Gao, Francisco Guzmán, Justine Kao, Ann Lee, Alexandre Mourachko, Juan Pino, Sravya Popuri, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Paden Tomasello, Changhan Wang, Jeff Wang, Skyler Wang
2023 — conf
Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity.
EMNLP (Findings)
Haoran Xu, Maha Elbayad, Kenton Murray, Jean Maillard, Vedanuj Goswami
2023 J jnl
Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity.
CoRR
Haoran Xu, Maha Elbayad, Kenton Murray, Jean Maillard, Vedanuj Goswami
2022 J jnl
Causes and Cures for Interference in Multilingual Translation.
CoRR
Uri Shaham, Maha Elbayad, Vedanuj Goswami, Omer Levy, Shruti Bhosale
2022 — conf
Findings of the IWSLT 2022 Evaluation Campaign.
IWSLT@ACL
Antonios Anastasopoulos, Loïc Barrault, Luisa Bentivogli, Marcely Zanon Boito, Ondrej Bojar, Roldano Cattoni, Anna Currey, Georgiana Dinu, Kevin Duh, Maha Elbayad, Clara Emmanuel, Yannick Estève, Marcello Federico, Christian Federmann, Souhir Gahbiche, Hongyu Gong, Roman Grundkiewicz, Barry Haddow, Benjamin Hsu, Dávid Javorský, Vera Kloudová, Surafel Melaku Lakew, Xutai Ma, Prashant Mathur, Paul McNamee, Kenton Murray, Maria Nadejde, Satoshi Nakamura, Matteo Negri, Jan Niehues, Xing Niu, John Ortega, Juan Miguel Pino, Elizabeth Salesky, Jiatong Shi, Matthias Sperber, Sebastian Stüker, Katsuhito Sudoh, Marco Turchi, Yogesh Virkar, Alexander Waibel, Changhan Wang, Shinji Watanabe
2022 J jnl
Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation.
CoRR
Maha Elbayad, Anna Y. Sun, Shruti Bhosale
2022 J jnl
No Language Left Behind: Scaling Human-Centered Machine Translation.
CoRR
Marta R. Costa-jussà, James Cross, Onur Çelebi, Maha Elbayad, Kenneth Heafield, Kevin Heffernan, Elahe Kalbassi, Janice Lam, Daniel Licht, Jean Maillard, Anna Y. Sun, Skyler Wang, Guillaume Wenzek, Al Youngblood, Bapi Akula, Loïc Barrault, Gabriel Mejia Gonzalez, Prangthip Hansanti, John Hoffman, Semarley Jarrett, Kaushik Ram Sadagopan, Dirk Rowe, Shannon Spruit, Chau Tran, Pierre Andrews, Necip Fazil Ayan, Shruti Bhosale, Sergey Edunov, Angela Fan, Cynthia Gao, Vedanuj Goswami, Francisco Guzmán, Philipp Koehn, Alexandre Mourachko, Christophe Ropers, Safiyyah Saleem, Holger Schwenk, Jeff Wang
2022 C conf
Rethinking the Design of Sequence-to-Sequence Models for Efficient Machine Translation.
EAMT
Maha Elbayad
2021 — conf
Findings of the IWSLT 2021 Evaluation Campaign.
IWSLT
Antonios Anastasopoulos, Ondrej Bojar, Jacob Bremerman, Roldano Cattoni, Maha Elbayad, Marcello Federico, Xutai Ma, Satoshi Nakamura, Matteo Negri, Jan Niehues, Juan Miguel Pino, Elizabeth Salesky, Sebastian Stüker, Katsuhito Sudoh, Marco Turchi, Alex Waibel, Changhan Wang, Matthew Wiesner
2021 J jnl
Joint source-target encoding with pervasive attention.
Mach. Transl.
Maha Elbayad, Laurent Besacier, Jakob Verbeek
2020 A* conf
Depth-Adaptive Transformer.
ICLR
Maha Elbayad, Jiatao Gu, Edouard Grave, Michael Auli
2020 A conf
Efficient Wait-k Models for Simultaneous Machine Translation.
INTERSPEECH
Maha Elbayad, Laurent Besacier, Jakob Verbeek
2020 J jnl
Efficient Wait-k Models for Simultaneous Machine Translation.
CoRR
Maha Elbayad, Laurent Besacier, Jakob Verbeek
2020 — conf
ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020.
IWSLT
Maha Elbayad, Ha Nguyen, Fethi Bougares, Natalia A. Tomashenko, Antoine Caubrière, Benjamin Lecouteux, Yannick Estève, Laurent Besacier
2020 J jnl
ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020.
CoRR
Maha Elbayad, Ha Nguyen, Fethi Bougares, Natalia A. Tomashenko, Antoine Caubrière, Benjamin Lecouteux, Yannick Estève, Laurent Besacier
2020 B conf
Online Versus Offline NMT Quality: An In-depth Analysis on English-German and German-English.
COLING
Maha Elbayad, Michael Ustaszewski, Emmanuelle Esperança-Rodier, Francis Brunet-Manquat, Jakob Verbeek, Laurent Besacier
2020 J jnl
Online Versus Offline NMT Quality: An In-depth Analysis on English-German and German-English.
CoRR
Maha Elbayad, Michael Ustaszewski, Emmanuelle Esperança-Rodier, Francis Brunet-Manquat, Laurent Besacier
2020 — —
Rethinking the Design of Sequence-to-Sequence Models for Efficient Machine Translation. (Une alternative aux modèles neuronaux séquence-à-séquence pour la traduction automatique).
Maha Elbayad
2019 J jnl
Depth-Adaptive Transformer.
CoRR
Maha Elbayad, Jiatao Gu, Edouard Grave, Michael Auli
2018 B conf
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction.
CoNLL
Maha Elbayad, Laurent Besacier, Jakob Verbeek
2018 J jnl
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction.
CoRR
Maha Elbayad, Laurent Besacier, Jakob Verbeek
2018 — conf
Token-level and sequence-level loss smoothing for RNN language models.
ACL (1)
Maha Elbayad, Laurent Besacier, Jakob Verbeek
2018 J jnl
Token-level and sequence-level loss smoothing for RNN language models.
CoRR
Maha Elbayad, Laurent Besacier, Jakob Verbeek