• Code Translation with Compiler Representations (Szafraniec, Marc; Roziere, Baptiste; Charton, Hugh Leather Francois; Labatut, Patrick; Synnaeve, Gabriel; 2022)
• Star Temporal Classification: Sequence classification with partially labeled data (Pratap, Vineel; Hannun, Awni; Synnaeve, Gabriel; Collobert, Ronan; 2022)
• Flashlight: Enabling innovation in tools for machine learning (Kahn, Jacob D; Pratap, Vineel; Likhomanenko, Tatiana; Xu, Qiantong; Hannun, Awni; Cai, Jeff; Tomasello, Paden; Lee, Ann; Grave, Edouard; Avidov, Gilad; 2022)
• Augmenting Convolutional networks with attention-based aggregation (Touvron, Hugo; Cord, Matthieu; El-Nouby, Alaaeldin; Bojanowski, Piotr; Joulin, Armand; Synnaeve, Gabriel; Jégou, Hervé; 2021)
• Pseudo-Labeling for Massively Multilingual Speech Recognition (Lugosch, Loren; Likhomanenko, Tatiana; Synnaeve, Gabriel; Collobert, Ronan; 2022)
• Hierarchical skills for efficient exploration (Gehring, Jonas; Synnaeve, Gabriel; Krause, Andreas; Usunier, Nicolas; 2021)
• ASR4REAL: An extended benchmark for speech models (Riviere, Morgane; Copet, Jade; Synnaeve, Gabriel; 2021)
• Leveraging automated unit tests for unsupervised code translation (Roziere, Baptiste; Zhang, Jie M; Charton, Francois; Harman, Mark; Synnaeve, Gabriel; Lample, Guillaume; 2021)
• Word order does not matter for speech recognition (Pratap, Vineel; Xu, Qiantong; Likhomanenko, Tatiana; Synnaeve, Gabriel; Collobert, Ronan; 2022)
• Xcit: Cross-covariance image transformers (Ali, Alaaeldin; Touvron, Hugo; Caron, Mathilde; Bojanowski, Piotr; Douze, Matthijs; Joulin, Armand; Laptev, Ivan; Neverova, Natalia; Synnaeve, Gabriel; Verbeek, Jakob; 2021)
• ROMUL: Scale Adaptative Population Based Training (HAZIZA, Daniel; Rapin, Jérémy; Synnaeve, Gabriel; 2020)
• CAPE: Encoding relative positions with continuous augmented positional embeddings (Likhomanenko, Tatiana; Xu, Qiantong; Synnaeve, Gabriel; Collobert, Ronan; Rogozhnikov, Alex; 2021)
• Resmlp: Feedforward networks for image classification with data-efficient training (Touvron, Hugo; Bojanowski, Piotr; Caron, Mathilde; Cord, Matthieu; El-Nouby, Alaaeldin; Grave, Edouard; Izacard, Gautier; Joulin, Armand; Synnaeve, Gabriel; Verbeek, Jakob; 2021)
• MDETR-modulated detection for end-to-end multi-modal understanding (Kamath, Aishwarya; Singh, Mannat; LeCun, Yann; Synnaeve, Gabriel; Misra, Ishan; Carion, Nicolas; 2021)
• Differentiable model compression via pseudo quantization noise (Défossez, Alexandre; Adi, Yossi; Synnaeve, Gabriel; 2021)
• Gradient matching for domain generalization (Shi, Yuge; Seely, Jeffrey; Torr, Philip HS; Siddharth, N; Hannun, Awni; Usunier, Nicolas; Synnaeve, Gabriel; 2021)
• Robust wav2vec 2.0: Analyzing domain shift in self-supervised pre-training (Hsu, Wei-Ning; Sriram, Anuroop; Baevski, Alexei; Likhomanenko, Tatiana; Xu, Qiantong; Pratap, Vineel; Kahn, Jacob; Lee, Ann; Collobert, Ronan; Synnaeve, Gabriel; 2021)
• Going deeper with image transformers (Touvron, Hugo; Cord, Matthieu; Sablayrolles, Alexandre; Synnaeve, Gabriel; Jégou, Hervé; 2021)
• Semi-Supervised end-to-end Speech Recognition via Local Prior Matching (Hsu, Wei-Ning; Lee, Ann; Synnaeve, Gabriel; Hannun, Awni; 2021)
• Joint masked cpc and ctc training for asr (Talnikar, Chaitanya; Likhomanenko, Tatiana; Collobert, Ronan; Synnaeve, Gabriel; 2021)
• Rethinking evaluation in asr: Are our models robust enough? (Likhomanenko, Tatiana; Xu, Qiantong; Pratap, Vineel; Tomasello, Paden; Kahn, Jacob; Avidov, Gilad; Collobert, Ronan; Synnaeve, Gabriel; 2020)
• slimipl: Language-model-free iterative pseudo-labeling (Likhomanenko, Tatiana; Xu, Qiantong; Kahn, Jacob; Synnaeve, Gabriel; Collobert, Ronan; 2020)
• Self-training and pre-training are complementary for speech recognition (Xu, Qiantong; Baevski, Alexei; Likhomanenko, Tatiana; Tomasello, Paden; Conneau, Alexis; Collobert, Ronan; Synnaeve, Gabriel; Auli, Michael; 2021)
• Mls: A large-scale multilingual dataset for speech research (Pratap, Vineel; Xu, Qiantong; Sriram, Anuroop; Synnaeve, Gabriel; Collobert, Ronan; 2020)
• Population Based Training for Data Augmentation and Regularization in Speech Recognition (Haziza, Daniel; Rapin, Jérémy; Synnaeve, Gabriel; 2020)
• Word-level speech recognition with a letter to word encoder (Collobert, Ronan; Hannun, Awni; Synnaeve, Gabriel; 2020)
• Massively multilingual asr: 50 languages, 1 model, 1 billion parameters (Pratap, Vineel; Sriram, Anuroop; Tomasello, Paden; Hannun, Awni; Liptchinsky, Vitaliy; Synnaeve, Gabriel; Collobert, Ronan; 2020)
• Data augmenting contrastive learning of speech representations in the time domain (Kharitonov, Eugene; Rivière, Morgane; Synnaeve, Gabriel; Wolf, Lior; Mazaré, Pierre-Emmanuel; Douze, Matthijs; Dupoux, Emmanuel; 2021)
• Real time speech enhancement in the waveform domain (Defossez, Alexandre; Synnaeve, Gabriel; Adi, Yossi; 2020)
• End-to-end object detection with transformers (Carion, Nicolas; Massa, Francisco; Synnaeve, Gabriel; Usunier, Nicolas; Kirillov, Alexander; Zagoruyko, Sergey; 2020)
• Iterative pseudo-labeling for speech recognition (Xu, Qiantong; Likhomanenko, Tatiana; Kahn, Jacob; Hannun, Awni; Synnaeve, Gabriel; Collobert, Ronan; 2020)
• Contextualizing ASR lattice rescoring with hybrid pointer network language model (Liu, Da-Rong; Liu, Chunxi; Zhang, Frank; Synnaeve, Gabriel; Saraf, Yatharth; Zweig, Geoffrey; 2020)
• Deja-vu: Double feature presentation and iterated loss in deep transformer networks (Tjandra, Andros; Liu, Chunxi; Zhang, Frank; Zhang, Xiaohui; Wang, Yongqiang; Synnaeve, Gabriel; Nakamura, Satoshi; Zweig, Geoffrey; 2020)
• Semi-supervised speech recognition via local prior matching (Hsu, Wei-Ning; Lee, Ann; Synnaeve, Gabriel; Hannun, Awni; 2020)
• Polygames: Improved zero learning (Cazenave, Tristan; Chen, Yen-Chi; Chen, Guan-Wei; Chen, Shi-Yu; Chiu, Xian-Dong; Dehos, Julien; Elsa, Maria; Gong, Qucheng; Hu, Hengyuan; Khalidov, Vasil; 2020)
• Scaling up online speech recognition using convnets (Pratap, Vineel; Xu, Qiantong; Kahn, Jacob; Avidov, Gilad; Likhomanenko, Tatiana; Hannun, Awni; Liptchinsky, Vitaliy; Synnaeve, Gabriel; Collobert, Ronan; 2020)
• Libri-light: A benchmark for asr with limited or no supervision (Kahn, Jacob; Rivière, Morgane; Zheng, Weiyi; Kharitonov, Evgeny; Xu, Qiantong; Mazaré, Pierre-Emmanuel; Karadayi, Julien; Liptchinsky, Vitaliy; Collobert, Ronan; Fuegen, Christian; 2020)
• End-to-end asr: from supervised to semi-supervised learning with modern architectures (Synnaeve, Gabriel; Xu, Qiantong; Kahn, Jacob; Likhomanenko, Tatiana; Grave, Edouard; Pratap, Vineel; Sriram, Anuroop; Liptchinsky, Vitaliy; Collobert, Ronan; 2019)
• Growing Up Together: Structured Exploration for Large Action Spaces (Synnaeve, Gabriel; Gehring, Jonas; Lin, Zeming; Haziza, Daniel; Usunier, Nicolas; Rothermel, Danielle; Mella, Vegard; Ju, Da; Carion, Nicolas; Gustafson, Laura; 2019)
• Deja-vu: Double feature presentation in deep transformer networks (Tjandra, Andros; Liu, Chunxi; Zhang, Frank; Zhang, Xiaohui; Wang, Yongqiang; Synnaeve, Gabriel; Nakamura, Satoshi; Zweig, Geoffrey; 2020)
• A structured prediction approach for generalization in cooperative multi-agent reinforcement learning (Carion, Nicolas; Usunier, Nicolas; Synnaeve, Gabriel; Lazaric, Alessandro; 2019)
• Word-level Speech Recognition with a Dynamic Lexicon (Collobert, Ronan; Hannun, Awni; Synnaeve, Gabriel; 2019)
• Growing Action Spaces (Farquhar, Gregory; Gustafson, Laura; Lin, Zeming; Whiteson, Shimon; Usunier, Nicolas; Synnaeve, Gabriel; 2019)
• Why Build an Assistant in Minecraft? (Szlam, Arthur; Gray, Jonathan; Srinet, Kavya; Jernite, Yacine; Joulin, Armand; Synnaeve, Gabriel; Kiela, Douwe; Yu, Haonan; Chen, Zhuoyuan; Goyal, Siddharth; 2019)
• Who needs words? lexicon-free speech recognition (Likhomanenko, Tatiana; Synnaeve, Gabriel; Collobert, Ronan; 2019)
• A fully differentiable beam search decoder (Collobert, Ronan; Hannun, Awni; Synnaeve, Gabriel; 2019)
• Bayesian programming and learning for multi-player video games: application to RTS AI (Synnaeve, Gabriel; 2012)
• Wav2letter++: A fast open-source speech recognition system (Pratap, Vineel; Hannun, Awni; Xu, Qiantong; Cai, Jeff; Kahn, Jacob; Synnaeve, Gabriel; Liptchinsky, Vitaliy; Collobert, Ronan; 2019)
• Fully convolutional speech recognition (Zeghidour, Neil; Xu, Qiantong; Liptchinsky, Vitaliy; Usunier, Nicolas; Synnaeve, Gabriel; Collobert, Ronan; 2018)
• To reverse the gradient or not: An empirical comparison of adversarial and multi-task learning in speech recognition (Adi, Yossi; Zeghidour, Neil; Collobert, Ronan; Usunier, Nicolas; Liptchinsky, Vitaliy; Synnaeve, Gabriel; 2019)
• High-level strategy selection under partial observability in starcraft: Brood war (Gehring, Jonas; Ju, Da; Mella, Vegard; Gant, Daniel; Usunier, Nicolas; Synnaeve, Gabriel; 2018)
• Forward modeling for partial observation strategy games-a starcraft defogger (Synnaeve, Gabriel; Lin, Zeming; Gehring, Jonas; Gant, Dan; Mella, Vegard; Khalidov, Vasil; Carion, Nicolas; Usunier, Nicolas; 2018)
• End-to-end speech recognition from the raw waveform (Zeghidour, Neil; Usunier, Nicolas; Synnaeve, Gabriel; Collobert, Ronan; Dupoux, Emmanuel; 2018)
• Value propagation networks (Nardelli, Nantas; Synnaeve, Gabriel; Lin, Zeming; Kohli, Pushmeet; Torr, Philip HS; Usunier, Nicolas; 2018)
• Intrinsic motivation and automatic curricula via asymmetric self-play (Sukhbaatar, Sainbayar; Lin, Zeming; Kostrikov, Ilya; Synnaeve, Gabriel; Szlam, Arthur; Fergus, Rob; 2017)
• Letter-Based Speech Recognition with Gated ConvNets (Liptchinsky, Vitaliy; Synnaeve, Gabriel; Collobert, Ronan; 2017)
• Learning filterbanks from raw speech for phone recognition (Zeghidour, Neil; Usunier, Nicolas; Kokkinos, Iasonas; Schatz, Thomas; Synnaeve, Gabriel; Dupoux, Emmanuel; 2018)
• An analysis of model-based heuristic search techniques for StarCraft combat scenarios (Churchill, David; Lin, Zeming; Synnaeve, Gabriel; 2017)
• Stardata: A starcraft ai research dataset (Lin, Zeming; Gehring, Jonas; Khalidov, Vasil; Synnaeve, Gabriel; 2017)
• Torchcraft: a library for machine learning research on real-time strategy games (Synnaeve, Gabriel; Nardelli, Nantas; Auvolat, Alex; Chintala, Soumith; Lacroix, Timothée; Lin, Zeming; Richoux, Florian; Usunier, Nicolas; 2016)
• Wav2letter: an end-to-end convnet-based speech recognition system (Collobert, Ronan; Puhrsch, Christian; Synnaeve, Gabriel; 2016)
• Episodic exploration for deep deterministic policies: An application to starcraft micromanagement tasks (Usunier, Nicolas; Synnaeve, Gabriel; Lin, Zeming; Chintala, Soumith; 2016)
• Jointly Learning to Locate and Classify Words Using Convolutional Networks. (Palaz, Dimitri; Synnaeve, Gabriel; Collobert, Ronan; 2016)
• Joint learning of speaker and phonetic similarities with siamese networks. (Zeghidour, Neil; Synnaeve, Gabriel; Usunier, Nicolas; Dupoux, Emmanuel; 2016)
• Classification and automatic transcription of primate calls (Versteegh, Maarten; Kuhn, Jeremy; Synnaeve, Gabriel; Ravaux, Lucie; Chemla, Emmanuel; Cäsar, Cristiane; Fuller, James; Murphy, Derek; Schel, Anne; Dunbar, Ewan; 2016)
• A temporal coherence loss function for learning unsupervised acoustic embeddings (Synnaeve, Gabriel; Dupoux, Emmanuel; 2016)
• Starcraft bots and competitions (Churchill, David; Preuss, Mike; Richoux, Florian; Synnaeve, Gabriel; Uriarte, Alberto; Ontanón, Santiago; Certicky, Michal; 2016)
• Quantitative Methods for Comparing Featural Representations (Dunbar, Ewan; Synnaeve, Gabriel; Dupoux, Emmanuel; 2015)
• Prosodic boundary information helps unsupervised word segmentation (Ludusan, Bogdan; Synnaeve, Gabriel; Dupoux, Emmanuel; 2015)
• A deep scattering spectrum—deep siamese network pipeline for unsupervised acoustic modeling (Zeghidour, Neil; Synnaeve, Gabriel; Versteegh, Maarten; Dupoux, Emmanuel; 2016)
• Mazebase: A sandbox for learning from games (Sukhbaatar, Sainbayar; Szlam, Arthur; Synnaeve, Gabriel; Chintala, Soumith; Fergus, Rob; 2015)
• RTS AI Problems and Techniques. (Ontanón, Santiago; Synnaeve, Gabriel; Uriarte, Alberto; Richoux, Florian; Churchill, David; Preuss, Mike; 2015)
• Multiscale Bayesian modeling for RTS games: An application to StarCraft AI (Synnaeve, Gabriel; Bessiere, Pierre; 2015)
• A hybrid dynamic time warping-deep neural network architecture for unsupervised acoustic modeling (Thiolliere, Roland; Dunbar, Ewan; Synnaeve, Gabriel; Versteegh, Maarten; Dupoux, Emmanuel; 2015)
• Phonetics Embedding Learning with Side Information (Synnaeve, Gabriel; Schatz, Thomas; Dupoux, Emmanuel; 2014)
• Unsupervised Word Segmentation in Context (Synnaeve, Gabriel; Dautriche, Isabelle; Börschinger, Benjamin; Johnson, Mark; Dupoux, Emmanuel; 2014)
• Learning words from images and speech (Synnaeve, Gabriel; Versteegh, Maarten; Dupoux, Emmanuel; 2014)
• Weakly supervised multi-embeddings learning of acoustic models (Synnaeve, Gabriel; Dupoux, Emmanuel; 2014)
• A survey of real-time strategy game AI research and competition in StarCraft (Ontanón, Santiago; Synnaeve, Gabriel; Uriarte, Alberto; Richoux, Florian; Churchill, David; Preuss, Mike; 2013)
• Discretized kinetic models for abductive reasoning in systems biology (Synnaeve, Gabriel; Inoue, Katsumi; Doncescu, Andrei; Nabeshima, Hidetomo; Kameya, Yoshitaka; Ishihata, Masakazu; Sato, Taisuke; 2011)
• Programmation et apprentissage bayésien pour les jeux vidéo multi-joueurs, application à l'intelligence artificielle de jeux de stratégies temps-réel (Synnaeve, Gabriel; 2012)
• A dataset for StarCraft AI and an example of armies clustering (Synnaeve, Gabriel; Bessiere, Pierre; 2012)
• A Bayesian Tactician (Synnaeve, Gabriel; Bessiere, Pierre; 2012)
• Special tactics: A bayesian approach to tactical decision-making (Synnaeve, Gabriel; Bessiere, Pierre; 2012)
• A Bayesian hybrid approach to unsupervised time series discretization (Kameya, Yoshitaka; Synnaeve, Gabriel; Doncescu, Andrei; Inoue, Katsumi; Sato, Taisuke; 2010)
• Bayesian modeling of a human MMORPG player (Synnaeve, Gabriel; Bessière, Pierre; 2011)
• A Bayesian model for RTS units control applied to StarCraft (Synnaeve, Gabriel; Bessiere, Pierre; 2011)
• A Bayesian model for plan recognition in RTS games applied to StarCraft (Synnaeve, Gabriel; Bessiere, Pierre; 2011)
• A Bayesian model for opening prediction in RTS games with application to StarCraft (Synnaeve, Gabriel; Bessiere, Pierre; 2011)
• Kinetic models for logic-based hypothesis finding in metabolic pathways (Synnaeve, Gabriel; Doncescu, Andrei; Inoue, Katsumi; 2009)
• Kinetic models and qualitative abstraction for relational learning in systems biology (Synnaeve, Gabriel; Inoue, Katsumi; Doncescu, Andrei; Nabeshima, Hidetomo; Kameya, Yoshitaka; Ishihata, Masakazu; Sato, Taisuke; 2011)