🧑‍🔬 Armand Joulin — all works

35 works · ← Armand Joulin

1. Enriching Word Vectors with Subword InformationTransactions of the Association for Computational Linguistics (TACL)Piotr Bojanowski, Edouard Grave, Armand Joulin, et al.2017 · 11,873 citations
2. LLaMA: Open and Efficient Foundation Language ModelsarXiv:2302.13971Hugo Touvron, Thibaut Lavril, Gautier Izacard, et al.2023 · 9,603 citations
3. Emerging Properties in Self-Supervised Vision TransformersIEEE/CVF International Conference on Computer Vision (ICCV)Mathilde Caron, Hugo Touvron, Ishan Misra, et al.2021 · 6,046 citations
4. Bag of Tricks for Efficient Text Classification ↗Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers · no summary yetArmand Joulin et al.2017 · 5,325 citations
5. Gemma: Open Models Based on Gemini Research and Technology ↗arXiv:2403.08295 · no summary yetGemma Team et al.2024 · 1,313 citations
6. Gemma 2: Improving Open Language Models at a Practical Size ↗arXiv:2408.00118 · no summary yetGemma Team et al.2024 · 1,302 citations
7. FastText.zip: Compressing text classification modelsarXiv:1612.03651Armand Joulin, Edouard Grave, Piotr Bojanowski, et al.2016 · 1,219 citations
8. Gemma 3 Technical Report ↗arXiv:2503.19786 · no summary yetGemma Team et al.2025 · 1,147 citations
9. ImageBind: One Embedding Space To Bind Them AllIEEE Computer Society Conference on Computer Vision and Pattern RecognitionRohit Girdhar, Alaaeldin El-Nouby, Zhuang Liu, et al.2023 · 954 citations
10. LeViT: a Vision Transformer in ConvNet’s Clothing for Faster Inference ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetBenjamin Graham et al.2021 · 908 citations
11. Unsupervised Dense Information Retrieval with Contrastive LearningarXiv:2112.09118Gautier Izacard, Mathilde Caron, Lucas Hosseini, et al.2021 · 836 citations
12. Atlas: Few-shot Learning with Retrieval Augmented Language ModelsarXiv:2208.03299Gautier Izacard, Patrick Lewis, Maria Lomeli, et al.2022 · 673 citations
13. CCNet: Extracting High Quality Monolingual Datasets from Web Crawl DataLanguage Resources and Evaluation Conference (LREC)Guillaume Wenzek, Marie-Anne Lachaux, Alexis Conneau, et al.2020 · 666 citations
14. Learning Word Vectors for 157 LanguagesLanguage Resources and Evaluation Conference (LREC)Edouard Grave, Piotr Bojanowski, Prakhar Gupta, et al.2018 · 646 citations
15. Advances in Pre-Training Distributed Word RepresentationsLanguage Resources and Evaluation Conference (LREC)Tomas Mikolov, Edouard Grave, Piotr Bojanowski, et al.2017 · 628 citations
16. Reducing Transformer Depth on Demand with Structured DropoutarXiv:1909.11556Angela Fan, Edouard Grave, Armand Joulin2019 · 560 citations
17. Towards AI-Complete Question Answering: A Set of Prerequisite Toy TasksJason Weston, Antoine Bordes, Sumit Chopra, et al.Mova's core list · 555 citations
18. An End-to-End Transformer Model for 3D Object Detection ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetIshan Misra, Rohit Girdhar, Armand Joulin2021 · 515 citations
19. Loss in Translation: Learning Bilingual Word Mapping with a Retrieval CriterionConference on Empirical Methods in Natural Language Processing (EMNLP)Armand Joulin, Piotr Bojanowski, Tomas Mikolov, et al.2018 · 479 citations
20. Adaptive Attention Span in TransformersAnnual Meeting of the Association for Computational Linguistics (ACL)Sainbayar Sukhbaatar, Edouard Grave, Piotr Bojanowski, et al.2019 · 367 citations
21. Unsupervised Joint Object Discovery and Segmentation in Internet Images ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetMichael Rubinstein et al.2013 · 362 citations
22. CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEBarXiv:1911.04944Holger Schwenk, Guillaume Wenzek, Sergey Edunov, et al.2019 · 358 citations
23. Self-Supervised Pretraining of 3D Features on any Point-Cloud ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetZaiwei Zhang et al.2021 · 282 citations
24. Unsupervised Pre-Training of Image Features on Non-Curated Data ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetMathilde Caron et al.2019 · 262 citations
25. Efficient softmax approximation for GPUsarXiv:1609.04309Edouard Grave, Armand Joulin, Moustapha Cisse, et al.2016 · 205 citations
26. Omnivore: A Single Model for Many Visual Modalities ↗IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · no summary yetRohit Girdhar et al.2022 · 204 citations
27. Improving Neural Language Models with a Continuous Cache ↗arXiv:1612.04426 · no summary yetEdouard Grave, Armand Joulin, Nicolas Usunier2016 · 179 citations
28. MedGemma Technical Report ↗arXiv:2507.05201 · no summary yetAndrew Sellergren et al.2025 · 150 citations
29. Linking People in Videos with “Their” Names Using Coreference Resolution ↗Lecture notes in computer science · no summary yetVignesh Ramanathan et al.2014 · 103 citations
30. Augmenting Self-attention with Persistent Memory ↗arXiv (Cornell University) · no summary yetSainbayar Sukhbaatar et al.2019 · 84 citations
31. The effectiveness of MAE pre-pretraining for billion-scale pretraining ↗IEEE/CVF International Conference on Computer Vision (ICCV) · no summary yetMannat Singh et al.2023 · 56 citations
32. Learning Simple Algorithms from Examples ↗arXiv (Cornell University) · no summary yetWojciech Zaremba et al.2015 · 41 citations
33. RecurrentGemma: Moving Past Transformers for Efficient Open Language Models ↗arXiv (Cornell University) · no summary yetAleksandar Botev et al.2024 · 22 citations
34. Target Conditioning for One-to-Many Generation ↗Findings of the Association for Computational Linguistics: EMNLP 2020 · no summary yetMarie-Anne Lachaux, Armand Joulin, Guillaume Lample2020 · 17 citations
35. CommAI: Evaluating the first steps towards a useful general AI ↗arXiv:1701.08954 · no summary yetMarco Baroni et al.2017 · 12 citations

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/armand-joulin/works/