AJ
Armand Joulin
cs.CLcs.LGcs.CVcs.AIstat.MLcs.IRArtificial Intelligencecs.NEcs.SDeess.AS
On Valency
published · living versionsW_vu5dc8qp·v1 · currentpublished
EmbeddingGemma 2: Unified and Efficient Multimodal Representations
with Henrique Schechter Vera, Sahil Dua, Jovan Andonov, Sara Smoot +68
1 version
Preprints & journals
88 papers in the corpus · 2008–2026An open vision-language model for diverse medical applications.42839104 · Sellergren, Andrew, Kazemzadeh, Sahar, Mahvar, Fereshteh et al.2026 · 46 citationsNature medicine. 2026;32(10):3695-3704
Advancing human-centric AI for robust X-ray analysis through holistic self-supervised learning.42754575 · Moutakanni, Théo, Bojanowski, Piotr, Chassagnon, Guillaume et al.2026 · 5 citationsNature communications. 2026;17(1)
Gemma 4 Technical Report2607.02770v2 · Gemma Team: Sherif El Abd, Vaibhav Aggarwal, Robin Algayres et al.2026 · 8 citationsarXiv
Cell-DINO: Self-supervised image-based embeddings for cell fluorescent microscopy.41460955 · Moutakanni, Théo, Couprie, Camille, Yi, Seungeun et al.2026 · 6 citationsPLoS computational biology. 2025;21(12):e1013828
T5Gemma 2: Seeing, Reading, and Understanding Longer2512.14856v2 · Biao Zhang, Paul Suganthan, Gael Liu et al.2025 · 0 citationsarXiv
VaultGemma: A Differentially Private Gemma Model2510.15001v2 · Amer Sinha, Thomas Mesnard, Ryan McKenna et al.2025 · 1 citationarXiv
EmbeddingGemma: Powerful and Lightweight Text Representations2509.20354v3 · Henrique Schechter Vera, Sahil Dua, Biao Zhang et al.2025 · 4 citationsarXiv
Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation2504.06225v1 · Biao Zhang, Fedor Moiseev, Joshua Ainslie et al.2025 · 0 citationsarXiv
Gemma 3 Technical Report2503.19786v1 · Gemma Team: Aishwarya Kamath, Johan Ferret, Shreya Pathak et al.2025 · 72 citationsarXiv
Gemma 2: Improving Open Language Models at a Practical Size2408.00118v3 · Gemma Team: Morgane Riviere, Shreya Pathak, Pier Giuseppe Sessa et al.2024 · 149 citationsarXiv
Whispering Experts: Neural Interventions for Toxicity Mitigation in Language Models2407.12824v1 · Xavier Suau, Pieter Delobelle, Katherine Metcalf et al.2024 · 0 citationsarXiv
Time Sensitive Knowledge Editing through Efficient Finetuning2406.04496v2 · Xiou Ge, Ali Mousavi, Edouard Grave et al.2024 · 0 citationsarXiv
Automatic Data Curation for Self-Supervised Learning: A Clustering-Based Approach2405.15613v2 · Huy V. Vo, Vasil Khalidov, Timoth'ee Darcet et al.2024 · 6 citationsarXiv
RecurrentGemma: Moving Past Transformers for Efficient Open Language Models2404.07839v2 · Aleksandar Botev, Soham De, Samuel L Smith et al.2024 · 5 citationsarXiv
Gemma: Open Models Based on Gemini Research and Technology2403.08295v4 · Gemma Team: Thomas Mesnard, Cassidy Hardin, Robert Dadashi et al.2024 · 283 citationsarXiv
Scalable Pre-training of Large Autoregressive Image Models2401.08541v1 · Alaaeldin El-Nouby, Michal Klein, Shuangfei Zhai et al.2024 · 9 citationsarXiv
PaSS: Parallel Speculative Sampling2311.13581v1 · Giovanni Monea, Armand Joulin, Edouard Grave2023 · 2 citationsarXiv
ImageBind: One Embedding Space To Bind Them All2305.05665v2 · Rohit Girdhar, Alaaeldin El-Nouby, Zhuang Liu et al.2023 · 860 citationsarXiv
DINOv2: Learning Robust Visual Features without Supervision2304.07193v2 · Maxime Oquab, Timoth'ee Darcet, Th'eo Moutakanni et al.2023 · 1,077 citationsarXiv
The effectiveness of MAE pre-pretraining for billion-scale pretraining2303.13496v3 · Mannat Singh, Quentin Duval, Kalyan Vasudev Alwala et al.2023 · 54 citationsarXiv
ResMLP: Feedforward Networks for Image Classification With Data-Efficient Training.36094972 · Touvron, Hugo, Bojanowski, Piotr, Caron, Mathilde et al.2023 · 807 citationsIEEE transactions on pattern analysis and machine intelligence. 2023;45(4):5314-5321
LLaMA: Open and Efficient Foundation Language Models2302.13971v1 · Hugo Touvron, Thibaut Lavril, Gautier Izacard et al.2023 · 4,525 citationsarXiv
Atlas: Few-shot Learning with Retrieval Augmented Language Models2208.03299v3 · Gautier Izacard, Patrick Lewis, Maria Lomeli et al.2022 · 213 citationsarXiv
Improving Wikipedia Verifiability with AI2207.06220v1 · Fabio Petroni, Samuel Broscheit, Aleksandra Piktus et al.2022 · 20 citationsarXiv
OmniMAE: Single Model Masked Pretraining on Images and Videos2206.08356v2 · Rohit Girdhar, Alaaeldin El-Nouby, Mannat Singh et al.2022 · 77 citationsarXiv
Masked Siamese Networks for Label-Efficient Learning2204.07141v1 · Mahmoud Assran, Mathilde Caron, Ishan Misra et al.2022 · 231 citationsarXiv
Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision2202.08360v2 · Priya Goyal, Quentin Duval, Isaac Seessel et al.2022 · 47 citationsarXiv
Omnivore: A Single Model for Many Visual Modalities2201.08377v2 · Rohit Girdhar, Mannat Singh, Nikhila Ravi et al.2022 · 206 citationsarXiv
Detecting Twenty-thousand Classes using Image-level Supervision2201.02605v3 · Xingyi Zhou, Rohit Girdhar, Armand Joulin et al.2022 · 563 citationsarXiv
Augmenting Convolutional networks with attention-based aggregation2112.13692v1 · Hugo Touvron, Matthieu Cord, Alaaeldin El-Nouby et al.2021 · 31 citationsarXiv
Unsupervised Dense Information Retrieval with Contrastive Learning2112.09118v4 · Gautier Izacard, Mathilde Caron, Lucas Hosseini et al.2021 · 172 citationsarXiv
Learning Co-segmentation by Segment Swapping for Retrieval and Discovery2110.15904v2 · Xi Shen, Alexei A. Efros, Armand Joulin et al.2021 · 16 citationsarXiv
An End-to-End Transformer Model for 3D Object Detection2109.08141v1 · Ishan Misra, Rohit Girdhar, Armand Joulin2021 · 502 citationsarXiv
XCiT: Cross-Covariance Image Transformers2106.09681v2 · Alaaeldin El-Nouby, Hugo Touvron, Mathilde Caron et al.2021 · 369 citationsarXiv
Emerging Properties in Self-Supervised Vision Transformers2104.14294v2 · Mathilde Caron, Hugo Touvron, Ishan Misra et al.2021 · 5,874 citationsarXiv
Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples2104.13963v3 · Mahmoud Assran, Mathilde Caron, Ishan Misra et al.2021 · 98 citationsICCV 2021
LeViT: a Vision Transformer in ConvNet's Clothing for Faster Inference2104.01136v2 · Ben Graham, Alaaeldin El-Nouby, Hugo Touvron et al.2021 · 981 citationsarXiv
Self-supervised Pretraining of Visual Features in the Wild2103.01988v2 · Priya Goyal, Mathilde Caron, Benjamin Lefaudeux et al.2021 · 141 citationsarXiv
Self-Supervised Pretraining of 3D Features on any Point-Cloud2101.02691v1 · Zaiwei Zhang, Rohit Girdhar, Armand Joulin et al.2021 · 283 citationsarXiv
Beyond English-Centric Multilingual Machine Translation2010.11125v1 · Angela Fan, Shruti Bhosale, Holger Schwenk et al.2020 · 494 citationsarXiv
Target Conditioning for One-to-Many Generation2009.09758v1 · Marie-Anne Lachaux, Armand Joulin, Guillaume Lample2020 · 9 citationsarXiv
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments2006.09882v5 · Mathilde Caron, Ishan Misra, Julien Mairal et al.2020 · 2,499 citationsarXiv
Training with Quantization Noise for Extreme Model Compression2004.07320v3 · Angela Fan, Pierre Stock, Benjamin Graham et al.2020 · 145 citationsarXiv
Learning to Visually Navigate in Photorealistic Environments Without any Supervision2004.04954v1 · Lina Mezghani, Sainbayar Sukhbaatar, Arthur Szlam et al.2020 · 11 citationsarXiv
Addressing Some Limitations of Transformers with Feedback Memory2002.09402v3 · Angela Fan, Thibaut Lavril, Edouard Grave et al.2020 · 29 citationsarXiv
Unsupervised pretraining transfers well across languages2002.02848v1 · Morgane Riviere, Armand Joulin, Pierre-Emmanuel Mazar'e et al.2020 · 186 citationsICASSP 2020
Pruning Convolutional Neural Networks with Self-Supervision2001.03554v1 · Mathilde Caron, Ari Morcos, Piotr Bojanowski et al.2020 · 30 citationsarXiv
Libri-Light: A Benchmark for ASR with Limited or No Supervision1912.07875v1 · Jacob Kahn, Morgane Riviere, Weiyi Zheng et al.2019 · 479 citationsarXiv
CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB1911.04944v2 · Holger Schwenk, Guillaume Wenzek, Sergey Edunov et al.2019 · 152 citationsarXiv
CCNet: Extracting High Quality Monolingual Datasets from Web Crawl Data1911.00359v2 · Guillaume Wenzek, Marie-Anne Lachaux, Alexis Conneau et al.2019 · 303 citationsarXiv
Career total: 127 works. 88 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.