Articles

Sebag I., Pydi M., Franceschi J-Y., Rakotomamonjy A., Gartrell M., Atif J., Allauzen A. (2025), Differentially Private Gradient Flow based on the Sliced Wasserstein Distance, Transactions on machine learning research, p. 1-25

Noto D., Allauzen A., Chibbaro S. (2024), An efficient training method to learn a model of turbulence, The European Physical Journal Plus, vol. 139, n°3

DELATTRE B., ARAUJO A., Barthélemy Q., Allauzen A. (2024), The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing, International Conference on Learning Representations (ICLR)

Parcollet T., Nguyen H., Evain S., Boito M., Pupier A., Mdhaffar S., Le H., Alisamir S., Tomashenko N., Dinarelli M., Zhang S., Allauzen A., Coavoux M., Estève Y., Rouvier M., Goulian J., Lecouteux B., Portet F., Rossato S., Ringeval F., Schwab D., Besacier L. (2024), LeBenchmark 2.0: A standardized, replicable and enhanced framework for self-supervised representations of French speech, Computer Speech & Language, vol. 86, p. 101622

Cvetkov-Iliev A., Allauzen A., Varoquaux G. (2023), Relational Data Embeddings for Feature Enrichment with Background Information, Machine Learning, vol. 112, p. 687-720

Bucci M., Semeraro O., Allauzen A., Wisniewski G., Cordier L., Mathelin L. (2019), Control of chaotic systems by deep reinforcement learning, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, vol. 475, n°2231, p. 20190351

Costa-jussà M., Allauzen A., Barrault L., Cho K., Schwenk H. (2017), Introduction to the special issue on deep learning approaches for machine translation, Computer Speech & Language, vol. 46, p. 367-373

Communications avec actes

Herron F., Rossato S., Allauzen A., Favre B., Portet F. (2026), Speaker Group Encoding in Self-supervised Speech Recognition Models, in Kamil Ekštein, Miloslav Konopík, Ondřej Pražák, František Pártl, Text, Speech, and Dialogue, Springer Nature Switzerland, 121-132 p.

DELATTRE B., CAILLON P., Barthélemy Q., Fagnou E., Allauzen A. (2025), Bridging the Theoretical Gap in Randomized Smoothing, in , Proceedings of Machine Learning Research (PMLR)

Fagnou E., CAILLON P., DELATTRE B., Allauzen A. (2025), Accelerated Training through Iterative Gradient Propagation Along the Residual Path, in , ICRL

Duong S., Le Bronnec F., Allauzen A., Guigue V., Lumbreras A., Soulier L., Gallinari P. (2025), Scope : a self-supervised framework for improving faithfulness in conditional text generation, in , OpenReview

Fagnou E., CAILLON P., Allauzen A. (2024), Chain and Causal Attention for Efficient Entity Tracking, in Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen, Association for Computational Linguistics, 13174–13188 p.

Le Bronnec F., VERINE A., Negrevergne B., Chevaleyre Y., Allauzen A. (2024), Exploring Precision and Recall to assess the quality and diversity of LLMs, in Lun-Wei Ku, Andre Martins, Vivek Srikumar, Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL Anthology, 11418-11441 p.

Araújo A., Barthélemy Q., Allauzen A. (2024), The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing, in , OpenReview, 25 p.

Le Bronnec F., Duong S., Allauzen A., Guigue V., Lumbreras A., Soulier L., Gallinari P. (2024), LOCOST: Modèles Espace-État pour le Résumé Abstractif de Documents Longs, in Mathieu Balaguer ; Nihed Bendahman ; Lydia-Mai Ho-dac ; Julie Mauclair ; Jose G Moreno ; Julien Pinquier, Association pour le Traitement Automatique des Langues (ATALA)

Le Bronnec F., Duong S., Ravaut M., Allauzen A., Chen N., Guigue V., Lumbreras A., Soulier L., Gallinari P. (2024), LOCOST: State-Space Models for Long Document Abstractive Summarization, in Yvette Graham ; Matthew Purver, elsevier, Association for Computational Linguistics, 1144–1159 p.

Piat G., Semmar N., Tourille J., Allauzen A., Essafi H. (2023), What does KnowBert-UMLS forget?, in , 2023 20th ACS/IEEE International Conference on Computer Systems and Applications (AICCSA), IEEE - Institute of Electrical and Electronics Engineers, 1-8 p.

Piat G., Kirby E., Tourille J., Semmar N., Allauzen A., Essafi H. (2023), Intégration de connaissances structurées par synthèse de texte spécialisé, in Christophe Servan ; Anne Vilnat, Association pour le Traitement Automatique des Langues (ATALA), 275-284 p.

Piat G., Semmar N., Allauzen A., Essafi H., Tourille J. (2022), Enriching Contextualized Representations with Biomedical Ontologies: Extending KnowBert to UMLS, in Kohei Arai, Intelligent Computing, Springer International Publishing, 760-773 p.

Piat G., Allauzen A., Essafi H., Bernard G., Tourille J., Semmar N. (2022), Adapting without forgetting: KnowBert-UMLS, in , elsevier, Piscataway, NJ, IEEE - Institute of Electrical and Electronics Engineers, 19-24 p.

Communications sans actes

Semeraro O., Bucci M., Hosseinkhan-Boucher R., Chibbaro S., Allauzen A., Mathelin L. (2025), On the use of entropy-based metrics for data-driven modeling and reinforcement learning control, oint event Euromech Colloquium on Data-Driven Fluid Dynamics/2nd ERCOFTAC Workshop on Machine Learning for Fluid Dynamics, Londres, Royaume-Uni

Semeraro O., Bucci M., Allauzen A., Chibbaro S., Mathelin L. (2023), Curriculum learning for data-driven modeling of dynamical systems, XLIII Dynamics Days Europe 2023, Naples, Italie

Evain S., Nguyen M., Le H., Zanon Boito M., Mdhaffar S., Alisamir S., Tong Z., Tomashenko N., Dinarelli ., Parcollet T., Allauzen A. (2021), Task Agnostic and Task Specific Self-Supervised Learning from Speech with LeBenchmark, Thirty-fifth Conference on Neural Information Processing Systems (NeurIPS 2021), États-Unis

Evain S., Nguyen H., Le H., Zanon Boito M., Mdhaffar S., Alisamir S., Tong ., Tomashenko N., Dinarelli M., Parcollet T., Allauzen A. (2021), LeBenchmark: A Reproducible Framework for Assessing Self-Supervised Representation Learning from Speech, NTERSPEECH 2021: Conference of the International Speech Communication Association, Brno, Tchèque, rÉpublique

Prépublications / Cahiers de recherche

Sebag I., Franceschi J-Y., Rakotomamonjy A., Allauzen A., Atif J. (2025), On the MIA Vulnerability Gap Between Private GANs and Diffusion Models, Paris, Preprint Lamsade

Verine A., Le Bronnec F., Zheng K., Allauzen A., Chevaleyre Y., Negrevergne B. (2025), Improving Diversity in Language Models: When Temperature Fails, Change the Loss, Paris, Preprint Lamsade

Bucci M., Semeraro O., Allauzen A., Chibbaro S., Mathelin L. (2021), Leveraging the structure of dynamical systems for data-driven modeling, Paris, Preprint Lamsade