- Hélie Bazin, Anouk Barberousse, François Yvon. A retrospective analysis on the use of LLMs to study infant syntax learning. EMNLP 2026 Main Conference, ACL SIGDAT, Oct 2026, Budapest (Hungary), Hungary. ⟨hal-05757896⟩
- Benedetta Liberatori, Nermin Samet, Paolo Rota, Matthieu Cord, Elisa Ricci, et al.. Spot-the-shift: Evaluating Grounded Image Difference Captioning of Long-term Changes. 2026. ⟨hal-05754597⟩
- Théophane Vallaeys, Jakob Verbeek, Matthieu Cord. SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization. ECCV 2026, Sep 2026, Malmo, Sweden. ⟨hal-05734191⟩
- Erkan Narmanli, Alexandre Lanau, Mara Neacsu, Mariia Koshkina, Pierre Fumeron, et al.. An alignment-last approach enables rapid transcriptomic biomarker discovery in large cohorts. 2026. ⟨hal-05738006⟩
- Nicolas Dahan, Ziqian Peng, François Yvon, Rachel Bawden. Improving Term Evaluation in Machine Translation: Variation Matters. AMTA 2026 - 17th Conference of the Association for Machine Translation in the Americas, Aug 2026, Quebec City, Canada. ⟨hal-05713582⟩
- Danyal Ahmed, Edouard Oyallon. Know What You Need: Efficient Activation Checkpointing. 2026. ⟨hal-05708820⟩
- Ben Kabongo, Arthur Satouf, Vincent Guigue. Rank, Don't Generate: Statement-level Ranking for Explainable Recommendation. Proceedings of the 2026 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR), 2026, pp.159 - 170. ⟨10.1145/3805713.3820414⟩. ⟨hal-05669752⟩
-
Yash Kankanampati, Yuxuan Zong, Nadi Tomeh, Benjamin Piwowarski, Joseph Le Roux. A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models. SIGIR '26: The 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2026, Melbourne, Australia. pp.756-766, ⟨10.1145/3805712.3809726⟩. ⟨hal-05704944⟩
[ HTTP ]
- Mihai Branga-Peicu, Mathias Vast, Basile van Cooten, Laure Soulier, Jules Françoise, et al.. IR Lens: A Tool for Interpreting Cross-Encoder Models. SIGIR'26 - 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2026, Melbourne, Australia. pp.5135-5139, ⟨10.1145/3805712.3808382⟩. ⟨hal-05690304⟩
- Yuxuan Zong, Mathias Vast, Basile van Cooten, Laure Soulier, Benjamin Piwowarski. From Tokens to Concepts: Leveraging SAE for SPLADE. Proceedings of the 49th International ACM SIGIR Conference on Research and Development in Information Retrieval, Jul 2026, Melbourne (AUS), Australia. pp.2622-2632, ⟨10.1145/3805712.3809565⟩. ⟨hal-05751792⟩
-
Mohamed Salim Aissi, Clemence Grislain, Clément Romac, Laure Soulier, Mohamed Chetouani, et al.. PRISM: Perception Reasoning Interleaved for Sequential Decision Making. ICML 2026 - 43rd International Conference on Machine Learning, Jul 2026, Seoul, South Korea. ⟨hal-05705337⟩
[ HTTP ]
- Pierre-Antoine Lequeu, Léo Labat, Laurène Cave, Gaël Lejeune, François Yvon, et al.. The GDN-CC Dataset: Automatic Corpus Clarification for AI-enhanced Democratic Citizen Consultations. 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), ACL, Jul 2026, San Diego, CA, United States. pp.32976-33006, ⟨10.18653/v1/2026.acl-long.1523⟩. ⟨hal-05706676⟩
- Victor Morand, Nadi Tomeh, Josiane Mothe, Benjamin Piwowarski. ToMMeR -Efficient Entity Mention Detection from Large Language Models. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Jul 2026, San Diego, France. pp.27489-27509, ⟨10.18653/v1/2026.acl-long.1268⟩. ⟨hal-05709683⟩
- Paul Lerner, François Yvon. Sur l'équité politique des grands modèles de langue multilingues. Conférence sur le Traitement Automatique des Langues Naturelles, ATALA, Jun 2026, Nantes, France. pp.576-594. ⟨hal-05677100⟩
- Ziqian Peng, Lichao Zhu, Maxime Bouthors, François Yvon. Alignement Bilingue des Résumés et des Mots-Clés de theses.fr. Atelier sur l'Analyse et la Recherche de Textes Scientifiques (CORIA-TALN 2026), Jun 2026, Nantes, France. ⟨hal-05680111⟩
- Maxime Bouthors, Josep Crego, Dakun Zhang, François Yvon. Improving Retrieval-Augmented Neural Machine Translation with Monolingual Data. 26th Annual Conference of the European Association for Machine Translation (EAMT), European Association for Machine Translation, Jun 2026, Tilburg, Netherlands. pp.435-454. ⟨hal-05658209⟩
- Panagiotis Tsolakis, Ziqian Peng, Laurent Romary, François Yvon, Rachel Bawden. The MaTOS Pipeline for the Translation of Scientific Abstracts on the HAL Platform. EAMT 2026 - 26th Annual Conference of the European Association for Machine Translation, Jun 2026, Tilburg, Netherlands. pp.104-113. ⟨hal-05662981⟩
- Nicolas Dahan, Rachel Bawden, François Yvon. MetaDocEval: A Contrastive Framework for Evaluating Machine Translation Metrics at the Document-Level. EAMT 2026 - 26th Annual Conference of the European Association for Machine Translation, Jun 2026, Tilburg, Netherlands. pp.268-303. ⟨hal-05663019⟩
- Yihong Xu, Eloi Zablocki, Yuan Yin, Elias Ramzi, Ellington Kirby, et al.. Test-Time Trajectory Optimization for Autonomous Driving. 2026. ⟨hal-05693473⟩
- Fabian Schramm, Pierre Fabre, Nicolas Perrin-Gilbert, Justin Carpentier. Reference-Free Sampling-Based Model Predictive Control. IEEE International Conference on Robotics and Automation (ICRA 2026), Jun 2026, Vienne, Austria. ⟨hal-05401976v3⟩
- Fabian Schramm, Franki Nguimatsia Tiofack, Nicolas Perrin-Gilbert, Marc Toussaint, Justin Carpentier. Variance-Reduced MPPI: Workshop Version. 2026. ⟨hal-05629693⟩
- Franki Nguimatsia Tiofack, Theotime Le Hellard, Fabian Schramm, Nicolas Perrin-Gilbert, Justin Carpentier. Guided Flow Policy: Workshop Version. 2026. ⟨hal-05629700⟩
- Ziqian Peng, Lichao Zhu, Rachel Bawden, Maud Bénard, Éric de la Clergerie, et al.. Parallel Corpora of Scholarly Documents for English-French Machine Translation. BUCC 2026 - 19th Workshop on Building and Using Comparable Corpora, LREC2026, May 2026, Palma de Mallorca, Spain. ⟨hal-05608444v2⟩
- Nazanin Shafiabadi, François Yvon. Biases in Translation: Assessing Opinion Distortion in Machine Translated Texts. LREC 2026, May 2026, Palma, Mallorca, Spain. ⟨hal-05559927⟩
- Jorge Mifsut Benet, Armand Kassaï Koupaï, Ramon Daniel Regueiro-Espino, Nicolas Baskiotis, Patrick Gallinari. Adaptive SDE Interpolants for Calibrated Probabilistic PDE Forecasting. ICLR 2026 workshop AI & PDE, Apr 2026, Rio de Janeiro, Brazil. ⟨hal-05658031⟩
- Franki Nguimatsia Tiofack, Théotime Le Hellard, Fabian Schramm, Nicolas Perrin-Gilbert, Justin Carpentier. Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning. ICLR 2026 - The Fourteenth International Conference on Learning Representations, Apr 2026, Rio de Janeiro, Brazil. ⟨hal-05400311v2⟩
- Sophia Sirko-Galouchenko, Monika Wysoczańska, Andrei Bursuc, Nicolas Thome, Spyros Gidaris. Boosting Visual Instruction Tuning with Self-Supervised Guidance. 2026. ⟨hal-05593841⟩
- Abdullah Al Sefat, Amir Hossein Kargaran, François Yvon, Hinrich Schütze. GlotWeb: Web Indexing for Minority Languages. ACM Web Conference 2026, ACM, Apr 2026, Dubai, United Arab Emirates. pp.8469-8472, ⟨10.1145/3774904.3792887⟩. ⟨hal-05594291⟩
-
Benjamin Thérien, Charles-Étienne Joseph, Boris Knyazev, Edouard Oyallon, Irina Rish, et al.. $μ$LO: Compute-Efficient Meta-Generalization of Learned Optimizers. International Conference on Representation Learning, Apr 2026, Rio de Janeiro, Brazil, France. ⟨hal-05759999⟩
[ HTTP ]
- Léo Labat, Etienne Ollion, François Yvon. Polyglots or Multitudes? Multilingual LLM Answers to Value-laden Multiple-Choice Questions. 19th Conference of the European Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, Mar 2026, Rabat, Morocco. pp.3382-3398, ⟨10.18653/v1/2026.eacl-long.156⟩. ⟨hal-05580862⟩
- Alexandre Combeau, Vincent Guigue, Cristina Manfredotti, Fatiha Saïs, Stéphane Dervaux, et al.. Personalized Sequence Generation in Food Recommender Systems. The 41st ACM/SIGAPP Symposium On Applied Computing, Mar 2026, Thessaloniki, Greece. ⟨10.1145/3748522.3779963⟩. ⟨hal-05609698⟩
-
Arthur Satouf, Yuxuan Zong, Habiboulaye Amadou Boubacar, Pablo Piantanida, Benjamin Piwowarski. QueStER: Query Specification for Generative Keyword-Based Retrieval. Findings of the Association for Computational Linguistics: EACL 2026, ACL, Mar 2026, Rabat, Morocco. pp.5957-5968, ⟨10.18653/v1/2026.findings-eacl.312⟩. ⟨hal-05733394⟩
[ HTTP ]
- François Yvon. Intelligence Artificielle et Grands Modèles de Langage. Mohamed Embarki. La langue française dans le Monde - 2023-2026, Editions Gallimard; Observatoire de la langue française, pp.193-196, 2026, 978-2-07-313049-5. ⟨hal-05718357⟩
- Paul Lerner, François Yvon. Assessing the Political Fairness of Multilingual LLMs: A Case Study based on a 21-way Multiparallel EuroParl Dataset. 2026. ⟨hal-05328251v2⟩
- Killian Bakong, Laurent Massoulié, Edouard Oyallon, Kevin Scaman. Unbiased Approximate Vector-Jacobian Products for Efficient Backpropagation. 2026. ⟨hal-05512493⟩
- Fabian Schramm, Franki Nguimatsia Tiofack, Nicolas Perrin-Gilbert, Marc Toussaint, Justin Carpentier. Variance-Reduced Model Predictive Path Integral via Quadratic Model Approximation. RSS 2026 - Robotics: Science and Systems, Jul 2026, Sydney, Australia. ⟨hal-05492619v2⟩
- Lucas Schott, Elies Gherbi, Hatem Hajri, Sylvain Lamprier. Reward-Preserving Attacks For Robust Reinforcement Learning. 2026. ⟨hal-05461979v2⟩
- Ellington Kirby, Alexandre Boulch, Yihong Xu, Yuan Yin, Gilles Puy, et al.. Driving on Registers. 2026. ⟨hal-05453518⟩
- Ahmed Rayane Kebir, Vincent Guigue, Lynda Said Lhadj, Laure Soulier. RAC: Retrieval-Augmented Clarification for Faithful Conversational Search. European Conference on Information Retrieval (ECIR), Mar 2026, Delft, Netherlands. ⟨10.1007/978-3-032-21289-4_39⟩. ⟨hal-05527527⟩
-
Paul Janson, Edouard Oyallon, Eugene Belilovsky. Stabilizing Native Low-Rank LLM Pretraining. International Conference on Machine Learning, 2026, Seoul, South Korea, France. ⟨hal-05760032⟩
[ HTTP ]
- Mathias Vast, Victor Morand, Basile van Cooten, Laure Soulier, Josiane Mothe, et al.. Encodeurs croisés légers pour ré-ordonner les résultats de recherche d'information. 21e Conférence en Recherche d’Information et Applications, Jun 2026, Nantes, France. pp.19-29. ⟨hal-05690307⟩
- Yuxuan Zong, Mathias Vast, Basile van Cooten, Laure Soulier, Benjamin Piwowarski. Des Tokens aux Concepts: Exploiter les SAE pour SPLADE. 21e Conférence en Recherche d'Information et Applications (CORIA) 19e Rencontres Jeunes Chercheurs en RI (RJCRI) 33e Conférence sur le Traitement Automatique des Langues Naturelles (TALN) 28e Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL), Jun 2026, Nantes, France. pp.30-53. ⟨hal-05708394⟩
- Clémence Grislain, Hamed Rahimi, Olivier Sigaud, Mohamed Chetouani. I-FailSense: Towards General Robotic Failure Detection with Vision-Language Models. IEEE International Conference on Robotics & Automation (ICRA 2026), Jun 2026, Vienne, Austria. ⟨hal-05519469⟩
- Vijini Pilana Liyanage, François Yvon. AdaptBPE: From General Purpose to Specialized Tokenizers. 19th Conference of the European Chapter of the Association for Computational Linguistics, Association for Computational Linguistics, Mar 2026, Rabat, Morocco. pp.2607--2620, ⟨10.18653/v1/2026.eacl-long.119⟩. ⟨hal-05563266⟩
- Ziqian Peng, Lichao Zhu, Maxime Bouthors, François Yvon. Alignement Bilingue des Résumés et des Mots-Clés de these.fr. 21e Conférence en Recherche d'Information et Applications (CORIA) 19e Rencontres Jeunes Chercheurs en RI (RJCRI) 33e Conférence sur le Traitement Automatique des Langues Naturelles (TALN) 28e Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL), Jun 2026, Nantes, France. pp.1-14. ⟨hal-05708483⟩
- Victor Besnier, Anh-Quan Cao, Elias Ramzi, Spyros Gidaris, Tuan-Hung Vu, et al.. How Far Can 5,500 Hours of Driving Take You? A Scaling Law Analysis of Video Diffusion Models. 2026. ⟨hal-05737101⟩
- Raphaël Mouravieff, Tanguy Herserant, Arthur Satouf, Habiboulaye Amadou Boubacar, Pablo Piantanida, et al.. DQE : Génération de données diversifiées par agents pour le question-réponse sur tables. 21e Conférence en Recherche d'Information et Applications (CORIA) 19e Rencontres Jeunes Chercheurs en RI (RJCRI) 33e Conférence sur le Traitement Automatique des Langues Naturelles (TALN) 28e Rencontre des Étudiants Chercheurs en Informatique pour le Traitement Automatique des Langues (RÉCITAL), Jun 2026, Nantes, France. pp.94-106. ⟨hal-05708399⟩
-
Louis Serrano, Jiequn Han, Edouard Oyallon, Shirley Ho, Rudy Morel. Test-time Generalization for Physics through Neural Operator Splitting. International Conference on Machine Learning, 2026, Seoul, South Korea, France. ⟨hal-05760018⟩
[ HTTP ]
- Ben Kabongo, Vincent Guigue. On the Factual Consistency of Text-based Explainable Recommendation Models. 2025. ⟨hal-05438234v2⟩
- Yuan Yin, Shashanka Venkataramanan, Tuan-Hung Vu, Andrei Bursuc, Matthieu Cord. IPA: An Information-Reconstructive Input Projection Framework for Efficient Foundation Model Adaptation. Transactions on Machine Learning Research , 2025. ⟨hal-05735476⟩
