112 documents
- Vicky Kouni, Stelios Perrakis, Francis Bach, Pascal Frossard, Yann Chevaleyre. Frame the adversary: a structure-aware attack methodology. NeurIPS 2026 - 40th Conference on Neural Information Processing System, Dec 2026, Paris, France. ⟨hal-05790109⟩
- Paul Caillon, Christophe Cerisara, Alexandre Allauzen. Across the Loss Landscape with Progressive Growth. European Conference on Machine Learning (ECML-PKDD) 2026, Sep 2026, Naples, Italy. pp.598-615, ⟨10.1007/978-3-032-37667-1_34⟩. ⟨hal-05777870⟩
- Anne Morvan, Antoine Souloumiac, Krzysztof Choromanski, Cédric Gouy-Pailler, Jamal Atif. On the Needs for Rotations in Hypercubic Quantization Hashing. 2026. ⟨cea-05693589⟩
- Erwan Fagnou, Paul Caillon, Blaise Delattre, Alexandre Allauzen. Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing. Forty-third International Conference on Machine Learning, Jul 2026, Seoul, South Korea. ⟨hal-05754606⟩
- Minh Tri Lê, Pierre Wolinski, Julyan Arbel. Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review. ACM Transactions on Intelligent Systems and Technology, 2026, 17 (4), pp.1-41. ⟨10.1145/3798276⟩. ⟨hal-04296440v2⟩
- Alex Colagrande, Paul Caillon, Eva Feillet, Alexandre Allauzen. Limits of Resolution Equivariance in Fourier Neural Operators. AI&PDE: ICLR 2026 Workshop on AI and Partial Differential Equations, Apr 2026, Rio de Janeiro, Brazil. arXiv, 2026, ⟨10.48550/arXiv.2606.00677⟩. ⟨hal-05742295⟩
- Eva Feillet, Ryan Whetten, David Picard, Alexandre Allauzen. POLYNOMIAL MIXING FOR EFFICIENT SELF-SUPERVISED SPEECH ENCODERS. 2026. ⟨hal-05589762⟩
- Constant Bourdrez, Alexandre Verine, Olivier Cappé. Learning To Sample From Diffusion Models Via Inverse Reinforcement Learning. 2026. ⟨hal-05523140v2⟩
- Romaric Audigier, Patrick Bas, Jan Butora, Emma Coletta, Christophe Charrier, et al.. Projet COMPROMIS WP 2: Research activities in Integrity. 2026. ⟨hal-05600611⟩
- Alexandre Verine, Florian Le Bronnec, Kunhao Zheng, Alexandre Allauzen, Yann Chevaleyre, et al.. Improving Diversity in Language Models: When Temperature Fails, Change the Loss. 2025. ⟨hal-05413727⟩
Documents récupérés de l'archive ouverte HAL 