Publications – Miles

Constant Bourdrez, Alexandre Verine, Olivier Cappé. Learning To Sample From Diffusion Models Via Inverse Reinforcement Learning. 2026. ⟨hal-05523140⟩
Minh Tri Lê, Pierre Wolinski, Julyan Arbel. Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Review. ACM Transactions on Intelligent Systems and Technology, In press, ⟨10.1145/3798276⟩. ⟨hal-04296440v2⟩
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⟩
Paul Caillon, Alex Colagrande, Erwan Fagnou, Blaise Delattre, Alexandre Allauzen. Forward Only Learning for Orthogonal Neural Networks of Any Depth. 28th European Conference on Artificial Intelligence, Oct 2025, Bologne, Italy. ⟨10.3233/FAIA251041⟩. ⟨hal-05528951⟩
Denis Cornaz, Sébastien Kerleau, Clément Royer. A characterization of positive spanning sets with ties to strongly edge-connected digraphs. Discrete Applied Mathematics, 2025, 374, pp.105-119. ⟨10.1016/j.dam.2025.05.025⟩. ⟨hal-05235650⟩
Lucas Gnecco, Benjamin Negrevergne, Yann Chevaleyre. Lattice Climber Attack: Adversarial attacks for randomized mixtures of classifiers. Proceedings of ECML PKDD 2025, Sep 2025, Porto, Portugal. ⟨hal-05089941v3⟩
Alexandre Vérine, Inane Ahmed Mehdi, Florian Le Bronnec, Benjamin Negrevergne, Yann Chevaleyre. Improving Discriminator Guidance in Diffusion Models. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Sep 2025, Porto, Portugal. ⟨hal-05416219⟩
Pierre Wolinski. Gathering and Exploiting Higher-Order Information when Training Large Structured Models. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, Sep 2025, Porto, Portugal. pp.436-452, ⟨10.1007/978-3-032-06078-5_25⟩. ⟨hal-05178426⟩
Ilana Sebag, Jean-Yves Franceschi, Alain Rakotomamonjy, Alexandre Allauzen, Jamal Atif. On the MIA Vulnerability Gap Between Private GANs and Diffusion Models. 2025. ⟨hal-05236329⟩
Yunzhen Feng, Ariel Kwiatkowski, Kunhao Zheng, Julia Kempe, Yaqi Duan. PILAF: Optimal Human Preference Sampling for Reward Modeling. Forty-Second International Conference on Machine Learning. ICML 2025., Jul 2025, Vancoucer, Canada. pp.16744-16776, ⟨10.48550/arXiv.2502.04270⟩. ⟨hal-05429131⟩