Publications

Improving Diversity in Language Models: When Temperature Fails, Change the Loss
Alexandre Vérine, Florian Le Bronnec, Kunhao Zheng, Alexandre Allauzen, Yann Chevaleyre, Benjamin Negrevergne
PDF Cite OpenReview Google Scholar
Improving Diversity in Language Models: When Temperature Fails, Change the Loss
Alexandre Vérine, Ahmed Mehdi Inane, Florian Le Bronnec, Benjamin Negrevergne, Yann Chevaleyre
PDF Cite ArXiv Google Scholar
Quality and Diversity in Generative Models through the lens of f-divergences
Alexandre Vérine
PDF Cite HAL Google Scholar
Exploring Precision and Recall to assess the quality and diversity of LLMs
Alexandre Vérine, Florian Le Bronnec, Benjamin Negrevergne, Yann Chevaleyre, Alexandre Allauzen
PDF Cite arXiv Google Scholar
Optimal Budgeted Rejection Sampling for Generative Models
Alexandre Vérine, Muni Sreenivas Pydi, Benjamin Negrevergne, Yann Chevaleyre
PDF Cite arXiv Google Scholar
Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows
Alexandre Vérine, Benjamin Negrevergne, Muni Sreenivas Pydi, Yann Chevaleyre
PDF Cite arXiv Google Scholar
On the expressivity of bi-Lipschitz normalizing flows
Alexandre Vérine, Benjamin Negrevergne, Fabrice Rossi, Yann Chevaleyre
PDF Cite arXiv Google Scholar