Scholar
Benjamin Negrevergne
Google Scholar ID: kXkSpn4AAAAJ
Unversité PSL -- Paris Dauphine
Citations & Impact
Citations
558
H-index
12
i10-index
15
Publications
20
Co-authors
0
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- Publications:
- 1. Improving Diversity in Language Models: When Temperature Fails, Change the Loss (ICML, 2025)
- 2. Lattice Climber Attack: Adversarial attacks for randomized mixtures of classifiers (ECML, 2025)
- 3. Improving Discriminator Guidance in Diffusion Models (ECML, 2025)
- 4. What Makes Large Language Models Reason in (Multi-Turn) Code Generation? (ICLR, 2025)
- 5. Unveiling the Role of Randomization in Multiclass Adversarial Classification: Insights from Graph Theory (AIStats, 2025)
- 6. Exploring Precision and Recall to assess the quality and diversity of LLMs (ACL, 2024)
- 7. Optimal Budgeted Rejection Sampling for Generative Models (AIStats, 2024)
- 8. Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows (NeurIPS, 2023)
- 9. On the Role of Randomization in Adversarially Robust Classification (NeurIPS, 2023)
- 10. On the expressivity of normalizing flows (Asian Conference on Machine Learning, 2022)
- 11. Deep Policy Learning for Perfect Rectangle Packing (PRL@IJCAI, 2021)
- 12. Deep Reinforcement Learning for Morpion Solitaire (ICGA, 2021)
- 13. On the expressivity of bi-Lipschitz normalizing flows (arXiv preprint arXiv:2107.07232, 2021)
Research Experience
- Past or current Ph.D. students include:
- - Alexandre Araujo (defended), with Jamal Atif, CIFRE with Wavestone, currently postdoc at NYU.
- - Boris Doux (defended), with Tristan Cazenanve, currently Software Engineer AWS, Dallas Texas.
- - Alexandre Vérine, with Yann Chevaleyre, École Normale scholarship.
- - Lucas Gnecco, with Yann Chevaleyre, ANR project DELCO.
- - Kunhao Zheng, with Gabriel Synnaeve and Yann Chevaleyre, CDDP META/FAIR.
Background
- Associate professor at the Lamsade laboratory from PSL – Paris Dauphine university, in Paris. Co-leader of the MILES research team, with a focus on Machine Learning. Also co-director of the IASD Master Program (AI and Data Science) with Olivier Cappé, and partially in charge of the computer science graduate program of PSL. Currently launching Nautia, a startup project aiming to use reinforcement learning to steer large racing sailboats.
Miscellany
- Contact Information:
- - E-mail: {firstname.lastname} @ psl.dauphine.eu
- - Mailing Address: LAMSADE, Place du Maréchal de Lattre de Tassigny, 75 775 PARIS CEDEX 16, FRANCE
- - Office: P407
- - Tel: +33 1 44 05 44 18
Co-authors