Tom Dupre la Tour — accepted AI-conference papers

2026

Persona Features Control Emergent Misalignment

Miles Wang, Tom Dupre la Tour, Olivia Watkins, Aleksandar Makelov, Ryan Andrew Chi, Samuel Miserendino +5

ICLR 2026poster

Understanding how language models generalize behaviors from their training to a broader deployment distribution is an important problem in AI safety. Betley et al. discovered that fine-tuning GPT-4o on intentionally insecure code causes "emergent misalignment," where models give stereotypically mali…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Scaling and evaluating sparse autoencoders

Leo Gao, Tom Dupre la Tour, Henk Tillman, Gabriel Goh, Rajan Troll, Alec Radford +3

ICLR 2025oral

Sparse autoencoders provide a promising unsupervised approach for extracting interpretable features from a language model by reconstructing activations from a sparse bottleneck layer. Since language models learn many concepts, autoencoders need to be very large to recover all relevant features. Howe…

Cited by 138 Source ↗PDF ↗code ↗Scholar ↗

2022

Benchopt: Reproducible, efficient and collaborative optimization benchmarks

Thomas Moreau, Mathurin Massias, Alexandre Gramfort, Pierre Ablin, Pierre-Antoine Bannier, Benjamin Charlier +15

NeurIPS 2022accept

Numerical validation is at the core of machine learning research as it allows us to assess the actual impact of new methods, and to confirm the agreement between theory and practice. Yet, the rapid development of the field poses several challenges: researchers are confronted with a profusion of meth…

Cited by 46 Source ↗PDF ↗code ↗Scholar ↗