Lausanne, Switzerland
Arthur Renard
Founding engineer and ML researcher at Xent Labs, building games and evaluations for language models.
Selected work
View all →- Cross-Entropy Games and Frost TrainingPreprint, 2026
A method that uses reward gradients in embedding space to accelerate GRPO training on Cross-Entropy Games.
- Cognitive Training for Language ModelsPreprint, 2026
A principled framework for relevant skill discovery in language models via Cross-Entropy Games.
- BoolformerAI for Math Workshop, ICML 2025
A Transformer model for symbolic regression of Boolean functions, presented at the AI for Math Workshop at ICML 2025.