Jan Kautz

Papers that credit Jan Kautz in their source bylines. Matching names may refer to different researchers.

2 results

1. PaperAI & Agents

   MagicBeanStalk builds training problems from hard seeds

   MagicBeanStalk builds model-calibrated math training problems, improving average test accuracy in reported evaluations.

   Added to Chiosa Oct 14, 2026
2. PaperNLP & Language

   Solo scores often miss which models help a team

   Compositional reinforcement learning improved team performance across tested tasks and also helped in selected held-out settings.

   Added to Chiosa Oct 14, 2026