On the Generalization Limitation of On-Policy Distillation for Post-RL Consolidation Paper • 2611.05609 • Published 6 days ago • 25
Why Can't Transformers Learn Multiplication? Reverse-Engineering Reveals Long-Range Dependency Pitfalls Paper • 2510.00184 • Published Sep 30, 2025 • 17
Concept Incongruence: An Exploration of Time and Death in Role Playing Paper • 2505.14905 • Published May 20, 2025 • 2