Post-Trained MoE Can Skip Half Experts via Self-Distillation Paper • 2605.18643 • Published 12 days ago • 30
Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models Paper • 2511.08577 • Published Nov 11, 2025 • 110
R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing Paper • 2505.21600 • Published May 27, 2025 • 71