SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving Paper • 2609.34117 • Published 11 days ago • 13
Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning Paper • 2606.29985 • Published Jun 29 • 19
Co-training and Co-distillation for Quality Improvement and Compression of Language Models Paper • 2311.02849 • Published Nov 6, 2023 • 7