Arbitrage: Efficient Reasoning via Advantage-Aware Speculation Paper • 2512.05033 • Published about 1 month ago • 15
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders Paper • 2510.19779 • Published Oct 22, 2025 • 60
The Art of Scaling Reinforcement Learning Compute for LLMs Paper • 2510.13786 • Published Oct 15, 2025 • 31
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization Paper • 2508.10395 • Published Aug 14, 2025 • 42