Arbitrage: Efficient Reasoning via Advantage-Aware Speculation Paper • 2512.05033 • Published Dec 4, 2025 • 17
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders Paper • 2510.19779 • Published Oct 22, 2025 • 62
XQuant: Breaking the Memory Wall for LLM Inference with KV Cache Rematerialization Paper • 2508.10395 • Published Aug 14, 2025 • 42
Learning Adaptive Parallel Reasoning with Language Models Paper • 2504.15466 • Published Apr 21, 2025 • 44
