SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification 事件

SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification arXiv:2510.02329v2 Announce Type: replace Abstract: Speculative decoding accelerates LLM inference by verifying candidate tokens from a draft model against a larger target model. Recent judge decoding boosts this process by relaxing verification criteria by accepting draft tokens that may exhibit minor discrepancies from target model output, but existing methods are restricted by their reliance on human annotations or