SOURCE-LINKED INTELLIGENCE

Watermarkable Multi-Draft Speculative Sampling via Poisson Processes

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Large language models (LLMs) have achieved state-of-the-art performance across a wide range of tasks, motivating two important aspects of deployment: inference efficiency and output provenance, which can be tackled by speculative sampling and watermarking, respectively. However, recent works have shown that combining these two goals is highly nontrivial and can be potentially impossible. In this work, we develop a novel multi-draft speculative sampling algorithm based on Poisson processes that improves the frontier of this fundamental trade-off. The proposed algorithm has strong sampling effic

Read original source ↗ Open in workspace

recordType

paper

region

Global