SOURCE-LINKED INTELLIGENCE

Accelerating Diffusion Sampling via Speculative Draft Trees

arXiv · AI, language, vision and robotics · article · Sep 15, 2026 · UTC

Speculative sampling accelerates diffusion model generation by drafting inexpensive candidate states and correcting them under a coupling that preserves the target distribution exactly, reducing the number of expensive target evaluations. Existing diffusion samplers, notably those based on reflection maximal coupling, are topologically constrained: their lookahead drafts form a chain graph, a single linear sequence, which inherently limits the acceptance rate per target evaluation. We connect speculative sampling in diffusion models to relative entropy coding (REC). This perspective shows the

Read original source ↗ Open in workspace

recordType

paper

region

Global