BlockPilot: Instance-Adaptive Policy Learning for Diffusion-based Speculative Decoding
Speculative decoding accelerates inference by using a lightweight draft model to generate candidate tokens in parallel, and are then verified by the target model, enabling lossless acceleration. Recently, diffusion-based speculative decoding further improves parallelism by generating multiple tokens per forward pass via block-level diffusion, achieving state-of-the-art (SOTA) performance. However, existing methods adopt a fixed inference block size and assume a uniform optimal decoding strategy across all inputs. In this paper, we show that this assumption is suboptimal, as the optimal block s
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via unknownDSpark: Speculative decoding accelerates LLM inference [pdf] →
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-xl-base-1.0 →
“Fuzzy title match (0.73): “BlockPilot: Instance-Adaptive Policy Learning for Diffusion-” ≈ “stabilityai/stable-diffusion-xl-base-1.0””
- FuzzySimilar title/name (fuzzy) · 59%CompVis/stable-diffusion-v1-4 →
“Fuzzy title match (0.73): “BlockPilot: Instance-Adaptive Policy Learning for Diffusion-” ≈ “CompVis/stable-diffusion-v1-4””
- FuzzySimilar title/name (fuzzy) · 59%stabilityai/stable-diffusion-3.5-large →
“Fuzzy title match (0.73): “BlockPilot: Instance-Adaptive Policy Learning for Diffusion-” ≈ “stabilityai/stable-diffusion-3.5-large””
- PossiblePossibly related (embedding) · 53%sgl-project/SpecForge →
- PossiblePossibly related (embedding) · 61%lightseekorg/TorchSpec →
- FuzzySimilar title/name (fuzzy) · 59%aymericdamien/TopDeepLearning →
“Fuzzy title match (0.73): “BlockPilot: Instance-Adaptive Policy Learning for Diffusion-” ≈ “aymericdamien/TopDeepLearning””