DepCap accelerates diffusion LM inference up to 5.63x by using last-block influence for adaptive block boundaries and conflict-free token selection for parallel decoding, with negligible quality loss.
DAWN: dependency-aware fast inference for diffusion LLMs.CoRR, abs/2602.06953
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
DepCap: Adaptive Block-Wise Parallel Decoding for Efficient Diffusion LM Inference
DepCap accelerates diffusion LM inference up to 5.63x by using last-block influence for adaptive block boundaries and conflict-free token selection for parallel decoding, with negligible quality loss.