DARTree constructs speculative draft trees with batched autoregressive correction across branches and deferred pruning, reporting the highest acceptance length and speedup among diffusion-based drafters tested.
InProceedings of the 2025 Conference of the NationsoftheAmericasChapteroftheAssociationforCom- putationalLinguistics:HumanLanguageTechnologies(Vol- ume 1: Long Papers), 12042–12059
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DARTree: Speculative Diffusion Decoding with Autoregressive Draft Trees
DARTree constructs speculative draft trees with batched autoregressive correction across branches and deferred pruning, reporting the highest acceptance length and speedup among diffusion-based drafters tested.