AdaPLD adaptively mixes lexical and semantic retrieval with branched reuse to improve model-free speculative decoding and reports up to 3.10x speedup across benchmarks.
SAM Decoding: Speculative Decoding via Suffix Automaton
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AdaPLD: Adaptive Retrieval and Reuse for Efficient Model-Free Speculative Decoding
AdaPLD adaptively mixes lexical and semantic retrieval with branched reuse to improve model-free speculative decoding and reports up to 3.10x speedup across benchmarks.