Phillip Howard
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
NLP×1AI×1
Frequent co-authors
Research Timeline
2026
Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding
The paper introduces Hybrid Verified Decoding, a method that predicts the acceptance length of a cache draft to intelligently select between cache verification and model-based drafting, achieving significant speedups, especially in agentic workflows.
Highlighted terms show continued research focus across papers
Papers
cs.CLcs.AIRecentMay 31, 2026
Hybrid Verified Decoding: Learning to Allocate Verification in Speculative Decoding
Xin Su, Dawid Majchrowski, Fangyuan Yu, Vanshil Atul Shah +4 more
The paper introduces Hybrid Verified Decoding, a method that predicts the acceptance length of a cache draft to intelligently select between cache verification and model-based drafting, achieving sign…
View →