ME reinterprets LLM ensembling as token-level sampling from a mixture model, enabling single-model invocation per token with claimed mathematical equivalence to full ensembling and measured speedups of 1.78x-2.68x.
Exact byte-level probabilities from tokenized 9 Rethinking LLM Ensembling from the Perspective of Mixture Models language models for fim-tasks and model ensembles
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
No citing papers match the current filters.