Papers by Fuwei Yang

1 papers
Jakiro: Boosting Speculative Decoding via Decoupled MoE (2026.acl-long)

Copied to clipboard

Challenge: Existing methods to accelerate large language model inference have a fundamental limitation: candidates at the same tree layer share identical feature representations, constraining diversity and diminishing overall effectiveness.
Approach: They propose a decoupled mixture of experts (MoE) into a draft model to generate diverse tokens from distinct feature spaces.
Outcome: The proposed approach achieves significant speedups over strong baselines, with notable improvements in non-greedy scenarios where token diversity is crucial.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations