Cite
Notes
Only stored in your browser.
Attribution
MiniCPM4: Ultra-Efficient LLMs on End Devices
arXiv 2025
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling
Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding
arXiv 2024
from 3 papers
Maosong Sun
professor
Weilin Zhao
Xu Han
Yuxiang Huang
Zhiyuan Liu
Ao Sun
Chaojun Xiao
Weilun Zhao
Yewei Fang
Yudi Zhang