Yang Hu
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
This paper presents MOCAP, a framework that accelerates long-context prefill for large language models on wafer-scale chips.
The paper presents a method to improve the efficiency of industrial large language model labelers by reformulating them as semantic scoring and adapting multiple-item scoring to score hundreds of candidates in one sequence.
Papers
From Generation to Scoring: Scaling LLM-Based Semantic Labeling at LinkedIn
Jian Sheng, Sriram Vasudevan, Sundara Raman Ramachandran, Yang Hu +11 more
The paper presents a method to improve the efficiency of industrial large language model labelers by reformulating them as semantic scoring and adapting multiple-item scoring to score hundreds of cand…