Wanyun Cui

Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs

2025

Recent advances in Large Language Models (LLMs) have highlighted the critical importance of extending context length, yet the quadratic complexity of attention mechanisms poses significant challenges for efficient long-context modeling. KV cache compression has emerged …

KBQA

2017 · Proceedings of the VLDB Endowment

Question answering (QA) has become a popular way for humans to access billion-scale knowledge bases. Unlike web search, QA over a knowledge base gives out accurate and concise results, provided that natural language questions can …