Xinye Zhao

Xinye Zhao

Ph.D. student in Computer Science and Engineering at the University of Notre Dame, with research interests in AI for Software Engineering (AI4SE), Software Engineering Security, and Systems for Machine Learning.

SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching

Published in IJCNLP 2025, 2025

Semantic-aware KV cache sharing framework for reducing LLM inference cost across semantically similar prompts.

Recommended citation: Xinye Zhao and Spyridon Mastorakis. (2025). "SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching." arXiv / IJCNLP 2025.
Download Paper