Mufei Li (李牧非)'s Homepage
  • About
  • Publications
  • CV

Announcement_2025 06 12

June 12, 2025

2025

Check our new paper on better leveraging the LLM KV cache for modeling multi-doc interdependencies, Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models, led by Haoyu!

© Copyright 2025 Mufei Li. Powered by Jekyll with al-folio theme. Hosted by GitHub Pages. Photos from Unsplash. Last updated: June 13, 2025.