Zhao, Yunlong, Haoran Wu, and Bo Xu. “Leveraging Attention to Effectively Compress Prompts for Long-Context LLMs”. Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 24 (April 11, 2025): 26048–26056. Accessed May 29, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/34800.