Qin, Ziran, Youru Lv, Mingbao Lin, Hang Guo, Zeren Zhang, Danping Zou, and Weiyao Lin. “Head-Aware KV Cache Compression for Efficient Visual Autoregressive Modeling”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 30 (March 14, 2026): 24982-24990. Accessed May 4, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/39686.