JIANG, Zhonghua; CHEN, Kui; LI, Kunxi; YIN, Keting; ZHOU, Yiyun; WANG, Zhaode; LV, Chengfei; ZHANG, Shengyu. AccKV: Towards Efficient Audio-Video LLMs Inference via Adaptive-Focusing and Cross-Calibration KV Cache Optimization. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 7, p. 5494–5502, 2026. DOI: 10.1609/aaai.v40i7.37467. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/37467. Acesso em: 12 may. 2026.