[1]
Fan, X., Sun, Z., Ji, T., Shen, L. and Gui, T. 2026. MHA2MLA-VLM: Enabling DeepSeek’s Economical Multi-Head Latent Attention Across Vision-Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 36 (Mar. 2026), 30638-30646. DOI:https://doi.org/10.1609/aaai.v40i36.40319.