arXivHidir Yesiltepe, Jiazhen Hu, Tuna Han Salih Meral, Adil Kaan Akan, Kaan Oktay, Hoda Eldardiry, Pinar YanardagThu, May 28, 2026, 10:59 AM PDT
score 14.8
Low-rank compression cuts video AI model memory by 93 percent
Original: VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
Source: arxiv.org ↗
Writing ELI5 summary…