Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video Diffusion
Hidir Yesiltepe, Jiazhen Hu, Tuna Han Salih Meral +4
Long-rollout causal video diffusion has converged on a fixed-size sliding-window KV cache, with recent progress innovating within this layout by changing which tokens occupy the wi…
cs.CV2025
VideoAVE: A Multi-Attribute Video-to-Text Attribute Value Extraction Dataset and Benchmark Models
Ming Cheng, Tong Wu, Jiazhen Hu +2
Attribute Value Extraction (AVE) is important for structuring product information in e-commerce. However, existing AVE datasets are primarily limited to text-to-text or image-to-te…