#machine learning
Sep 2026
Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation
This work instantiates VDN on MiniMax H3, which combines local Softmax attention with bidirectional linear memory for long-range video context and introduces Video Delta Attention (VDA), which updates memory once per frame by jointly incorporating its spatial tokens.
Hao-Cheng Xi, Yiming Xie, He-Xue Zhao et al.
· arXiv.org · 4 citations