Showing cs.CVShow all
2 papers · 1 filter
cs.CV2025
MAGI-1: Autoregressive Video Generation at Scale
Sand. ai, Hansi Teng, Hongyu Jia +36
We present MAGI-1, a world model that generates videos by autoregressively predicting a sequence of video chunks, defined as fixed-length segments of consecutive frames. Trained to…
cs.CV2024
BA-Net: Bridge Attention in Deep Neural Networks
Ronghui Zhang, Runzong Zou, Yue Zhao +5
Attention mechanisms, particularly channel attention, have become highly influential in numerous computer vision tasks. Despite their effectiveness, many existing methods primarily…