Showing cs.CVShow all
3 papers · 1 filter
cs.CV2026
Just Align : Aligning Predictions, Not Representations
Yuyao Zhang, Yuwei Hu, Ziyang Mai +1
Representation alignment has become an effective way to accelerate diffusion training, but its benefits do not transfer reliably to pixel-space clean-image prediction. In JiT, we f…
cs.CV2026
AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling
Ziyang Mai, Yuyao Zhang, Yu-Wing Tai
Recent diffusion-based video generators have achieved remarkable visual fidelity and prompt controllability, yet scaling them to ultra-high-resolution (UHR) long videos remains pro…
cs.CV2025
ContextAnyone: Context-Aware Diffusion for Character-Consistent Text-to-Video Generation
Ziyang Mai, Yu-Wing Tai
Text-to-video generation has advanced rapidly, yet preserving a character's holistic appearance from a single reference image remains challenging, particularly when the character u…