Huan Yang

5

Papers

115

Total Citations

Papers (5)

Zero-Reference Low-Light Enhancement via Physical Quadruple Priors

VISTA: Enhancing Long-Duration and High-Resolution Video Understanding by Video Spatiotemporal Augmentation

Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation

Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers

SEGA: A Stepwise Evolution Paradigm for Content-Aware Layout Generation with Design Prior