A novel hierarchical caption encoding mechanism that efficiently injects decoupled hierarchical caption segments into the U-Net's cross-attention layers enables the model to exert hierarchical and decoupled attentional control over the global scene, spatial layout, and geographical element details during the denoising...
Jia-Xin Ren, Wan-Zeng Liu, Feng Zhang et al.· ISPRS Annals of the Photogra...· 0 citations
This work proposes Step-Aware Annealing (SAA), a plug-and-play reward sharpening mechanism that progressively increases reward curvature during training, amplifying subtle quality differences among high-scoring samples while preserving stability in early learning.
Yunhao Wang, Bing-Hong Wu, Zhenyu Huang et al.· 0 citations
Multilingual documents encapsulate rich regional cultures, scientific discoveries, and historical records. Parsing this content into structured, machine-readable formats is critical for unlocking global knowledge. However, existing benchmarks predominantly focus on high-resource languages like English and Chinese, crea...
Long Xu, Binghong Wu, Ting-Ting Yu et al.· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
