arXiv · cs.AI · Yuxin Mao, Zhen Qin, Jinxing Zhou, Hui Deng, Xuyang Shen, Bin Fan, Jing Zhang, Yiran Zhong, Yuchao Dai · 10 小时前模型评分30
LASAD:用空间感知衰减实现线性复杂度自回归图像生成
Autoregressive Image Generation with Linear Complexity: A Spatial-Aware Decay Perspective
导读
研究者提出空间感知衰减线性注意力(LASAD,Linear Attention with Spatial-Aware Decay),按原始二维 token 几何调整衰减,解决光栅扫描展平后一维序列局部性失真、行切换处出现虚假局部性偏差的问题。
分类置信度
中 · 待人工复核
- 只有单一媒体来源,需要人工复核。
来源级别:媒体与个人
事件类型:研究发布
证据摘录
- “To address this problem, we propose Linear Attention with Spatial-Aware Decay (LASAD), a simple recurrent attention mechanism that modulates decay according to the original 2D token geometry while preserving linear complexity.”
来源:arXiv · cs.AI · arxiv.org