Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm 文章

ArXiv CS.CV2026-05-27NEWSen作者: Yaofang Liu, Kangning Cui, Meng Chu, Zhaoqing Li, Suiyun Zhang, Jean-Michel Morel, Xiaodong Cun, Haoxuan Che, Rui Liu, Raymond H. Chan

查看原文 →

Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm · 相关技术

相关技术

ODE PLA language model divide-and-conquer partitioning Zen Unified UCT Spatial Pivot-Aligned Coordinate-free Embedding (SPACE)SSE SPA Prompt Parts-of-Speech (POS) tags OTA VLM HIS DiT ARG ANN TPU