LongBanana is introduced, to the authors' knowledge the first expert-designed and expert-verified benchmark for long-context multi-reference image synthesis in the age of agent-driven image generation, and experiments show that minimal agent harnesses improve over direct generation, while a ReAct-Plan-Exec-Reflect (RPR...
Hao-Xiang Cao, Yuxuan Zhang, Peng-Hui Du et al.· 0 citations
Unified Multimodal Models (UMMs) enable powerful multi-image synthesis but incur substantial computation from long visual contexts. While token pruning offers a direct route to accelerating inference, existing methods are primarily adapted from understanding tasks, suffering from insufficient reference image exploratio...
Zi-Meng Wu, Qi-Jian Tian, Peng-Hui Du et al.· 0 citations
Instruction-based image editing uses a planner-renderer pipeline: a vision-language model (VLM) first converts the instruction into an edit plan, and a diffusion model then executes that plan. Training such systems with only final-image rewards is inefficient because a poor edit does not reveal whether additional optim...
Hao-Xiang Cao, Jiajiong Cao, Xuan-Pu Zhang et al.· 0 citations
Controllable image relighting is an important problem in image editing, and hand-drawn scribbles provide an intuitive interface for specifying the desired illumination. However, existing methods do not establish a consistent and effective mapping between scribble inputs and relighting results, limiting their ability to...
Xuan-Pu Zhang, Xue-Song Niu, Hao-Xiang Cao et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
