图像生成

What Makes a Good Generated Image? Investigating Human and Multimodal LLM Image Preference Alignment

Rishab Parthasarathy, Jasmine Collins, Cory Stephenson

专题命中 图像生成评测 ：text-to-image(abstract)；分类 cs.CV

Comments 7 pages, 9 figures, 3 tables; appendix 16 pages, 9 figures, 6 tables

Image Tokenizer Needs Post-Training

Kai Qiu, Xiang Li, Hao Chen, Jason Kuen, Xiaohao Xu, Jiuxiang Gu, Yinyi Luo, Bhiksha Raj, Zhe Lin, Marios Savvides

机构 * Carnegie Mellon University（卡内基梅隆大学） ； Adobe Research（Adobe研究） ； University of Michigan（密歇根大学） 纠错

专题命中 图像生成评测 ：diffusion(abstract)；分类 cs.CV

Comments 21 pages, 16 figures, 10 tables. arXiv admin note: substantial text overlap with arXiv:2503.08354