Poster "discrete visual tokens" Papers
2 papers found
Conference
Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens
Kaihang Pan, Wang Lin, Zhongqi Yue et al.
CVPR 2025arXiv:2504.14666
20
citations
SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation
Leigang Qu, Haochuan Li, Wenjie Wang et al.
CVPR 2025arXiv:2412.05818
10
citations