ICCV 2025 "semantic fidelity" Papers
2 papers found
Importance-Based Token Merging for Efficient Image and Video Generation
Haoyu Wu, Jingyi Xu, Hieu Le et al.
ICCV 2025posterarXiv:2411.16720
4
citations
Rethinking Cross-Modal Interaction in Multimodal Diffusion Transformers
Zhengyao Lyu, Tianlin Pan, Chenyang Si et al.
ICCV 2025posterarXiv:2506.07986
5
citations