Visual generative models increasingly blur the line between synthesizing observations and simulating environments. Yet visual plausibility alone does not constitute successful world modeling: compelling outputs may lack persistent state, physical dynamics, or causally consistent responses to interactions. We define a g...
Juan-Xi Tian, Jia-Dong Hou, Bai-Ang Li et al.· 0 citations
OmniXRef, a unified framework for multimodal multi-reference video editing that allows users to combine variable numbers of text, image, and video references to control diverse attributes of a source video, is introduced.
Xiao-Yan Cong, Tian-Yu Wang, Hyeonho Jeong et al.· 0 citations
PixelDense is introduced, which routes DINOv2 and SAM2 through a semantic projection stream, routes Depth Anything v2 and Metric3D v2 through a geometric projection stream, and adds a weight-space orthogonality penalty that keeps the two streams in disjoint subspaces.
Lehan Yang, Dai-Qing Qi, Wen-Hao Zhang et al.· 0 citations
Distribution matching distillation (DMD) provides a general framework for few-step diffusion generation, but its modern text-to-image instantiations have been developed primarily around latent diffusion. It therefore overlooks key properties and design opportunities of native RGB. We revisit two DMD interfaces for pixe...
This work identifies direct output access to the image statistics being corrected as a key factor governing when adversarial post-training succeeds, the first systematic study of adversarial post-training for pixel diffusion.
Experiments show that PixelControl improves structural fidelity and visual quality over existing controllable generation methods, with especially strong gains on boundaries and medium/small conditioned regions.
Xin Lin, Haodong Li, Zhi-Fei Zhang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.