Language models typically increase per-token computation through deeper or looped layers and latent reasoning steps, while richer residual connections improve information flow across layers. We instead increase computational capacity: the number of active computational states a model maintains. We introduce the Lattice...
Shivam Duggal, Zongze Wu, W. Freeman et al.· 0 citations
Joint scaling and STAC consistently improve few-step distillation across class-conditional ImageNet generation, text-to-image generation with SDXL and FLUX, and text-to-video generation with Wan2.1.2.
Zongze Wu, Xian-Bang Wang, Zheng-Yang Geng et al.· 0 citations
Interactive video generation and editing are becoming increasingly important for creative design. In this report, we introduce EditStream: a unified framework for interactive video generation and editing. EditStream unifies multiple video creation and manipulation tasks within a single DiT-based model through flexible...
Yu-Qian Zhou, Zhenghong Zhou, Zongze Wu 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.