Video diffusion models are rapidly scaling and exhibiting enhanced generation capabilities. Among these recent advancements, MiniMax-H3 stands out as a highly capable, production-level open-source model. However, its 33-billion parameters and multi-step iterative denoising process introduce substantial computational ov...
Yi-Tong Li, Jin-Cheng Yu, Jun-Song Chen et al.· 0 citations
This work establishes a novel theoretical analysis: DDPO is an implicit form of score/flow matching with noisy targets, which increases variance and slows convergence, and introduces Advantage Weighted Matching (AWM), a policy-gradient method for diffusion.
It is shown decoder-only MDMs, despite a larger modeling space, can achieve significant inference speedups and comparable perplexity with techniques like temperature annealing, offering a path to reduced inference compute.
Shuchen Xue, Tianyu Xie, Tianyang Hu et al.· arXiv.org· 17 citations· ⚡1
This work introduces SANA-Video 2.0, a hybrid video diffusion transformer instantiated at 5B and 14B scales under a unified architecture that recovers softmax-level expressiveness at substantially reduced cost, unlocking scalable long, high resolution video generation.
Junsong Chen, Jincheng Yu, Yitong Li et al.· arXiv.org· 1 citation· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
