Complexity-Balanced Diffusion Splitting 事件

Complexity-Balanced Diffusion Splitting arXiv:2606.06477v1 Announce Type: new Abstract: Standard continuous-time generative models rely on monolithic architectures that must navigate vastly different signal regimes, from isotropic noise to intricate data distributions. While scaling model capacity improves performance, deploying a massive network uniformly across the entire generative timeline is inherently inefficient. In this work, we propose Complexity-Balanced Splitting (CBS), a principled