Learning Discriminative Geometry for Drifting Models
Persistent representation learning improves one-step Drifting Models, cutting pixel-space FID by about 82-95%.
Stories per day · 30 days
2 RSS
5 stories, newest first · one card per story
Stories tagged #one-step-generation
Depth as Time in One-Step Generative Models
Depth-as-time analysis shows one-step diffusion models reorganize temporal denoising across network depth, enabling 16.6x compression of MeanFlow SiT-L/2.
Discrete Wasserstein Flows for One-Step Generative Modeling
Discrete Wasserstein flows enable one-step generative modeling on finite state spaces.
Unifying Distributional Training for One-Step Visual Generation
MGFlow unifies one-step visual training and beats FD-Loss on ImageNet and four-step FLUX.2.
Discrete Beckmann Transport Models for One-Step Language Modeling and Reasoning
DBTM achieves one-step text generation via a time-independent transport map trained directly from data, removing pretrained teacher distillation.