نسخة أولية وصول مفتوح
Residual-Stream Burden Shapes Representation Learning in Diffusion Transformers
In diffusion-based generation, a neural network can be trained to predict the clean data, the noise, or the velocity from a noisy input. These prediction targets are interconvertible and describe the same generative process, yet plain Diffusion Transformers operating on large pixel patches succeed with clean prediction …