AI Research Feed

Rethinking Self-Alignment in Diffusion Transformers: Data Augmentation, Not Inter-Noise Token Interaction, Drives Performance Gains

New research challenges the prevailing understanding of performance improvements in self-alignment methods for diffusion transformers. Contrary to previous assumptions, the gains from methods like Self-Flow over SRA appear to stem primarily from data augmentation along the noise dimension, rather than interactions between tokens at different noise levels. The introduction of 'Attention Separation' demonstrates that blocking such interactions can even improve performance, highlighting the role of augmentation.