UniRA: Unified Representation Alignment and Auto-Encoding for Efficient Diffusion Generation

Paper recorded by Signals 4 on 2026-10-29 in cs.CV. Abstract reproduced from arXiv; link to the original below.

Published 2026-10-29 on arXiv · recorded by Signals 4 on 2026-10-30

Category: cs.CV · 计算机视觉 · first seen 2026-10-30

Abstract

Diffusion transformers (DiTs) have become the dominant architecture for high-fidelity image synthesis, yet they suffer from slow training convergence and high computational cost. Two recent lines of work address this from complementary angles: Representation Alignment (REPA) accelerates DiT training by aligning intermediate features with a pretrained external representation model (e.g., DINOv2), w

Read on arXiv →