Representation by Design in Generation: Cross-View Class-Token Alignment in Diffusion Transformers
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
The Flow has not summarised this story yet — read it at arXiv AI.
The paper introduces SCION, a single-model framework that jointly learns generative and self‑supervised representation tasks without relying on labels or pretrained encoders. SCION uses a pixel‑space encoder conditioned on a flow timestep and a shared embedding, training contrastive and flow‑matching objectives simultaneously with gradient‑norm balancing and stop‑gradient techniques. On ImageNet 256×256, SCION achieves state‑of‑the‑art FID scores (8.92 with JiT‑B and 5.89/3.47 with JiT‑L) surpassing prior class‑unconditional and pretrained‑conditioned methods.
arXiv:2610.20608v1 Announce Type: new Abstract: Representation-alignment methods effectively accelerate the diffusion transformer training. REPA, for example, uses a pretrained vision encoder to supe...
arXiv:2606. 00583v1 Announce Type: cross Abstract: Recent diffusion transformers have demonstrated strong image synthesis capabilities but remain inefficient to train due to weak alignment between generative and discriminative representations.
arXiv:2602.03753v2 Announce Type: replace Abstract: While representation alignment with self-supervised models has been shown to improve diffusion model training, its potential for enhancing inferenc...
The paper introduces D3S2, a diffusion‑guided dataset distillation framework tailored for semantic segmentation. It tackles long‑tailed class imbalance, pixel‑wise alignment, and high computational cost by first selecting class‑balanced masks and then synthesizing images with a pretrained diffusion model conditioned on those masks. Guided diffusion sampling further refines the data with segmentation‑consistency and class‑wise feature matching losses, achieving superior performance at a 1% compression rate on ADE20K and COCO‑Stuff.
arXiv:2608.23864v1 Announce Type: new Abstract: Visual tokenizers increasingly inject semantic supervision into latent spaces to make downstream diffusion easier. Yet how these semantics should be or...