Representation Distribution Matching for One-Step Visual Generation
- Published
- Source
- arXiv
- Paper number
- 554
- Field
- Computer Vision
- arXiv ID
- 2607.02375
Key points
- It systematizes RDM along two axes, distribution comparison and representation space, and derives the best design for each axis.
- It shows that MMD becomes a strong objective when estimated with Nyström approximation and large batches of 2,048 or more.
- A single encoder can be gamed, so the paper proposes SWr14, an evaluation metric using 14 encoders that is resistant to gaming and independent of training loss.
- iRDM reaches a one-stage state-of-the-art SWr14 of 1.30 on ImageNet and a PickScore win rate of 71.2%.
- It compresses FLUX.2[klein] from four stages to one stage, reaching a GenEval score of 0.826 versus 0.794 for the original model with 90 H200 GPU hours.
- Proportional Lagrangian optimization keeps the encoders balanced and improves the weakest encoder.
Paper links
External research summaries. These are not HDATF publications or measured product results.