- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 3
- Soundness
- 1
Read review
Paper summary
This paper proposes StateMix, a mixed-state training strategy for distribution matching diffusion distillation. StateMix combines noise-start states sampled from a fixed Gaussian prior with intermediate states generated by the student, while retaining DMD2 supervision and leaving inference unchanged. The authors evaluate the method on text-to-image generation and image editing using public benchmarks, supplemented by human GSB evaluation for image editing.
Critical strengths
The core idea is simple and easy to understand. It modifies the training procedure while preserving the inference process.
Critical weaknesses
-
The motivation for noise-start training could be clearer.
The paper does not convincingly explain why fixed Gaussian inputs at intermediate times should improve a sampler that uses rollout states during inference. Section 3.2 explicitly shows that matching the pooled training distribution does not ensure matching the final inference distribution. -
The two DMD2 baselines need a more direct comparison.
Appendix C.1 explains that Table 4 uses a separate fixed-budget ablation model with other training variables controlled. However, DMD2 performs substantially worse than in Table 1, while StateMix’s results remain identical. A direct comparison of training budgets, configurations, and checkpoint-selection criteria would help explain this gap. -
Numerical reporting could be more concise.
Appendix C.1 reports full-precision HPSv3 values such as9.994385379046202. Although this is explicitly acknowledged, rounded values in the prose would improve readability, with full-precision records provided separately.
Questions for authors
-
Could the authors provide a direct comparison of the training configurations, update counts, and checkpoint-selection criteria for the DMD2 models in Tables 1 and 4? Which differences could explain the performance gap?
-
What motivates using a fixed Gaussian prior at intermediate target times, despite its difference from the states encountered during inference?