- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
SOAR is a supervised post-training method that exposes diffusion/flow-matching models to their own local prediction errors. It constructs states through a detached one-step rollout and shared-noise re-noising, then supervises recovery toward the paired clean image. On SD3.5-Medium, it improves GenEval from 0.70 to 0.78 and OCR from 0.64 to 0.67 over SFT, without additional inference cost. Experiments include component ablations, supervised-state-count controls, and matched-LoRA comparisons with Flow-GRPO.
Critical strengths
- SOAR provides a simple way to train on model-induced errors using paired-data supervision, without reward-model queries during optimization or additional inference cost.
- Broad-data improvements are supported by useful controls for supervision count and LoRA parameterization, strengthening the evidence beyond a standard SFT comparison.
Critical weaknesses
-
The contribution of the correction target is less clear than that of state augmentation. In Table 4, the standard-target substitution already improves five of six metrics over SFT, while the proposed target outperforms this substitution on only three. The evidence for the specific correction mechanism is therefore mixed.
-
The matched-LoRA advantages over Flow-GRPO are small and lack uncertainty estimates in the main-paper tables. Computational costs are not directly matched, and reduced diversity and some non-target regressions complicate claims of an overall advantage.
Questions for authors
- Can repeated-run results clarify whether the correction target reliably improves over the standard-target ablation, particularly on GenEval and OCR?
- Can you provide uncertainty estimates and measured training costs for the matched-LoRA comparisons with Flow-GRPO?
- Which configuration produced the reported diversity reductions, and how do its quality and diversity compare with the standard-target ablation?
Thank you for the detailed responses and additional experiments. However, the revised version of the paper substantially changes its central positioning and experimental evidence, introducing several key results only at the end of the rebuttal period.
I believe revisions of this scope require a more thorough evaluation and more time than the remaining discussion period allows. Therefore, I will maintain my original score.