- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes a few-step generation method based on data-space iteration. The method moves the rollout from probability-flow space to data space while retaining the remaining DMD training components. The paper validates the method mainly on ImageNet 256×256.
Critical strengths
- The paper is well-written and easy to follow.
- The paper achieves performance improvements with a relatively small modification.
Critical weaknesses
- The work is relatively incremental. The core change is only switching the DMD rollout from probability-flow space to data space. The authors should more clearly articulate the essential mechanistic difference beyond a different iteration space.
- Comparison with other few-step generation methods is missing. Comparison against non-DMD few-step methods such as iMeanFlow is recommended.
- The work is validated mainly on ImageNet 256×256 and a single architecture (DiT-XL/2).
Questions for authors
- Please see weaknesses.
- It is recommended to report metrics beyond FID in the main text, such as sFID, IS, precision, and recall.
3 comments
Thank you for your responses.
I am sorry for not stating my main concern clearly. My primary worry is about dataset coverage. The only large-scale dataset is ImageNet, and CIFAR-10 is relatively small in resolution. I therefore still have some concerns about whether the empirical evaluation covers a sufficiently diverse set of datasets.
However, I am not fully confident in my judgment. After considering the comments of other reviewers and the initial response, I have decided to raise my rating to 3. I will revisit the discussion before it closes and confirm my final rating.
We thank the reviewer for updating their rating.
We would also like to clarify that evaluating on ImageNet-256 and CIFAR-10 is a well-established protocol in recent work on few-step generative models. The table below summarizes the evaluation datasets used by representative methods. Most of these works evaluate on ImageNet together with one smaller dataset, while several report results on ImageNet alone. Notably, MeanFlow, iMM, and FACM use exactly the same ImageNet-256 and CIFAR-10 setting as ours. We therefore believe that our experimental scope is consistent with the evaluation standards established by the recent literature and provides a sufficiently rigorous basis for comparison.
| Paper | Evaluation datasets | Venue and citation |
|---|---|---|
| MeanFlow | ImageNet-256 + CIFAR-10 | NeurIPS 2025 |
| iMeanFlow | ImageNet-256 | CVPR 2026 |
| pMeanFlow | ImageNet-256 + ImageNet-512 | ICML 2026 |
| Shortcut | ImageNet-256 + CelebA-HQ | ICLR 2025 |
| CM | ImageNet-64 + CIFAR-10 + LSUN | ICML 2023 |
| iCM | ImageNet-64 + CIFAR-10 | ICLR 2024 |
| sCM | ImageNet-64 + ImageNet-512 + CIFAR-10 | ICLR 2025 |
| iMM | ImageNet-256 + CIFAR-10 | ICML 2025 |
| AlphaFlow | ImageNet-256 | ICLR 2026 |
| AFM | ImageNet-256 | ICML 2026 |
| FACM | ImageNet-256 + CIFAR-10 | ICLR 2026 |
We hope this clarification addresses the reviewer’s remaining concern. If there are any outstanding questions or reservations that prevent a stronger assessment, we would be grateful if the reviewer could let us know. We would be happy to provide any additional clarification, analysis, or experimental evidence that would be helpful.
Response to Reviewer pJiS
We thank the reviewer for their feedback and address their questions and concerns below.
1. Importance of our work
The key contribution is not merely changing the iteration space, but introducing a new schedule-free paradigm for few-step generation.
Existing flow-space methods pass schedule-specific noisy states between steps, requiring the schedule to be fixed before self-rollout training; testing another schedule may therefore require training a separate model. This is an increasingly important bottleneck in image and causal streaming-video distillation. Our method instead passes the current data prediction back to the generator and directly refines it toward the data distribution. This removes costly schedule search and consistently improves FID over flow-renoise and flow-map baselines under matched training settings. Importantly, this new paradigm can be adopted in existing DMD pipelines with minimal changes and no additional sampling cost.
2. Comparison to MeanFlow
As the reviewer suggested, we include MeanFlow [1] as an additional baseline.
We selected MeanFlow [1] rather than iMeanFlow [2] because their objectives are identical in the distillation setting. Moreover, MeanFlow uses the SiT architecture, allowing us to adopt its hyperparameters directly, whereas iMeanFlow uses a different custom architecture.
Our MeanFlow distillation model was trained using velocity predictions from the SiT teacher and the same hyperparameter configuration as the XL/2+ model in the MeanFlow paper, except that we changed the adaptive loss-weighting parameter p from 1.0 to 0.5. We made this change because the model failed to learn with p=1.0, an issue also reported in FACM [3]. Our reproduced MeanFlow distillation model performs worse than a MeanFlow model trained from scratch, for which the original paper reports FIDs of 3.43 at 1 NFE and 2.20 at 2 NFEs. This discrepancy may be due to the SiT teacher, and further hyperparameter tuning could potentially improve the results. We report our best-effort reproduction of MeanFlow distillation solely as an additional baseline.
3. Evaluation on additional datasets and architectures
Our original submission includes an additional evaluation on CIFAR-10 using the EDM U-Net architecture in the appendix, following the evaluation protocol of MeanFlow [1].
Because Reviewer 1Yce also raised concerns about the generality of our method, we conducted an additional experiment using the LightningDiT [4] architecture for this rebuttal. Specifically, we used the pretrained LightningDiT on ImageNet-256 (FID = 2.17, without CFG) as the teacher and adopted the same hyperparameter configuration as in our main SiT experiment. The results show that data-space iteration consistently outperforms the flow-renoise and flow-map methods across all evaluated NFE settings.
Thus far, we have evaluated our method on two datasets (ImageNet and CIFAR-10) and three architectures (SiT, LightningDiT, and EDM U-Net). We believe that these results demonstrate the generality of our method.
4. Evaluation metrics
We report the full set of metrics (sFID, IS, precision, and recall) in Table 5 of the appendix. Following the convention of recent papers and because of space constraints, the main text reports only FID. We will take the reviewer's suggestion into account when preparing the camera-ready version.
Conclusion
In this rebuttal, we clarified the importance and mechanistic novelty of data-space iteration, provided an additional comparison with MeanFlow distillation, evaluated our method on the LightningDiT architecture, and pointed to the full evaluation metrics reported in the appendix. These additions address the reviewer's concerns about novelty, baseline comparisons, generality, and evaluation breadth.
Citations