- Rating
- 2(+1)
- Confidence
- 4
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes FlowPINN, a physics-informed flow matching framework designed for one-step (1-NFE) generative modeling. Instead of learning a velocity field and numerically integrating the flow ODE at sampling time, FlowPINN directly parameterizes the solution map of the flow ODE and trains it once by minimizing a balanced physics-informed residual alongside a distributional terminal penalty. Consequently, sample generation requires only a single forward pass without any numerical solver. Empirical evaluations on low-dimensional synthetic distributions, medium-dimensional Neal's funnel, and image benchmarks (MNIST and CIFAR-10) demonstrate that FlowPINN achieves competitive one-step generation quality compared to multi-step ODE solvers and few-step baselines such as MeanFlow and Shortcut Models.
Critical strengths
-
Solid Mathematical Formulation: The mathematical construction and theoretical analysis of the proposed method are solid, systematically formulating four distinct algorithmic variants (FLOWPINN-P, FLOWPINN-L, FLOWPINN-C, and FLOWPINN-2T).
-
Simple Core Idea and Clear Presentation: The core idea of learning the flow map by minimizing the ODE residual once during training is straightforward, and the paper is clearly written and easy to follow.
Critical weaknesses
-
Overly Simple and Low-Resolution Datasets: The image generation experiments are restricted to MNIST () and CIFAR-10 (), with a maximum resolution of only . The authors should evaluate the method on higher-resolution benchmarks such as ImageNet-256, CelebA-HQ, and LSUN-Church.
-
Lack of Latent-Space Generation: The experiments focus exclusively on pixel-space generation, lacking any evaluation or discussion on the widely used latent-space generation setting.
-
Insufficient Baselines: The compared few-step baselines are overly simple, including only MeanFlow and Shortcut Models. Stronger and more recent one-step models—such as Improved MeanFlow [1], Align Your Flow (AYF) [2], and -Flow [3]—are missing.
-
Theoretical Overlap Between FLOWPINN-2T and MeanFlow: The theoretical formulation and core equations of FLOWPINN-2T (Eqs. 18–19) are essentially identical to existing MeanFlow, differing only in the time-axis convention.
-
Degradation on Mainstream DiT Backbones: As acknowledged in the Limitations section, the method degrades severely (losing 41%–68% in FID) when applied to mainstream DiT architectures.
-
Contradictory and Unfair Teacher-Guided Comparison on CIFAR-10: While the main text claims FLOWPINN-L trains from scratch without a teacher and achieves 8.69 FID on CIFAR-10 in 29 A100-hours, Appendix D.4 reveals that this result actually relies on a pretrained, frozen CFM teacher (distillation, costing an extra 11 hours), whereas true joint training from scratch reaches only 33.76 FID. This contradicts the main text and makes the comparison against train-from-scratch baselines (MeanFlow at 9.88 and Shortcut at 23.65) unfair.
[1] Geng, Zhengyang, et al. "Improved mean flows: On the challenges of fastforward generative models." Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2026.
[2] Sabour, Amirmojtaba, Sanja Fidler, and Karsten Kreis. "Align your flow: Scaling continuous-time flow map distillation." Advances in Neural Information Processing Systems 38 (2026): 146459-146512.
[3] Chen, Hansheng, et al. "pi-flow: Policy-based few-step generation via imitation distillation." International Conference on Learning Representations. Vol. 2026. 2026.
Questions for authors
Please refer to Weaknesses section.
3 comments
Thank you very much for your responses and the additional experiments in the rebuttal. I appreciate the PINN-based perspective for formulating single-time flow maps, as well as your efforts in re-running CIFAR-10 without a teacher, so I will raise my score to 2.
That being said, while the high-level core idea is intuitive, I still consider the current manuscript rather rough in execution and in need of further polishing. For example, there are clear formatting issues with the figures: 1:1 square CIFAR-10 images in Figure 5 and plots in Figure 3 are squashed out of proportion, leaving both the images and the text inside visibly flattened.
Most importantly, my primary concern remains the lack of evaluation at mainstream higher resolutions such as ImageNet-256. To convincingly demonstrate the superiority of your method, you either need to comprehensively reproduce recent strong SOTA baselines under your own experimental setup, or scale up to standard higher-resolution benchmarks where you can directly compare against official numbers reported in the literature. Right now, on your highest-dimensional benchmark CIFAR-10 (Table 2), only MeanFlow and Shortcut are compared—even the newly added iMeanFlow and LSD are absent there, not to mention recent strong baselines like alpha-Flow, AYF and -Flow—and FlowPINN-L (7.33 FID) still slightly trails MeanFlow (7.06 FID) at 1-NFE. As for citing earlier general ODE/flow works like Neural ODE (2018) or minibatch OT-CFM, those predated today's standardized evaluation consensus for one-step flow-map generation. In the current one-step/few-step generation literature (including Shortcut, MeanFlow, iMeanFlow, AYF, and -Flow), ImageNet benchmarks are well-established and mature, so I strongly encourage you to include them in future revisions.
iMeanFlow and LSD for CIFAR-10 added
Thank you for raising your score! We also appreciate your acknowledgment of our effort for improvement.
We agree with you on the figures so we have fixed them in the revision.
We understand your concern so we have added the missing puzzles -- more recent iMeanFlow and LSD results to Table 2 (old Table 6), with relevant rows quoted below:
Table 2: CIFAR-10 on the UNet backbone
| Method | NFE | FID ↓ | clf-FID ↓ | IS ↑ | memo ≈ 1 | ms/1k ↓ | Params |
|---|---|---|---|---|---|---|---|
| CFM + midpoint | 100 | 3.01 ± 0.03 | 0.08 ± 0.01 | 9.635 ± 0.025 | 1.000 ± 0.003 | 51756 | 55.68M |
| FlowPINN-L | 1 | 7.33 ± 0.03 | 0.48 ± 0.03 | 8.481 ± 0.033 | 0.999 ± 0.002 | 523 | 55.57M |
| iMeanFlow | 1 | 13.53 ± 0.06 | 0.36 ± 0.01 | 8.785 ± 0.028 | 0.998 ± 0.002 | 516 | 55.74M |
| iMeanFlow | 4 | 7.96 ± 0.04 | 0.26 ± 0.01 | 9.405 ± 0.062 | 1.000 ± 0.003 | 2059 | 55.74M |
| LSD | 1 | 14.69 ± 0.05 | 0.82 ± 0.01 | 7.841 ± 0.032 | 0.999 ± 0.002 | 516 | 55.74M |
| LSD | 4 | 4.90 ± 0.03 | 0.22 ± 0.01 | 8.893 ± 0.024 | 0.999 ± 0.002 | 2059 | 55.74M |
We can see that both iMeanFlow and LSD still trail FlowPINN-L at NFE=1. iMeanFlow at NFE=4 becomes comparable with FlowPINN-L; LSD at NFE=4 beats FlowPINN-L and is comparable with FlowPINN-2T at NFE=4. All the comparisons are done at the same model size described in Table 2 and may be different from their published numbers. We have new Table 8 for their training recipe in the revision to make it transparent.
We have made our best efforts to complete the comparison with 4 SOTA models on all examples including image benchmarks. Please note that iMeanFlow was published only 4~5 months ago and it took 50~70 hours to train each of these models on CIFAR-10 at the budget of 440K steps. They are models all in the pixel space so training takes time. We have ImageNet running with good trend on the recorded logs; however, it is less likely to finish within the discussion period.
We agree with the reviewer that results on larger datasets may further strengthen the numerical evidences. However, we have demonstrated the numerical advantages of the proposed FlowPINN methods with sufficient proof. We hope the reviewer can appreciate our new results and agree with us on this. Thanks again for your nice suggestions for improving this work!
Comparison to iMeanFlow added
We thank the reviewer for acknowledging the solid math foundation and clear presentation of our paper! Below we try our best to address your concerns.
Weaknesses:
MNIST and CIFAR-10 are standard image benchmarks in generative models. We have used them to demonstrate the numerical advantages of proposed methods over other models in fair comparisons. With available resources, we wish to complete tests on these extra high-dimensional datasets within the given discussion period. However, a paper's quality and contribution to the community should not depend solely on the problem size afforded. For example, Neural ODEs by Chen et al (2018) only reports MNIST, minibatch OT-CFM by Tong et al (2024) studies CIFAR-10 in the pixel space, and Boffi et al. (2025, LSD), Kim et al. (2024, CTM) also use the same datasets or images at this level.
This is a great suggestion and we have acknowledged in the revision. We understand latent-space is a powerful technique to scale up applications that can be applied to benefit our work. However, the main purpose for this paper is to establish single-time flow map for one-time generation by adopting PINN-style solving. Given the existing contents and the capacity limit, we think it would be a good future direction.
Thanks for pointing to the references. While we congratulate these authors on publishing their works on top conferences, we notice that they appear in this year. For example, "improved mean flows (iMeanFlow)" got accepted only three months ago! We have managed to add iMeanFlow in the revision. Below we quote iMeanFlow rows from Tables 1, 4, and 5 in the revision.
Table 1: MNIST on the UNet backbone
Table 4: The two-dimensional benchmarks.
Table 5: Neal's funnel distribution.
The connection and distinction between FlowPINN-2T and MeanFlow was in Appendix B of the submission and has been moved to Section 3.4. Indeed, we did NOT accredit the MeanFlow identity (18) to ourselves. On the contrary, we only regard FlowPINN-2T as a two-time relaxation of our single-time flow map that nicely connects to MeanFlow. A paragraph in Appendix B of revision now describes the implementation differences between FlowPINN-2T and MeanFlow.
As commented in the response to the first reviewer, the models' performance depends on the capacity of the backbone. First, In Table 6 (old Table 5), FlowPINN methods still beat MeanFlow and Shortcut at NFE=1 on DiT-6 (6 blocks) backbone even there is some gap to CFM-100NFE. Second, in new Table 7, increasing the size by 50, a deeper DiT-9 (9 blocks) improves all results of DiT-6 and closes the gap by up to 46. Finally, among models being compared in the paper, UNet is shipped in both MeanFlow (torch version) and LSD; while Shortcut and iMeanFlow use DiT -- we do not judge which is mainstream but UNet is not something used only by us.
We acknowledge this issue and have re-run the CIFAR-10 experiments with no teacher, at the same budget and with 5 random seeds. Please refer to Table 2 (old Table 6) for the updated results and responses to other two reviews.
We hope our answers address your concerns and we will be happy to take any follow-up questions.