- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 3
Read review
Paper summary
Building upon the foundation of established MeanFlow, which conventionally treats the prediction horizon and the state-update duration as equivalent, therefore this paper reveals that the distance of model prediction and the distance of actual movement do not necessarily need to be simply equated. Next, it demonstrates the necessity of distinguishing between the prediction horizon and the step size. Furthermore, the study also finds that extending the prediction horizon does not consistently yield performance improvements in terms of FID/KID across different query positions. Specifically, longer horizons worsen performance at earlier sampling positions, such as and , while improving performance around the midpoint , a phenomenon characterized as the midpoint effect. In the experiments, the authors compare the horizon strategy with other temporal control methods under constrained query budgets, showing that the relative effectiveness of different temporal controls depends on the tested models, query budgets, and evaluation metrics.
Critical strengths
To be honest, I am not deeply familiar with the specific technical details of the MeanFlow work. Nevertheless, I can clearly grasp the significance of the authors' motivation. They rethink the image generation process by decoupling the prediction horizon from the state-update duration, in particular considering how far the model should look (predict) ahead while keeping the actual movement of the sampling process fixed. Compared with the conventional MeanFlow setting that directly couples these two quantities, this research explores whether adjusting the prediction horizon can lead to better generation quality without increasing the number of model queries. Furthermore, both the paper's experimental validation provide solid support for the authors' hypotheses and final conclusions.
Critical weaknesses
None. The authors have already acknowledged the limitations of horizon selection in Section 6 (Discussion), which directly corresponds my main concern. But I have some questions below.
Questions for authors
Although Figure 4 presents a qualitative comparison between the Local and Horizon methods, the visual differences are relatively subtle. Therefore, for the sake of completeness, I would like the authors to provide a more detailed qualitative analysis or representative examples of failure and success cases. Additionally, could the authors clarify specifically which aspects of perception saw improvements or degradations due to the Horizon control?
Another important point concerns that why the benefit of horizon extension changes from degradation at to improvement at . Although the authors acknowledge the possible sources of this effect in the discussion section, I would like them to further elaborate on the underlying attribution of this benefit. It would provide more compelling evidence if the authors could conduct a quantitative results between these query positions to examine how the horizon performance grows, decays, or changes sign.
Could the authors maintain a consistent placement of table captions throughout the paper?
3 comments
Attribution of the position contrast
We added direct interventions to examine why midpoint adjustments produce larger benefits. We also refined the premise concerning : in the updated seven-checkpoint scan, gives a mean gain of +.105 FID with 6/7 improvements, whereas worsens all seven. Earlier small negative quarter-point results remain reported under their respective protocols. The consistent source-to-midpoint reversal and the quarter-to-midpoint benefit difference are treated separately.
For the quarter-to-midpoint comparison, RefLocal and RefLong are average velocities obtained by integrating the model's guided instantaneous field over the local and long prediction intervals. We apply each with the same physical update duration, . Their comparison removes the Local predictor's discrepancy from this integrated model reference at the changed query.
We then hold each arm's state fixed across final samplers and change only the interval [.75,1]. For the intervention, propagation through [.50,.75] remains native. Let be the RefLong-over-RefLocal FID gain at minus that at . On four confirmation checkpoints, mean is 3.421 with one native final update, 2.699 with two native half-steps and .073 with fourth-order Runge–Kutta (RK4) integration. Every checkpoint has this ordering in FID and KID. The one-native-step minus RK4 difference is 3.348 FID, with descriptive 95% interval [2.894, 3.803] (Appendix D.7).
Replacing only the final interval is sufficient to substantially reduce the measured position contrast. The interval for the smaller RK4 residual spans zero, leaving the residual contrast uncertain. These final-interval numbers also differ from the separate experiment that replaces the entire remaining suffix in Appendix D.6.
At the midpoint with full-amplitude reference interventions, the three exploration checkpoints provide additional distributional detail. Native and RK4 final maps yield similar feature-mean displacement lengths, 1.156 and 1.173, but mean-term FID gains of 1.347 and .142 and covariance-term gains of 2.133 and .182. Writing the baseline mean error as and the intervention's mean shift as , the mean-term gain is
A displacement of similar length can therefore have a different benefit when the baseline error and its alignment with the displacement change. The final sampler changes both quantities; the covariance term also contributes to the observed FID difference.
This is a more specific explanation than attributing the effect to a larger velocity change: the correction interacts with the subsequent sampling map and the baseline distribution it produces. The reference field comes from the learned model, and RK4 uses extra computation for diagnosis. The specific network-error source remains unresolved (Section 4; Appendices D.5–D.7).
Intermediate-position measurements and table captions
Figure 7 adds the requested intermediate-position measurements at , .35, .40, .45 and .50. Each uses the grid ; the third query has physical update duration .25 and prediction horizon .50. Local and Horizon share the entering state before that query and paired generation inputs.
| Position s | .30 | .35 | .40 | .45 | .50 |
|---|---|---|---|---|---|
| Mean FID gain | .243 | .630 | 1.051 | 1.494 | 2.002 |
| Mean KID gain x1000 | .402 | .646 | .908 | 1.173 | 1.470 |
Positive gain favors Horizon. Both FID and KID gains increase across the measured positions on each of the three checkpoints, and all measured positions have positive mean gains. Figure 7 shows the individual checkpoints as well as their mean; the supplementary files contain the paired numerical results (Appendix D.12).
The scan establishes an increasing benefit within this grid family. Moving s also changes the prefix and suffix durations, and the original intervention occurs at a different query index. Consequently, we do not join it to this series as a pure time-position sign-change experiment. The fixed-state final-interval interventions in Section 4 and Appendix D.7 test downstream sampling dependence separately.
We also standardized table captions above the tables throughout the manuscript and appendices. Figure numbers in these responses refer to the revised manuscript: the horizon-response curves are Figure 6, the intermediate-position scan is Figure 7, and the qualitative examples are Figure 8.
Dear authors,
Thanks for your adequate rebuttal with my concerns.
Proposed suggestions are anticipated to incorporate into the revised paper and imporve the clarification of paper.
So, I decide to remain the exisiting postitive score.
Paired examples and distributional measurements
Thank you for requesting clearer examples and a more specific account of what improves. Revised Figure 8 in Appendix E presents six paired Local/Horizon/direction-only examples. Within each triplet, checkpoint, initial noise, requested class and sample index are identical.
The six cases come from a 150-case pool of Local/early-Horizon/midpoint-Horizon triplets. Figure 8 adds existing direction-only outputs at six of those indices. The supplementary files contain the full original pool and contact sheets; the figure uses saved evaluation pixels without enhancement. This selection provides illustrative cases rather than a prevalence estimate.
In panels c and e, both midpoint Horizon and direction-only outputs appear clearer than Local. Panel c remains semantically ambiguous even after this change. The informal inspection found no visually discernible difference between Horizon and direction-only in these examples. These examples illustrate clearer appearance alongside persistent semantic ambiguity. They were assessed informally, rather than in a human preference study.
The distributional evaluations show a measurable tradeoff. In the separate seven-checkpoint classifier-free guidance (CFG) 1.5 comparison on identical saved images, Horizon lowers DINOv2 feature-space precision from .7171 to .6967 and raises recall from .3617 to .3921 relative to Local. DINOv2 distance, Inception FID and KID all improve. In this representation, more real features fall within the generated-feature neighborhoods, while fewer generated features fall within the real-feature neighborhoods. It is not a direct perceptual rating of Figure 8, which belongs to a different experiment.
The calibrated four-step comparison has a different pattern: Combination improves Inception precision and recall over Scalar, from .7369/.4481 to .7433/.4594, while requested-class agreement falls slightly from 98.44% to 98.29%. Appendix C reports those measurements, and Appendix E separates the evaluator-specific results.