- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
The paper does something with a few-step sampler. It tries to tackle some existing problems in scheduling (probably time-step) methods and tries to propose a new method that is more efficient with less number of function evaluations. It does this by formulating temporal allocation as a positive measure that fully specifies a finite-step solver action.
Critical strengths
None.
Critical weaknesses
- The writing and presentation of the paper need to be improved a lot. Even in the Introduction, it is challenging to understand what the authors want to say. There are too many notations/concepts that are undefined, which makes it much more challenging to read.
Questions for authors
I'm gonna ask clarification for writing only for the Introduction, although there are a lot more throughout the paper.
- line 36. "A numerical solver samples that field at selected times" <- Is this a correct explanation of flow matching?
- line 46. "Our deployed object is a positive temporal measure" <- What do you mean?
- line 46. "At midpoint NFE=8" <- What is midpoint here and you did not define what NFE is here yet...
- line 49. "ImageNet" <- No citation?
- line 49. "No target trajectory, feature, gradient, quality metric, or selection query enters acquisition." <- Need a lot more explanation on this.
- line 51. "FID50k by 14.3% on SiT and 18.6% on Self-Flow" <- Define or cite FID50k, SiT, or Self-Flow.
- line 53. "A directly acquired power measure recovers most of the gain. Transfer follows the temporal allocation, not one optimizer trajectory." <- Can you explain what you want to say here?
Some questions for the method section (below are questions I have while reading Section 3.1 only)
- What is "corresponding time-only dynamics" in Equation 2. Is it derivative of x w.r.t t? How did you get the Equation 2?
- What is and ? Did you define the difference between the two?
- What is in in physical grid?
- What is ? Did you define what it is?
- Also same for
- What is nonlinear clock?
- I cannot understand Equation 3 at all since there is no definition of
13 comments
The second sentence refers to two independent Sobol/GP searches. They gave different interval widths, but both schedules had the widest interval last. Both beat uniform allocation in all eight cross-stream evaluations.
The recurring late-loaded allocation transfers. Transfer does not require a particular optimizer trajectory or identical interval widths across runs.
Your question overlooks the independent acquisition and cross-model transfer experiments reported in Section 5.3.
I also have several questions about the Methods section. The following arose while I was reading Section 3.1 alone.
Comment 9
Question. In Equation 2, what are the “corresponding time-only dynamics”? Is this the derivative of x? How do you derive Equation 2?
Response 9
Yes. You are asking about the derivative of the transformed state with respect to physical time .
Equation 2 follows directly from the chain rule.
Let the original dynamics be:
and define:
Then, by the chain rule:
This is exactly Equation 2.
Immediately after Equation 2, the paper gives the relation between the exact solutions,
and their agreement at the endpoint,
The equation thus follows from the chain rule applied to the change of time variable.
Comment 10
Question. What are and ? Have you clearly distinguished between them?
Response 10
You will find both definitions in the paragraph immediately preceding Equation 3.
- is the numerical endpoint obtained by integrating the transformed dynamics in Equation 2 on the uniform physical-time grid.
- is the numerical endpoint obtained by integrating the original velocity field on the induced grid .
They are endpoints of two finite-step implementations of the same continuous time transformation.
A nonlinear time transformation generally changes the internal Runge–Kutta stages and their quadrature weights. This accounts for the difference.
This is the central issue studied in Section 3.1.
Comment 11
Question. What does denote on the physical-time grid?
Response 11
Here, is the step size on the uniform physical-time grid, standard notation in numerical ODE integration. For equal intervals over normalized time,
\qquad n=0,\ldots,K.$$ After the time transformation, the corresponding induced grid is: $$\tau_n=C_\lambda(t_n).$$ You are asking for clarification of standard numerical notation. The uniform grid, the numerical endpoint $D_h$, and the limit $h\to0$ establish the meaning of $h$. ##### Comment 12 > **Question.** What is $C_\phi(t)$? Have you defined it? **Response 12** You will find the definitions of the time transformations immediately before Equation 2. First: $$I(t)=t,$$ where $I$ denotes the identity time transformation. $C_\phi(t)$ denotes **a learned monotone time-transformation function with fixed endpoints**. ##### Comment 13 > **Question.** Likewise, what is $C_\lambda(t)$? **Response 13** For your question on interpolation, the definition is $$C_\lambda(t) =(1-\lambda)t+\lambda C_\phi(t), \qquad \lambda\in[0,1].$$ Here, $\lambda$ **sets the degree of interpolation between the identity and the learned transformation**. ##### Comment 14 > **Question.** What is a nonlinear clock? **Response 14** The nonlinear clock you ask about is **a non-affine time transformation**. It changes the mapping from the solver’s physical time to the original flow time. Time reparameterization and mesh redistribution are established concepts in numerical analysis. Section 2 cites the following work. - Lindberg (1977) - Estep (1995) - Carey and Dinh (1985) - Becker and Rannacher (2001) - Giles and Süli (2002) - Huang et al. (2026), *Adaptive Reparameterized Time (ART)* The paper gives the background and implementation. Your description of these concepts as entirely undefined is inaccurate. ##### Comment 15 > **Question.** I cannot understand Equation 3 at all because D has not been defined. **Response 15** Your assessment that D is undefined is inconsistent with the manuscript. The paragraph immediately before Equation 3 defines $D_h^{\mathrm{clock}}$ and $D_h^{\mathrm{grid}}$, as explained above. Equation 3 compares these endpoints, $$D_h^{\mathrm{clock}} \neq D_h^{\mathrm{grid}},$$ and: $$\left\| D_h^{\mathrm{clock}}-D_h^{\mathrm{grid}} \right\| \rightarrow 0, \qquad h\rightarrow0.$$ Your claim overlooks the text immediately before the equation.In summary
The review primarily raises concerns about presentation and notation, but does not explain how these concerns support the lowest soundness rating. In particular, it does not identify a specific mathematical error, flaw in the experimental design, or central conclusion contradicted by the evidence.
We recognize that unclear presentation can hinder technical verification. However, it is important to distinguish difficulty verifying an argument as presented from an identified technical flaw. We would appreciate clarification on which of these underlies the soundness assessment.
We take the readability concerns seriously and have made targeted revisions to improve the clarity of the presentation. We address the specific questions about terminology, notation, and derivations in our point-by-point responses.
We respectfully request that you reconsider the soundness assessment and overall rating in light of these clarifications and the methodological and experimental evidence presented in the paper. If substantive technical concerns remain, please identify the relevant claims or results so that we can address them directly.
Comment 1
Response 1
We made targeted revisions to the paper PDF to address the reading difficulties you raised.
Comment 2
Response 2
The sentence you question describes inference after training. Flow Matching learns a velocity field for continuous transport. At inference, the ODE solver evaluates this field to advance the trajectory. The sentence describes standard numerical sampling and contains no conceptual error.
Comment 3
Response 3
Section 3.2 defines the measure you ask about.
It consists of four positive interval widths satisfying
mj>0,∑j=14mj=1.
Their cumulative sums give the integration nodes. The four widths fully determine the midpoint computation at NFE = 8.
“Positive temporal measure” is our finite-dimensional representation of time allocation. It has four positive interval masses that sum to one. It has both a mathematical definition and a numerical implementation.
Comment 4
Response 4
NFE stands for Number of Function Evaluations, a standard measure of computational cost in Flow Matching and diffusion sampling.
Section 4 states the following.
“Midpoint” means the explicit second-order midpoint Runge–Kutta method (RK2). The abstract introduces it. Section 3.2 gives the full update.
Each interval uses two velocity-field evaluations, so NFE = 8 gives four intervals.
We suggest you read the paper carefully. It explains both terms.
Comment 5
Response 5
You are right that the citation is missing here. We will add the original ImageNet reference in the final version.
Comment 6
Response 6
The sentence you quote summarizes the procedure in Section 3.2.
We acquire the measure once on the source and deploy it directly on the target without target-side fitting. This distinguishes our method from target-specific optimization.
Your objection overlooks the full procedure given in Section 3.2.
Comment 7
Response 7
The manuscript provides definitions or references for the terms you identify.
Your description of these terms as undefined or uncited is inaccurate. They are established terms, metrics, and model names widely discussed or cited in the field.
Comment 8
Response 8
The “directly acquired power measure” is a single-parameter power schedule optimized on the source. The source search determines its exponent.
Section 5.3 reports that it retains 91.5%, 83.7%, and 91.8% of the four-interval gain on the three targets, respectively.