- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper designed a flow matching approach to generate manifold constrained data with application to robotics. This paper designed an attraction along the normal direction to push the distribution toward the manifold. The paper is interesting but lacks some theoretical justification.
Critical strengths
The approach is new and interesting.
Critical weaknesses
Theoretical soundness:
-
Around line 157, the author stated that is embedded in Euclidean space, and tubular neighborhood guarantees uniqueness of projection. Is this a fact, i.e., for any embedded manifold there exists such a tubular neighborhood? If yes, is there a proof or reference to it? If no, is there any additional condition on so that it is true?
-
line 290: "Suppose the solution of (4) remains in U": I think the paper should establish under what conditions the trajectory / solution would remain in U.
-
If during sampling process, there exists a pair s.t. , either because of Gaussian as prior so that it's outside the tubular neighborhood, or due to the solution of (4) fails to remain in U, what would happen? Furthermore, would this cause bad regularity of the vector field, or some instability?
-
If a Gaussian prior is used in flow matching, will this violate the tubular neighborhood condition?
-
In flow matching, the population / true vector field (i.e. the exact minimizer of (1) in the submitted paper) can be written as . Is there any similar formula for the proposed approach? If yes, does it rely on the tubular neighborhood?
Presentation:
-
The paragraph (line 162) "Why conventional flow matching does not imply stability." is difficult to follow. I suggest to remove the shorthand and use throughout, and emphasize what is distance shrink and why it matters. Also, I don't think adding a dot on top of is a good notation. If it represent time derivative, I suggest to simply wirte time derivative. It's a bit unclear to me by saying "only the normal component of the velocity matters", "this rate", "this pointwise condition".
-
Equation 4: I think there should be an intutive explanation for it. is not intuitive (e.g., what it is, why it is needed, how you set it in practice?). Also, I suggest change the notation to something else or just remove that shorthand. What I mean is that, when I first look at the equation it's unclear to me what the term is, and whether is a normal vector; on the notation side perhaps stand for normal, or some could make it clear.
-
What does "define" mean in line 189? Is it specifying by an initial value?
-
line 196: when "integrating this prescribed linear ODE" is needed? Will this be expensive?
-
Section 4.2 is difficult to follow.
Possibly related work:
- A paper last year https://arxiv.org/pdf/2510.22044 seems share some similarity. I think this worth a discussion.
Questions for authors
See weakness.
Some other questions:
-
I have concerns about how difficult it is to compute time derivative of .
-
The normal direction is by construction and only tangent direction require neural network approximation?
Remarks: I am not familiar with robotics, which appears as an application of the proposed approach. Therefore, my review is on the theoretical side of the proposed approach, not to assess or judge its practical performance or applicability. I will raise my score if the presentation can be improved and the theoretical soundness question can be addressed.
3 comments
Response to Reviewer aerv (2/3)
T4 (Gaussian prior): Does a Gaussian prior violate the tubular-neighborhood condition?
Response. Thank you for this comment. A Gaussian prior has full support, so some samples can lie outside any fixed-width neighborhood of a curved manifold. For a fixed affine proxy, this is not an issue, since its projection is defined everywhere. Following the revisions addressing the preceding comments, we now explicitly describe how to extend the manifold-convergence guarantee to any ambient prior, including a Gaussian prior, under the conditions stated in Appendix A (a known safe width around the manifold, an anchor on the manifold for each sample, and the same conditions on the contraction rate and the network as in Theorem 1).
Samples already within the fixed width can initialize MSFM directly. For samples farther away, an outer stage contracts each sample toward its selected anchor until it is closer to the anchor than the fixed width in Theorem 1. MSFM then runs inside U, where invariance and prescribed normal contraction ensure convergence to the manifold. Appendix A provides the construction, assumptions, and entry criteria, and notes that training must then use the distribution of samples after the entry step. For the rotation manifold SO(3), we further show that the guarantee holds for almost every initial matrix, so a Gaussian prior needs no extra step there (Appendix B). In our revised Square experiment, the rotation source is not Gaussian: every source rotation block lies inside the tube, so Theorem 1 and Lemma 1 apply directly (Appendix H).
T5 (population field): Is there an analogue of for MSFM, and does it rely on the tubular neighborhood?
Response. Thank you for this question. Yes. For square-integrable training velocities and a model class that can represent the optimum, the population-optimal MSFM output is where and are determined by the current state. This follows directly from Proposition 1: regression learns the tangential conditional mean, while the normal component is prescribed. Here, is the training-path velocity; it equals for linear paths.
Under normal compatibility, , this expression reduces to , recovering the usual flow-matching marginal field. Recovering the target distribution additionally requires the learned field to have unique solutions, as in standard flow matching.
The conditional-mean identity itself does not require a tubular neighborhood. For a known curved manifold, the geometric quantities must be defined; smooth projection is guaranteed within U. For a fixed affine proxy, they are globally defined. Whether this field equals the usual flow-matching field does depend on the neighborhood. For a curved manifold, we prove this equality when the source lies within the fixed width of Theorem 1 (Lemma 1 in Appendix C). For SO(3), we prove it for almost every source matrix (Appendix B). We have added this characterization immediately after Proposition 1.
P1 (line 162 paragraph): Hard to follow; use and an explicit time derivative instead of ; clarify "this rate" and related phrases.
Response. Thank you for pointing this out. We have rewritten this paragraph using squared distance directly and an explicit time derivative. It now explains that tangential velocity makes no contribution to the distance derivative, while inward normal motion reduces the distance and corrects off-manifold deviations. We also state that FM training and inference do not control this rate, so the distance can grow at some sampling states.
P2 (Equation 4): Explain intuitively and how it is set; clarify whether is a normal vector.
Response. We now call the normal residual and explain that its length is the distance to the manifold. Equation 4 labels the tangential and normal terms with parallel and perpendicular notation. The text explains that the network learns tangential motion, while the prescribed normal term pulls samples toward the manifold. The rate controls the strength of this attraction. We give as a practical example and point to Section 4.4 and the experimental appendices for the schedule and settings.
Continued in part 3 (reply below).
Response to Reviewer aerv (3/3)
P3 (line 189): What does "define" mean? Is specified by an initial value?
Response. Yes. The initial normal residual is fixed by the source sample: . The ODE then determines its value along the chosen base curve. We replaced “define” with “Obtain the normal residual by integrating the ODE” and made this construction explicit in Section 4.1.
P4 (line 196): When is integrating the prescribed linear ODE needed, and is it expensive?
Response. This ODE is used to construct training pairs. Numerical integration is needed for a general curved geometry when its solution is not available in closed form. The affine proxies and the SO(3) construction used here have explicit solutions, so they require no additional numerical ODE solve for the training path. For other geometries, the cost depends on the geometry and numerical solver. We have clarified this in Section 4.1.
P5 (Section 4.2): Section 4.2 is difficult to follow.
Response. We have added short explanations of the local PCA proxy, its tangent and normal projectors, and the normal residual. The revised text describes how the field combines learned tangential motion with attraction to the selected proxy. Additionally, we added Figure 2 in Section 4.2 to visualize the mathematical terms used in constructing our MSFM formulation.
R1 (related work): arXiv 2510.22044 seems similar and is worth discussing.
Response. Thank you for this reference. We agree that OLLA shares the idea of tangential motion combined with prescribed normal correction. OLLA uses Langevin dynamics with a specified target density and constraint functions, and proves convergence to the constrained target distribution under its assumptions. MSFM learns transport from data samples using analytical projectors or local PCA proxies. We now cite Jeon et al. (2025) and discuss this relationship in Related Work.
Q1 (time derivative of ): How difficult is it to compute the time derivative of ?
Response. Thank you for raising this concern. Section 4.1 now clarifies that is needed only to construct training targets, not during inference. For a general smooth known manifold, only the product is required. It can be evaluated analytically or by directional automatic differentiation along the base curve, holding the residual fixed, without forming the full projector Jacobian. Its cost depends on the geometry. For each fixed affine proxy, . For SO(3), the explicit path in Appendix B is differentiated directly to obtain the training velocity, avoiding explicit evaluation of and an additional numerical ODE solve.
Q2 (normal vs. tangent): Is the normal direction set by construction, with only the tangent direction learned by the network?
Response. Yes. The normal velocity is prescribed by the geometry and contraction schedule. The network affects only the tangential velocity through . Proposition 1 shows that only the tangential loss depends on the network parameters.
Response to Reviewer aerv (1/3)
We thank the Reviewer for their critical reading and constructive criticism. Revisions are highlighted in blue; see our general comment for a summary. Labels follow the review: T = Theoretical soundness, P = Presentation, R = Related work, Q = Questions.
T1 (tubular neighborhood): Does every embedded M have a tubular neighborhood with a unique projection? Proof, reference, or extra conditions?
Response. We thank the Reviewer for their comment. Yes, every smooth embedded submanifold of Euclidean space without boundary admits a sufficiently small tubular neighborhood in which the nearest-point projection is unique and smooth. See Theorem 6.24 and Problem 6-5 in Lee, J.M. (2012). Sard’s Theorem. In: Introduction to Smooth Manifolds. Graduate Texts in Mathematics, vol 218. Springer, New York, NY. We stated these assumptions explicitly and added this reference to the manuscript.
The width of this neighborhood may vary along the manifold. A neighborhood of fixed positive width, which the revised Theorem 1 uses, always exists when the manifold is compact, but compactness is not necessary (as in the case of our noncompact manifold R3×SO(3)×R for Square actions, for which 2 is the fixed positive width).
T2 (staying in U): Establish under what conditions the solution of (4) remains in U (line 290).
Response. Thank you for this comment. The revised Theorem 1 now proves this instead of assuming it. Suppose every point closer to M than some fixed width has a unique, smooth nearest point on M. Then every trajectory that starts closer than this width stays closer for all flow times, and hence stays in U. The reason is that the distance to M cannot increase along the MSFM field, so the trajectory can never reach this width. The argument uses only this distance estimate, so it does not need uniqueness of solutions. Under mild conditions on the network, namely continuity and at most linear growth, the theorem also shows that these solutions exist up to the terminal time. Such a width always exists when M is compact; compactness is not necessary, and we give a noncompact example after the theorem (which is used in our Robomimic Square task). The proof is in Appendix E.
T3 (leaving U): What happens if xt∈/U, from a Gaussian prior or from leaving U? Does this cause poor regularity or instability?
Response. Thank you for this comment. By the revised Theorem 1, trajectories that start within the fixed width described in our preceding response remain there. The remaining issue is initialization farther from the manifold. We added a short explanation in the main text and a new Appendix A to specifically address this comment. We describe an optional step before MSFM sampling. First, choose an anchor for each sample and keep it fixed. Move the sample straight toward this anchor until it is closer to the anchor than the fixed width in Theorem 1. Then start MSFM sampling. With this step, any ambient prior can be used, including a Gaussian.
Appendix A states the required assumptions, explains why samples enter the region, and gives examples of suitable regions.
Continued in part 2 (reply below).