- Rating
- 1
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 1
- Soundness
- 1
Read review
Paper summary
MASS uses endpoint from the partially trained flow model to identify nearby real training examples, then solve a semi-relaxed entropic optimal transport problem on the resulting sparse graph. The fixed plan supplies training pairs during continuation. The paper proposes a threshold- for empirical target-marginal quality and evaluates coupling diagnostics, CIFAR-10 retraining, synthetic transport, and single-cell interpolation.
Critical strengths
-
In Table 3, shuffling the alignment leaves induced-target FID almost unchanged, 0.63 versus 0.64, but worsens retrained FID from 17.46 to 20.30. This supports the importance of the source-to-target correspondence beyond matching target statistics.
-
Figure 4 reports an actual continuation benefit. The five-seed single-cell experiment also reaches , comparable to exact global OT at (Section 4.3). The paper explicitly acknowledges its limited benefit with an already strong teacher.
Critical weaknesses
- Let and , as defined in Section 3.4. The proof of Theorem A.9 establishes and Corollary A.10 sets . However, \le \chi^2(\widehat p_1\|p_1) \le \|r-1\|_\infty^2 \le C_3^2\Delta^{1/(d+1)}.$$ The first inequality follows from $\log r\le r-1$ and normalization of both densities. Consequently, $$\Delta_\star =\Delta-a_3\Delta^{1/(d+1)} \le -2\Delta<0.$$
This leads to, the required premise in Theorems 3.3/A.12 can't hold with the constants supplied by the proof. Naturally, all anlaysis in the paper simply unreliable. Appendix A.6 checks graph feasibility directly and does not demonstrate a nonvacuous instance of A.12. This
- SD-FM[1] already precomputes a dataset-wide coupling potential, including for MeanFlow. COT-FM [2] uses a pretrained flow to construct reusable OT maps to real data. These methods are absent from the positioning and experiments. Including these previous works completely voids the proposed novely in thi spaper.
-
Eq-14: Lipschitz densities give an small-ball remainder, rather than the stated . The weaker remainder appears compatible with the subsequent cross-mass rate.
-
Appendix B: Algorithm 3 relaxes the source marginal and fixes the target, whereas Equation (6) and Algorithm 4 fix the source and relax the target. Explain this change of orientation.
-
Table 2 assigns practical MAC an cost, but its Section 3.2 scores sampled candidate pairs [3]. Section 5 also incorrectly states that Spar-Sink necessarily shifts both marginals, its balanced version enforces both prescribed marginals when feasible and converged [4].
[1] Mousavi-Hosseini et al. Flow Matching with Semidiscrete Couplings, 2025. https://arxiv.org/abs/2509.25519
[2] Chiang et al. COT-FM: Cluster-wise Optimal Transport Flow Matching, 2026. https://arxiv.org/abs/2603.13395
[3] Lin et al. Beyond Optimal Transport: Model-Aligned Coupling for Flow Matching, 2025. https://arxiv.org/abs/2505.23346
[4] Li et al. Importance Sparsification for Sinkhorn Algorithm, JMLR, 2023. https://www.jmlr.org/papers/v24/22-1311.html
Questions for authors
-
Please address the inequality in Weakness 1 explicitly. Can you provide a nonvacuous replacement for Theorem A.12.
-
Can you extend the minibatch-OT and random-support controls to the common 400k horizon and compare against a directly relevant global method. eg: SD-FM or COT-FM.
-
Which endpoint budget was used for Figure 4 and Table 6: from Section 4.2 or from Appendix C.1?
Please state whether MASS and reflow use identical teacher endpoints and separate the costs of endpoint generation, IVF search, Sinkhorn iterations, and continuation. Clarify which costs the advertised complexity includes.