- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper primarily studies the effects of couplings on generation in one-step generative models under ( ) endpoint regression. In addition, the authors provide experiments involving non-( ) endpoint regression.
Critical strengths
This paper is easy to follow, and the theory is mostly solid under the constraints and settings imposed by the authors.
Critical weaknesses
Novelty
The effect of couplings on one-step generation has already been studied in various papers. For example, for independent couplings is well known, and previous papers have also identified this collapse. Similarly, it is straightforward from optimal transport and diffusion distillation that for deterministic couplings. However, mixtures of these couplings are not commonly studied.
The main result in C1 appears to follow directly from classical regression theory and the law of total variance. The characterization of collapse through conditional mean independence is closely related to the established correlation ratio (Rényi, 1959; Sampson, 1984). Furthermore, Shou (2026, Theorems 1–2) already establishes mean collapse under independent endpoint pairing and characterizes the optimal flow map using conditional expectations. The deterministic-coupling result also follows immediately from this characterization and is consistent with earlier rectified-flow and distillation work (Liu et al., 2022). While the distinction between conditional mean independence and full independence is useful, it is unclear what fundamentally new theoretical insight C1 provides beyond these established results.
The applicability of the theory to batch OT remains unclear, as batch OT does not necessarily satisfy the assumption that the coupling is a linear combination of deterministic and independent couplings.
The value of depends on the determinism of the coupling. Two arbitrary couplings can have and while having different transport costs. However, at the infimum of the transport cost the transport becomes deterministic, and therefore . This does not imply a general relationship between and the transport cost. The authors appear to conflate the relationship between coupling distance and while attempting to establish that no such relationship exists. Although the counterexample in Figure 1 illustrates this distinction, its necessity and additional contribution are unclear.
The authors should clarify what they intend to establish by demonstrating that $ \rho^* $ spans the entire interval , given that the two extreme cases ( and ) are already sufficient to establish non-identifiability and the minimax lower bound. Furthermore, the practical relevance of the proposed Bernoulli-mixture coupling, which randomly switches between independent and deterministic source–target pairings, remains unclear. Is such a coupling used in existing one-step generative modeling methods, or is it purely a theoretical construction? What additional theoretical insight or practical significance does this interpolation provide beyond the two extreme cases?
Finally, the authors provide experiments involving objectives other than endpoint regression, but little theoretical analysis or explanation of these results is provided.
Writing
The authors use inconsistent notation in multiple sections of the paper. Random variables are sometimes represented by lowercase letters, making the paper difficult to follow.
L17: "sufficient but unnecessary" is not standard mathematical terminology. I assume the authors meant "sufficient but not necessary."
References
- Shou (2026), ODE-free Neural Flow Matching for One-Step Generative Modeling.
- Liu et al. (2022), Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow.
- Rényi (1959), On Measures of Dependence.
- Sampson (1984), An Inequality for Correlation Ratios.
Questions for authors
The authors have developed a theoretical characterization of these coupling combinations. However, how this theory contributes to designing better couplings or extends beyond endpoint regression remains unanswered.