- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes G-LZN, in which an encoder predicts anchors and analytic inverse flow matching (IFM) constructs latent regions. Reconstruction training connects the encoder and decoder, while generation requires a single decoder evaluation. The experiments demonstrate strong generation results and several image-editing capabilities.
Critical strengths
-
Self, recursive, and weighted zoning adapt the original latent zoning approach to standalone generative modelling. This is an interesting stochastic posterior construction worth exploring.
-
The generation results are strong, and the paper includes multiple training seeds and component ablations, supporting effectiveness and training stability in the tested configurations.
Critical weaknesses
-
The value of the added complexity is insufficiently established. Compared with a conventional VAE, the method adds an IFM flow module requiring numerical integration and backpropagation, while removing an explicit KL term that is computationally inexpensive. Without comparisons against strong baselines at the same computational budget, it is unclear whether the performance gains justify the additional computational and methodological complexity. This concerns the necessity of the added machinery, rather than merely missing cost reporting.
-
A validation gap remains between the theory and the implementation. The theory assumes ideal latent regions, whereas the implementation uses finite smoothing and Euler integration. Region quality, the constant-KL property, and reversibility have not been sufficiently validated under these approximations. FID results and overall gradient curves do not directly answer these questions. The applicability of the guarantees to the implementation therefore remains unclear; this does not establish that numerical failures actually occur.
Overall assessment: The method has potential, but the necessity of its added complexity and the practical scope of its theoretical guarantees are not sufficiently supported. I lean toward weak rejection; clarification and targeted validation could change my assessment.
Final assessment after the author discussion
Thank you for the additional experiments, the compute analysis, and the explicit discussion of the reconstruction limitation. The compute analysis addresses my concern about the additional training FLOPs of increasing the latent dimension. Taking these clarifications and the supporting experiments into account, I have increased my rating from 2 to 3 (weak acceptance). Reconstruction fidelity on ImageNet with larger latent dimensions remains experimentally unverified. If the paper is accepted, the authors should complete this evaluation for the final version, reporting PSNR and LPIPS together with the computational cost at different latent dimensions.
Questions for authors
-
Relative to LZN, DDVI, and related methods, what are the most important new technical elements and practical benefits?
-
At the same computational budget, does the added IFM module still yield clear benefits over a conventional VAE and stronger variational posterior baselines?
-
How do the smoothing parameter g, Euler step count, and recursive depth affect actual distributional error, reversibility, and gradient stability? How should the constant-KL result be interpreted for the implementation?
2 comments
Rebuttal (2/2)
| W2/Q3 | Finite smoothing and Euler integration |
|---|
We thank the reviewer for this insightful comment. We have added a new appendix section (Appendix F.13, "Approximation Error of the Implementation") that quantifies the gap between the theory and the implementation on the released CIFAR-10 model, with no retraining. We sweep each of the three parameters the reviewer names, the smoothing parameter , the number of Euler steps, and the number of latent zoning layers , one at a time around the training configuration, and we measure a superset of the quantities the reviewer asks about: distributional error, zone quality, the KL bound, reversibility, gradient stability, and end-to-end reconstruction quality. All error measurements are made against float64 reference solutions that are themselves cross-validated. The main findings:
-
Distributional error (Figure 35). At the training configuration, the latents deviate from the exact map by a median relative error of 2.7%, and the error decreases linearly with the Euler step size. The error accumulates only mildly across layers (1.0% at to 2.7% at , far below worst-case compounding), and has almost no effect (changing by two orders of magnitude changes the exact map itself by only ).
-
Zone quality (Figure 36). At the training configuration, a layer's output lands in the correct zone of that layer's own anchors 91.6% of the time at the final layer, and all 15 layers are simultaneously correct for 24.8% of the samples; both improve monotonically with more steps (100% and 92.1% at 1,000 steps), so the leakage is mainly a discretization effect. Importantly, training does not rely on this within-sample zone separation; it only requires that the zones of different images do not overlap, which the reconstruction loss directly pushes for. The decoder is trained against the same 50-step map, so it fits the 50-step zones, and Figure 40 shows this carries no measurable end-to-end cost.
-
KL bound (Figure 37). This addresses the question of how the constant-KL result should be interpreted for the implementation. We prove in Appendix F.13 that finite smoothing preserves the bound for any (zone overlap can only make the actual smaller, so the bound in Corollary 1 remains valid and conservative). Euler discretization is the remaining approximation. As a diagnostic of its transport error, the moment-based Gaussian between the numerically transported mixture and the prior is 0.27 nats at the training configuration, versus a 0.08-nat sampling-noise floor, and converges to that floor with more steps. This diagnostic does not directly estimate the conditional ; the conditional guarantee under exact finite-smoothing integration instead follows from the analytical bound above.
-
Reversibility (Figure 38). The smoothed ODE flow remains mathematically reversible under exact integration; Fig. 38 measures the additional numerical round-trip error introduced by finite-step Euler integration. A single layer inverts cleanly: the round-trip error is 0.044 at 50 steps and decreases linearly with the step size. Inverting the full 15-layer chain is ill-conditioned, for a structural rather than numerical reason: each layer stores the incoming sample at scale , so the inverse divides by and amplifies any integration error (the measured error scales exactly as ). This reverse integration is not used by the model: native image inversion and editing use the encoder-produced latents directly, while generation is a single decoder evaluation of a prior sample.
-
Gradient stability (Figure 39). The largest singular value of the Jacobian of the zoning map is flat at about 2.2 across all three parameter axes (worst sample 3.1), showing that backpropagation through Euler steps does not exhibit exploding sensitivity. Together with the stable empirical gradient curves reported in the paper, this supports stable optimization of the zoning module.
-
End-to-end effect (Figure 39). Reconstruction FID, computed with the same FID implementation as all FID numbers in the paper, is flat for 25 or more Euler steps (1.73 to 1.80, with the training configuration in the flat regime), and is irrelevant to four decimal places across three orders of magnitude. The deviations measured above therefore carry no measurable cost on the inference path that uses the zoning integration.
In summary, the approximations affect the implementation in small, converging, and well-understood ways. Within-sample zone leakage incurs no measurable reconstruction cost, while numerical full-chain reverse integration is not used by either training or generation. We have added all of these results to the revised paper in Appendix F.13.
Rebuttal (1/2)
We thank the reviewer for recognizing self, recursive, and weighted zoning as an interesting stochastic-posterior construction for standalone generation, as well as the strong generation results and multi-seed and component-ablation evidence supporting effectiveness and stability.
We have revised the manuscript in response to the reviewer’s comments, with all changes highlighted in red.
We welcome further discussion and are available to address any remaining questions.
The submission already includes a controlled VAE comparison. Appendix F.8 compares G-LZN and VAE under identical CIFAR-10 settings, differing only in the use of KL loss (VAE) versus the latent zoning mechanism (G-LZN). To ensure a fair comparison, we tune the VAE's KL weight over 12 values ranging from 10−6 to 5×10−3.
Latent zoning is more stable and achieves better FID in this setting. The VAEs show frequent loss and gradient-norm spikes (Fig. 22), while G-LZN remains smooth (Fig. 23); the best VAE obtains FID 9.23 versus 6.80 for G-LZN (Table 7). We have summarized this conclusion in Secs. 4.3--4.4.
G-LZN performs better than VAEs under the same training compute. Following the reviewer's suggestion, we additionally compare the FID scores of G-LZN and VAEs across all KL weights at equal training times in Fig. 25 of the revision. G-LZN consistently achieves lower FID than all VAEs at any given training time. Moreover, latent zoning is computationally lightweight, requiring only element-wise arithmetic on 50-dimensional latents without neural network evaluations inside the integration loop. Consequently, G-LZN incurs only a 16.5% increase in per-iteration training time compared with VAEs.
G-LZN also achieves a better compute-quality trade-off than a stronger variational-posterior baseline. The reviewer also requests a comparison with "stronger variational posterior baselines" in Q2. LSGM in Table 2a is one such baseline, employing a hierarchical variational posterior and a diffusion-based prior, both more expressive than those in conventional VAEs. We follow the FLOP-accounting convention in Appendix F.12: for G-LZN, we use the first checkpoint that reaches FID 2.10 and multiply its iteration count by the measured per-step FLOPs; for LSGM, we multiply the official iteration count by the per-step FLOPs measured from its official configuration. At the same FID of 2.10, G-LZN requires only 80% of LSGM's training compute (5.26×1019 vs. 6.61×1019 FLOPs; Appendix F.8).
G-LZN turns LZN into a standalone generator. Self-latent zoning removes minibatch dependence, while recursive and weighted zoning make very small zones practical. Consequently, whereas LZN can only improve an existing diffusion model, G-LZN samples directly from a Gaussian prior as a standalone generative model.
G-LZN and DDVI differ in both their approach and practical benefits.
We thank the reviewer for pointing us to this important related work and have expanded Appendix A (Related Work) to discuss this method explicitly.