- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
Under the "common-cause" assumption, this work establishes that the non-locality window—the period during which non-local features influence generation—must lie within the speciation window, during which class-label information influences generation.
Critical strengths
This paper makes an interesting connection between non-local feature influence and label influence. The authors provide substantial theory under certain assumptions, and the derivation is theoretically correct. The authors also perform an empirical study to validate their theory.
Critical weaknesses
Questioning assumptions made by the authors
1. Common cause Assumption (Misleading naming convention. This implies completely different things in the causality literature.)
Even when a semantic variable S is a genuine common cause of regions A and C, conditioning on the intermediate region B can preserve or increase their residual dependence, violating the proposed inequality. Therefore, under the "common-cause" assumption,
does not always hold.
2. The empirical justification that Eq. (1) holds true for natural images is incorrect
The experiments on Stable Diffusion 3 measure reductions in the local–global velocity prediction gap rather than the CMI quantities appearing in the hypothesis. A reduction in the prediction gap does not necessarily imply a corresponding reduction in CMI. Therefore, the empirical evidence does not directly establish that Hypothesis 1 holds for natural images.
How does this assumption hold in practice? Here is what the authors claim:
But observing
does not imply
The authors should provide more direct validation of the assumption or clarify the limitations of applying the containment theorem to realistic data distributions. Based on Hu et al., for natural image datasets (for example, CIFAR), relying on the mentioned results, I would request that the authors provide evidence for all time steps .
3. Core gap suppression assumption also does not hold.
This assumption is not always true and does not hold for all annulus tripartitions.
Counterexample: A zebra with black and white stripes. Imagine a close-up photograph of a zebra. : A small patch of its body, potentially containing a black or white stripe. : The surrounding annulus, containing nearby stripes and texture. : A distant patch of the same zebra's body. : The semantic label describing a particular stripe pattern, such as "the two selected patches have opposite colors."
Minor Corrections
-
L32: "Such features must therefore emerge during inference." How do the authors validate this claim? The "must" claim does not hold.
-
"Generation of a pixel is determined by its neighborhood and not the image" (Kamb and Ganguly, 2024). The attribution is wrong. The cited work establishes that, under a locality constraint, the instantaneous score prediction at a pixel depends only on its local neighborhood. This does not imply that the final generated pixel is independent of global image information, since information can propagate through successive denoising steps. Furthermore, the analysis primarily concerns convolutional diffusion models and does not establish this property for diffusion models in general. The authors should clarify this distinction and qualify their claim accordingly.
-
The authors push all the relevant experiments into the appendix, which is a slight abuse of the paper limit.
References
Hu et al., Local Diffusion Models and Phases of Data Distributions.
Questions for authors
Addressing all the weaknesses will answer all my questions. I would be willing to raise my score if the authors provide appropriate reasoning for the weaknesses.
2 comments
Rebuttal part 2
3. "Score gap suppression assumption also does not hold." (Weakness 3)
The score-gap suppression inequality appears only in Section 3.1, inside a heuristic argument that motivates the information theoretic version (i.e., Hypothesis 1); no theorem uses it. Its only role is to give the intuition in operational terms, through the score function. We remark that Theorem 1 relies only on Hypothesis 1, and only for the tripartition to which it is applied: the theorem fixes one annulus tripartition and does not assume the hypothesis for all of them.
We also stress that we do not claim nor need the information theoretic assumption (Hypothesis 1) to hold for every distribution and label. Hypothesis 1 is a sufficient condition. It isolates one mechanism, the label accounting for a fixed fraction of the long-range conditional dependence, under which the nonlocality window must lie inside the speciation window. A sufficient condition is informative precisely because it is not universal. It tells us which distributions should show concurrence and which fall outside its scope: labels that are redundant across regions satisfy the hypothesis, while synergistic labels, such as parity, counts or relational labels, can violate it, and there concurrence is not guaranteed (Section 3.2.3).
Revision. We will state in Section 3.1 that the score-gap suppression inequality is a heuristic that fails for synergistic labels.
4. Minor points
(a) L32, "Such features must therefore emerge during inference." This sentence states an obvious logical consequence. Generation starts from noise, which carries no semantic structure. A sampler that reproduces a distribution with semantic structure must output samples that have this structure, so the structure must appear at some point during generation.
(b) Attribution to Kamb & Ganguli. We agree that "generation of a pixel" was ambiguous. We mean the single-step denoiser that updates the pixel during generation, not the distribution of the pixel at the end of generation, and this is the sense in which Kamb & Ganguli (2024) establish locality. Overlapping local denoisers can create long-range correlations over many steps, for example because each pixel's dependence region grows with every step.
(c) Experiments in the appendix. The central experiment supporting Hypothesis 1, Figure 2, is in the main text (Section 3.2.3). The appendices contain implementation details and complementary forward–backward experiments (Appendix B). As the paper is theoretical, we kept the main text focused on the theoretical contribution.
Revision. We will rephrase L32, replace "generation of a pixel" with "the denoiser update of a pixel".
Rebuttal part 1
Thank you for the review, and for finding the connection between nonlocal feature influence and label influence interesting and the derivations correct. We address your concerns in four points.
1. "Common cause Assumption (Misleading naming convention. This implies completely different things in the causality literature.)" (Weakness 1)
We acknowledge that "common cause" has a different meaning in causal inference. We are happy to rename the assumption to avoid this confusion. We stress that we did not state or use that Eq. (1) is implied by causal-inference "common cause", and note that our claims and results are not invalidated by this point.
Revision. We will rename the assumption, and state the scope of the hypothesis explicitly.
2. "A reduction in the prediction gap does not necessarily imply a corresponding reduction in CMI." (Weakness 2)
We agree that a smaller prediction gap does not establish the CMI inequality, as stated in Appendices D and G (and we will stress this more in the main text). We did not claim that Eq. (3) turns a reduction in the score gap into the CMI reduction required by Hypothesis 1.
Why score gaps. A direct test would estimate It(A;C∣B,S) and It(A;C∣B) from samples of high-dimensional images, which is notoriously hard: without strong assumptions on the distribution, no estimator can reliably measure, or even certify, such quantities from a feasible number of samples (McAllester & Stratos, 2020; Poole et al., 2019; Shah & Peters, 2020). Score gaps are also the more relevant quantity: the locality gap is proportional to the extra denoising error on A from replacing the global denoiser with the best local one (Appendix A.4, "Bounding Local Denoiser Error with CMI"). A smaller conditional gap therefore means that, once the label is supplied, a local denoiser loses less relative to the global one. In Stable Diffusion 3 Medium (Figure 2 in Section 3.2.3; setup and limitations in Appendix D), we measure the change in prediction when image–image attention is restricted to a 15×15 token neighborhood, along the same generation trajectories with and without the scene description (64 scenes, three nested description lengths, three seeds each).
Why we do not report direct estimates of α. Hu et al. (2025) estimate It(A;C∣B) with MINE for a single-pixel A on MNIST and Fashion-MNIST, without labels, and find it small at both ends of the trajectory with a peak at intermediate times. We attempted the label-conditional extension, estimating 1−It(A;C∣B,S)/It(A;C∣B) with the same estimator, but the estimates were not stable enough to bound α. This is expected. Each CMI is estimated as the difference of two variational lower bounds on mutual information, which is a bound in neither direction, and these lower bounds have high variance (Song & Ermon, 2020). The ratio is moreover ill-conditioned wherever It(A;C∣B) is small, which includes both ends of the trajectory. We therefore test the hypothesis through its operational counterpart, the score gap, and stress that Figure 2 is only consistent with Hypothesis 1, as stated in the caption of Figure 2.
Revision. We will re-emphasize the limitation of Figure 2 in Section 3.2.3 and list a direct estimate of α on natural images as an open problem, as already implied in the limitations (Appendix G).