- Rating
- 3(+1)
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies the composition of diffusion models, aiming to sample from a composed distribution given access only to the scores of the individual constituent distributions. The authors propose a two-stage method. In the first stage, an existing composition method is used to obtain a set of anchor samples. In the second stage, these anchors are used to construct an empirical score estimate, which is then combined with the score from a single constituent model for sampling. The authors also provide theoretical analyses of the asymptotic estimation error and the optimal correction coefficient. Experiments include a 1D numerical simulation, classifier-free guidance (CFG) for image generation, and ligand generation.
Critical strengths
The paper is well written and easy to follow. The theoretical analysis appears to be sound and provides some insights into the asymptotic behavior of the proposed algorithm.
Critical weaknesses
-
I am skeptical about whether using only 4–16 anchor samples can provide sufficient information in practice, especially for high-dimensional data such as images, where the empirical score estimated from so few samples could be highly inaccurate. I also noticed that the metrics in Table 8 do not consistently improve as increases. In many cases, using more anchors actually leads to worse results. This makes me question whether these anchors really contribute positively to the generation process, or whether similar performance could be achieved using only a single constituent model without any anchors. I would suggest adding at least two simple baselines: (i) directly sampling from the constituent model used in Stage 2, without any anchors; and (ii) more generally, sampling from different constituent models with probabilities determined by the desired composition weights (assuming the weights are nonnegative, so this would not be suitable for extrapolative CFG). I think these trivial baselines are important for demonstrating the actual effectiveness of the anchors. Otherwise, neither my intuition nor some of the experimental results convince me that the anchors are really helpful.
-
The current experimental section lacks many essential configuration details. For example, which pretrained models and datasets are used for the CFG and ligand generation experiments? How exactly are CLIP Score, ImageReward (IR), and diversity computed? In particular, there are different conventions for computing CLIP Score, so which one is used in this paper? The authors should provide more detailed descriptions or appropriate references for these experimental settings and evaluation metrics.
-
Another observation is that the adaptive correction coefficient often performs worse than the constant coefficient in Tables 8 and 9. This also makes me question whether the theoretically derived adaptive coefficient is really necessary in practice. I would appreciate a more detailed discussion of this observation and the actual benefits of using the adaptive coefficient over a much simpler constant one.
-
For the CFG experiments, I think a vanilla CFG baseline is necessary. Specifically, the authors could directly sample using the extrapolated score and report the corresponding evaluation metrics. In addition, I think the image generation experiments should at least include FID results and some visual examples of the generated images.
Questions for authors
For the ligand generation experiments, how is the reference constituent model selected in Stage 2? Is it always the model conditioned on the first protein pocket, as in the other experiments? If so, since the target distribution is symmetric with respect to the two constituent models, I wonder whether choosing a different reference model would significantly affect the results.
8 comments
W1(b): Nonmonotonic Cache-Size Behavior and Independent Anchors
We agree that the nonmonotonic dependence on cache size deserves further investigation.
In our main image experiments, the anchors come from a single FKC/RNC particle population with resampling at every step. This can cause genealogical collapse, so increasing the nominal particle count does not necessarily increase the amount of independent information proportionally.
Furthermore, when the total sample count is fixed, increasing changes the proportion of Stage-1 and Stage-2 samples included in the evaluation. Thus, the original trends should not be interpreted as a direct measurement of estimator convergence.
To examine AmCo beyond the particle-collapse regime, we conducted an additional independent-FKC-anchor experiment (Appendix B.2, Table 12, Figure 8).
We independently run FKC 128 times with four particles per run, retaining one output from each. AmCo uses the first outputs as anchors and generates additional samples.
At , :
| AmCo IR | Matched CFG IR | AmCo Div. | CFG Div. | |
|---|---|---|---|---|
| 8 | −0.097 | 0.007 | 0.219 | 0.234 |
| 16 | 0.030 | 0.031 | 0.226 | 0.237 |
| 32 | 0.090 | 0.043 | 0.235 | 0.239 |
| 64 | 0.155 | 0.049 | 0.239 | 0.240 |
AmCo's ImageReward increases as increases in this setting. At and , it outperforms compute-matched CFG, with paired per-class improvements of +0.047 ± 0.021 and +0.106 ± 0.021, while maintaining comparable diversity.
We acknowledge that the improvement with increasing also reflects the changing Stage-1/Stage-2 sample proportions. Nevertheless, the matched-cost comparisons show that AmCo retains a practical advantage when using substantially more diverse, independently collected anchors.
We also acknowledge that eight anchors are insufficient to outperform CFG in this setting, and that full independent FKC achieves higher ImageReward (0.268) at considerably greater cost (2,048 evaluations/sample).
These findings clarify that small caches are not universally sufficient; anchor quality, diversity, and cache size all matter. Figure 8 additionally provides qualitative comparisons in this less-collapsed setting.
W2: Experimental Configurations and Evaluation Metrics
We agree that the original manuscript lacked sufficient implementation and evaluation details. We have substantially expanded the experimental specifications in Section 4.2 and Appendices B.2–B.3.
Image generation (Appendix B.2).
We use pretrained conditional and unconditional EDM2-XS ImageNet-512 models:
- Conditional:
edm2-img512-xs-2147483-0.045 - Unconditional:
edm2-img512-xs-uncond-2147483-0.045
Both operate on latents decoded into images using the Stable Diffusion VAE.
We evaluate 100 randomly selected ImageNet classes at , using FKC/RNC steps and AmCo steps. Appendix B.2 additionally specifies the noise schedule, finite-noise endpoint, resampling settings, and correction hyperparameters.
Metric definitions.
We now explicitly specify the CLIPScore convention of Hessel et al. (2021):
using OpenAI CLIP ViT-B/32, with the text prompt a photo of a <class name> and normalized image/text embeddings.
ImageReward is evaluated using the official ImageReward-v1.0 model (Xu et al., 2023). Diversity is defined as one minus the mean pairwise cosine similarity of CLIP ViT-B/32 image embeddings within each class.
We also specify the conventions for FID, FDDINOv2, CMMD, Inception Score, and ConvNeXt classification accuracy (Tables 5–8).
Ligand generation (Appendix B.3).
We use the target-aware molecular diffusion architecture of Guan et al. (2023). The revised appendix specifies the evaluated protein-pocket tuples, two- and three-pocket compositions, molecular size, sampling parameters, and categorical atom-type handling.
Docking is evaluated using Uni-Dock. We define over molecules binding all target pockets, and molecular diversity using Tanimoto similarity. Table 16 additionally reports validity and joint-binding success rates.
These revisions substantially improve the clarity and reproducibility of our experimental evaluation.
W1(a): Do the Anchors Provide Benefits Beyond Constituent-Only Sampling?
We thank the reviewer for raising this fundamental concern. We agree that estimating a high-dimensional clean-prediction field using only a small number of anchors is challenging.
Importantly, AmCo does not rely on the empirical cache alone. The anchors provide target-specific compositional information, while the reference-model correction incorporates the exact clean prediction from a pretrained constituent model. Nevertheless, we agree that the anchors' practical contribution must be verified experimentally.
We have added the requested constituent-only and constituent-mixture baselines (Tables 8 and 16).
Image generation (Table 8). We directly sample from the conditional constituent used as the Stage-2 reference, without anchors. At the same end-to-end budget of 78 model evaluations per sample, including AmCo's Stage-1 cost:
Thus, sampling from the reference constituent alone does not reproduce AmCo's task-specific performance.
For extrapolative CFG (w>1), the unconditional constituent has exponent 1−w<0; hence, the composition exponents cannot define nonnegative mixture probabilities. We instead evaluate ordinary extrapolated-score CFG directly (W4).
Ligand generation (Table 16). For product-of-experts composition, we additionally implement the requested constituent-mixture baseline. Each trajectory selects one pocket uniformly at random and samples using only that constituent. We also evaluate the first-pocket constituent and β-scaled ODE controls.
At matched total budgets of 314 evaluations/sample for I=2 and 447 for I=3, AmCo outperforms these controls in mean joint docking score across all 12 evaluated settings.
For example, at β=2.0, the three-pocket scores are 795.2 (AmCo), 679.8 (first-pocket ODE), and 636.6 (constituent mixture). AmCo also maintains high joint-binding success rates (Table 16).
Although these controls do not sample the exact product-of-experts distribution, they directly demonstrate practical benefits beyond constituent-only generation.
We believe these additions provide direct experimental evidence that the Stage-1 compositional information contributes meaningfully to AmCo's performance.