- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper addresses the limitations of existing MOF generative models in precisely controlling small pore apertures. To address this challenge, the authors propose CoFi-MOF, a coarse-to-fine generation framework that combines global pore-geometry generation with local structural refinement. Specifically, the framework consists of three main components. First, a Periodic U-DiT generates target-conditioned pore geometries in a signed-distance-field latent space while incorporating periodic spatial relationships. Second, a topology-aware Constructor maps the generated geometries into discrete MOF structures by predicting node and linker assignments. Third, the authors introduce a verifier-guided refinement procedure that uses Zeo++ to select promising candidates and a Multi-Edit-Former (MEF) to propose target-directed linker modifications, followed by reassembly and geometric verification.
Additionally, the authors introduce MOF-Edit-DB, a large-scale dataset of MOF structures and linker-edit responses, to support the training of the editing model. Experimental results demonstrate substantially improved pore-size targeting compared with the evaluated baselines,
Critical strengths
-
Strong experimental performance. The proposed framework substantially improves pore-size targeting accuracy over existing MOF-generation methods, demonstrating its effectiveness.
-
Comprehensive ablation studies. The paper provides detailed ablation experiments that clearly illustrate the contributions of different components, particularly geometric verification and MEF-based linker refinement. These experiments clarify where the performance improvements come from and strengthen the empirical evaluation of the proposed framework.
Critical weaknesses
- The performance improvements are largely dominated by geometric verification rather than the proposed neural architectures.
- The comparisons with existing methods may not sufficiently isolate the proposed methodological contributions.
- The generated structures exhibit limited robustness after force-field relaxation
Questions for authors
-
According to Table 2, introducing Zeo++-based verification increases [email protected] from 17.56% to 83.40%, while MEF provides a further improvement to 88.15%. Given that most of the improvement comes from verification-based candidate selection, could the authors further clarify the contributions of Periodic U-DiT and the topology-aware Constructor to the final PLD-targeting performance? In particular, how much improvement would remain if the proposed architectures were replaced with the original MOFFUSION components under the same verification protocol?
-
Similarly to the previous question, could the authors provide comparisons under matched candidate counts and Zeo++ evaluation budgets? It would also be helpful to report how [email protected] changes as the number of evaluated candidates increases, to distinguish improvements from learned generation versus inference-time search.
-
While the experiments demonstrate that MEF outperforms random editing, it remains unclear whether the proposed joint editing architecture is necessary for these improvements. Could the authors provide ablation studies on the unary, pairwise, and global scoring components, or comparisons with simpler learned property-prediction and ranking baselines?
-
Appendix E.4 reports that CoFi-MOF's [email protected] decreases from 93.6% to 20.9% after force-field relaxation. Since accurate pore-size control is central to the paper's motivation, could the authors discuss whether the framework can directly optimize relaxed PLD rather than unrelaxed geometry? What are the main challenges in incorporating relaxation-aware verification or editing into the proposed pipeline?
6 comments
Dear Reviewer xonu,
Thank you again for your thoughtful and constructive feedback, which has helped us substantially strengthen our paper.
As the discussion period approaches its November 18 deadline, we would like to briefly highlight the new evidence addressing your central concerns.
Most importantly, our matched-budget comparison shows that CoFi-MOF retains a 9.24-percentage-point advantage over MOFFUSION (83.34% vs. 74.10% [email protected]) even without MEF, under the same Best-of-25 verification protocol. This provides direct evidence that the learned candidate-generation pipeline contributes beyond Zeo++-based selection alone. We have also added comparisons with simpler learned edit-ranking baselines, where MEF achieves 70.59% versus 39.39% Top-1 [email protected], further clarifying its contribution.
We sincerely appreciate your time and careful consideration. If you have any remaining concerns, we would be grateful for the opportunity to address them before the discussion closes. We hope these additional results and clarifications provide a stronger basis for reconsidering your initial assessment.
Thank you once again for your valuable feedback.
Thank you to the authors for the detailed clarifications and additional experiments. I appreciate the efforts to address my concerns. However, the substantial decrease in [email protected] after relaxation suggests that accurate control of unrelaxed pore geometry does not necessarily translate into reliable control of physically relaxed structures. This discrepancy remains a significant concern and leaves me uncertain about the strength of the paper's conclusions regarding practical pore-size control.
Response to Reviewer xonu
Dear Reviewer xonu, thank you for your constructive feedback. We address your questions with new experiments and quantitative analyses below, revised is highlighted in blue.
Verification evaluates candidates, whereas Periodic U-DiT and the topology-aware Constructor determine which candidates exist to be evaluated. Periodic U-DiT generates a target-conditioned continuous SDF, which admits multiple discrete atomistic realizations with distinct pore apertures. Constructor maps this SDF to ranked discrete assignments, and Zeo++ resolves the remaining geometric ambiguity. Controlled ablations confirm each learned module's standalone gain:
Yes. Under strictly aligned budgets (1,000 upstream attempts/target × 25 slots = 125,000 slots; failed attempts counted as misses without replacement), CoFi-MOF (without MEF) outperforms all baselines at K=5,10,25:
At K=25, CoFi-MOF beats MOFFUSION by +9.24 pp overall (+8.52 pp at K=10), leading across 3–6 Å (87.40%, 88.90%, 86.90%, 80.20% vs. 72.80%, 72.50%, 76.00%, 74.90%) while slightly trailing at 7 Å (73.30% vs. 74.30%). Candidates derive from one fixed upstream output via each method's native realization (MOFFlow-2: 25 geometric realizations; MOFDiff: 25 annealing seeds; MOFFUSION: top-25 node/linker assignments; CoFi-MOF: Constructor's top-25 assignments). Actual valid Zeo++ counts reflect assembly compatibility: CoFi-MOF records 124,211 measurements (from 124,850 attempts) vs. 105,711 (MOFFUSION), 115,510 (MOFDiff), and 114,374 (MOFFlow-2).
Even before Zeo++ verification, MEF achieves 70.59% Top-1 [email protected] across 1,129 shared-source tasks (+31.20 pp over XGBoost, cutting Top-1 MAE from 0.6777 to 0.3268 Å):
Under Best-of-10 verification, MEF retains the lowest MAE (0.2119 vs. 0.2501/0.2342 Å) and beats random editing on 937 shared tasks (78.12% vs. 65.21%). Across the full 5,000-attempt pipeline, MEF-guided refinement rescues ~30% of remaining failures without losing any existing hits, boosting [email protected] from 68.24% to 77.46% (+9.22 pp):
Under UFF4MOF/LAMMPS relaxation across 1,280 paired structures, [email protected] shifts from 93.6% to 20.9% (MAE 0.140→1.239 Å). The decrease in [email protected] quantifies post-relaxation target mismatch, rather than the fraction of structurally collapsed frameworks. Notably, CoFi-MOF substantially outperforms MOFFUSION in relaxed cohorts: 20.9% vs. 12.3% [email protected], 1.239 vs. 2.999 Å MAE, and 21.6% vs. 9.7% (2.2×) initial-hit retention, identifying 276 candidates across 106 topologies with PLD shift ≤0.5 Å (242 still hitting the target).
Our decoupled architecture directly supports selecting by relaxed PLD: erel(C)=∣PLDZeo++(R(C))−d⋆∣, ranking shortlisted Constructor/MEF candidates after relaxation R without differentiating through force fields. The primary bottleneck is compute cost: UFF4MOF three-stage minimization is ~500$\times$ slower than Zeo++ (316 ms/structure, App. B.4). Relaxing all 125,000 candidates would require ~6,250 core-hours (~1 day on 256 cores) vs. 11 core-hours for Zeo++. Fast geometric screening followed by relaxation-based re-ranking of top shortlisted candidates offers an immediately practical solution.
We hope these analyses support a positive reassessment of our paper.