- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes RAL, which uses learnable radial gating to adaptively adjust the retained spherical harmonic orders based on interatomic distances. It further employs a parameter-sharing Band-MoE with different maximum angular orders to reduce edge-wise computation in equivariant machine learning interatomic potentials (MLIPs). The authors also introduce an independent reflection symmetry constraint to reduce the number of model parameters. The paper evaluates accuracy and efficiency on OMol25 and OMat24. On OMol25, under the direct force prediction setting, the combined approach achieves 2.10× higher batched inference throughput than the dense baseline while maintaining comparable accuracy.
Critical strengths
-
Figure 1 is intuitive and clearly illustrates the proposed method, making it easy to understand.
-
Adopting different angular degrees for different cutoff regions is a meaningful research.
Critical weaknesses
-
I am not fully convinced by the experimental setup and results presented in the paper. Figure 2 uses pretrained models from different sources. I suggest that the authors provide details on the optimizers and training budgets used for each model, and clearly distinguish the contributions of training strategies (e.g., optimizers) from those of RAL itself. Furthermore, Table 1 shows that RAL leads to accuracy degradation in most configurations (I also have concerns about the results; see Question 3). In particular, the degradation in both energy and force accuracy is more pronounced under the important conservative setting. This further weakens the general applicability of the claim that RAL achieves acceleration with only a minor loss in accuracy.
-
I remain concerned about the applicability of Band-MoE to molecular dynamics (MD) simulations. Specifically, suppose the messages from two experts are mixed as follows:
Taking the derivative with respect to yields:
The stability of NVE MD simulations depends not only on the continuity of the potential energy surface but also on whether the magnitudes of its higher-order derivatives remain sufficiently controlled. Although Band-MoE employs a transition window and other mechanisms to ensure that the potential energy surface is continuously differentiable, these mechanisms do not provide an upper bound of its higher-order derivatives. In particular, the additional perturbation term further raises my concerns. Unfortunately, the paper does not quantify this effect, and the existing MD experiments are conducted only under the NVT ensemble. Therefore, the impact of expert switching on NVE stability remains unverified.
Questions for authors
- In Figure 2, are the optimizers used for the proposed method consistent with those used for the other baselines?
- Why is the accuracy degradation more pronounced under the conservative setting?
- In Table 1, why does the baseline with (Line 319) exhibit worse accuracy than that with (Line 318)? Based on my experience, larger values may require different optimal training hyperparameters than smaller ones. Moreover, models with more trainable parameters tend to be more prone to training instability on OMol25. Therefore, I suggest that the authors perform additional hyperparameter tuning to ensure a fair comparison.
- See Weakness 2. Can the authors provide guarantees regarding the smoothness of Band-MoE?
4 comments
I thank the authors for their response and additional experiments. After reviewing the rebuttal and revised manuscript, I still have two concerns:
-
Unlike UMA's MoLE[1], Band-MoE routes experts based on interatomic distances, which may lead to expert switching during MD simulations. Although the routing is -continuous, the force terms and higher-order derivatives introduced by expert switching are not sufficiently controlled. The authors also acknowledge that the method can fail in some applications (e.g., the release of C60, Line 1078).
-
At the same , RAL achieves lower accuracy than the dense baseline. Matching the baseline accuracy requires increasing , which reduces the speedup. For example, in Table 2, RAL with achieves only a 1.20× speedup.
Based on these concerns, I am inclined to maintain my current rating.
[1] Brandon M. Wood et.al UMA: A Family of Universal Models for Atoms. NeurIPS2025
Reply on Official Comment by Reviewer ntwT
We thank the Reviewer for their follow-up. What other experiments would convince the Reviewer to consider increasing the score?
On stability: The release of C60 was with the direct-force head model (similarly to other literature models). None of our new NVE simulations fail on the conservative models. These new NVE simulation use all MD22 molecules, including the C60, and the trajectory did not diverge on the three seeds. These results show, that the model is sufficiently controlled and they are stable.
On accuracy at fixed : At , the force accuracy difference remains within the single-run noise threshold (2.6%) across all four evaluated settings. More importantly, at matched accuracy, RAL achieves a 1.20–1.29× speedup, with configurations that are both faster and more accurate than their dense counterparts. We acknowledge that the speedup at matched accuracy is smaller than at fixed and have clarified this in the revised text. The 31–45% peak-memory reduction remains consistent across all operating points.
Dear Reviewer, as the paper discussion period will end soon, we wanted to follow up. We believe our rebuttal responses address all of your original and follow-up questions.
If our responses have addressed your concerns, we would appreciate it if you would consider raising your score.
Rebuttal
We thank the Reviewer for the comments and great insights. We addressed all concerns and we believe that edits made the manuscript significantly better in both delivery and content than before.
For Figure 2 we didn’t re-train the literature models but we used official released checkpoints and evaluated them under the same settings (same hardware, same data). UMA, AllScAIP and eSCN are using AdamW with cosine scheduler, while MACE models use AMSGrad Adam, we’ve specified the details in the manuscript.
We thank the Reviewer for the insightful comment (similar to Reviewer CWky). We performed 78 new NVE MD (following the eSEN examples) simulations on the MD22 and the OMol25 datasets’ molecules and added the results to the manuscript. In short: the conservative RAL+BandMoE shows the same trajectories as the dense baseline models and none of the conservative trajectories failed under 100ps at 2000K temperature. We believe that these results reflect that our RAL approach does not introduce instabilities to the models.
We also thank the reviewer for raising a concern about the smoothness guarantees. The quintic transition is C^2, with first and second derivatives vanishing at the window boundaries. Assuming the experts and downstream operations are C^2, the energy of the conservative Band-MoE model is C^2, so forces and Hessian remain continuous across expert transitions. Third and higher derivatives need not be continuous at the window boundaries.
Yes, and we update the manuscript for better readability.
We agree with the reviewer that the conservative results were lacking details, therefore, we performed more experiments on the conservative force RAL and updated Table 2 with longer training results, which decreased the force and energy errors significantly. We speculated that the larger error (compared to direct force head) is due to that the conservative force differentiates the routing weights in BandMoe, which adds a force term inside each transition window that a direct force head never sees. This issue could be simple addressed with two experts that have an overlapping transition window, which would solve the problem, but beyond the scope of this work.
We thank the Reviewer for being vigilant. We investigated further and the results turned out to be an unnoticed training error. We re-run the L-ablation on several more L-max values (Table 2) and now we confidently confirm that all L-values are correctly reported. These analysis also helped us to pinpoint a sweet spot where RAL with L-max = 6 has lower E/F MAE than the dense L-max=4 models while having similar inference throughput.