- Rating
- 3
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper introduces PhysLoopNO, which extends the LinearNO architecture with more parameter efficient looping mechanism, additional physics-gated tied dense experts, and selective parameter sharing. The parameter-reuse concept is inspired by looped architectures, with particular influence from the tied experts introduced in "Tying The Loop".
It claims the method achieves the best among the reported results in terms of L2 error on five out of six PDE benchmarks: "Airfoil", "Plasticity", "Darcy", "Navier-Stokes" and "Elasticity", where the compared baseline method LinearNO is reproduced according to the official implementation and experimental protocols on all benchmarks. On the benchmark "Pipe", the Transolver, Transolver++ and the reproduced LinearNO perform better.
On two further datasets, "AirfRANS" and "ShapeNet-Car", the reported results demonstrate competitive performance, again comparing against the reproduced LinearNO. PhysLoopNO achieves the best reported results in terms of volume and surface field predictions, and the drag and lift predictions are also competitive. The Spearman rank correlation for the drag for "ShapeNet-Car" is competitive, but on "AirfRANS" the Spearman rank correlation for the lift is worse than seven other methods including the reproduced LinearNO.
One main advantage that the authors stress is that compared to LinearNO, scaling the depth of the network from 8 to 40 layers adds 46.26% fewer parameters on "Darcy" and 21.76% fewer parameters on "Airfoil", while outperforming LinearNO at maximum depth of 40 on "Airfoil" and achieving a tie with LinearNO on "Darcy". On "Elasticity", the PhysLoopNO model can outperform LinearNO but the four-expert configuration adds 32.04% more parameters when scaling from 8 to 40 layers.
Regarding the choice of number of experts on the tested datasets, it finds that depending on the dataset, the best tested number of experts was between one and four experts, and using additional experts can degrade the performance.
Critical strengths
The paper ...
-
introduces looping to the LinearNO architecture with selective parameter reuse, achieving more efficient scaling in depth while retaining improved or competitive accuracy compared to prior methods.
-
reports results on a variety of benchmarks showing that: (1) their model outperforms a wide range of other methods and a reproduced version of LinearNO on five out of six PDE benchmarks, and (2) achieves competitive results on two additional CFD datasets.
-
identifies two different mechanisms, namely spatial aggregation / mixing of spatial features in the cores (slicing and deslicing) and pointwise / local, non-linear transformations (experts) that can be weighted for each point and loop, while expert banks are shared between the loops.
Critical weaknesses
-
It is not clear if the results from the experiments are robust, i.e. the number of tested random seeds is enough. This could especially make a difference for given the small relative differences in L2 error on experiments like "Airfoil" (0.0048 vs 0.0046), "Plasticity" (0.0013 vs 0.0012), "Darcy" (0.0050 vs 0.0048), AirfRANS surface field (0.0076 vs 0.0078) and ShapeNet-Car volume and surface field (0.0188 vs 0.0195 and 0.0744 vs 0.0752).
-
While the paper focuses on parameter-efficiency, it does not state the model sizes for comparison, just relative parameter counts as depth increases. It just states it on one separate three-expert Airfoil configuration the PhysLoopNO model uses 17.46% fewer trainable parameters than LinearNO at matched depth.
-
Since the experts are shared between different visits, parameter count does not directly relate to number of floating point operations (FLOPs). The number of FLOPs during training and inference with PhysLoopNO should be compared against the FLOPs of LinearNO.
Questions for authors
-
For clarity, could you expand on what physics-gated experts are and how they differ from gated experts?
-
How many independent training runs were performed per benchmark? Would it be possible to report the means and standard deviations over at least five random seeds in the table for the main results in tables 1 and 2?
-
Could you provide the total number of trainable parameters for the LinearNO and PhysLoopNO models used in the experiments from tables 1 and 2? If possible please also report the number of parameters for the other baseline models.
-
Could you provide the number of FLOPs for the LinearNO and PhysLoopNO models during inference and training for the experiments from tables 1 and 2?
-
For the "AirfRANS" dataset, the reproduction of LinearNO is worse than the original LinearNO model in terms of L2 errors of volume pressure field, as reported in the original paper [1]. This changes the claims about competitiveness with LinearNO. Could you reconcile the differences to the original LinearNO paper?
[1] Hu, Wenjie, et al. "Transolver is a linear transformer: Revisiting physics-attention through the lens of linear attention." Proceedings of the AAAI Conference on Artificial Intelligence. Vol. 40. No. 1. 2026.
4 comments
Thank you for the clarifications. The questions about the physics-gated experts and about the total parameter count are answered satisfactorily. There are still three remaining follow-up questions to the other points.
- Regarding robustness of the results: the new tables 9 and 10 in the appendix contain the same values as the tables in the original version of the paper, but given the relatively high standard deviations, it seems unlikely that all the mean values would correspond to a single seed result.
- Your answer regarding FLOPs does not compare LinearNO and PhyLoopNO in a fair way. As you note in the paper, in the eight-layer looped models some cores are visited multiple times which requires computation. In your answer you only count one visit per core. Could you give a comparison of the FLOPs for the full forward passes, and full forward + backward passes?
- Is it possible to resolve the reproduction gap?
Response to Reviewer fetP
Thank you for considering our additional experiments and for your positive feedback. We are glad to continue the discussion.
Regarding the computational comparison
We agree that a fair comparison must include every visit to each shared core. We have updated the table of parameter counts and computational costs accordingly. For both models, the table gives the full forward and full forward + backward costs across all eight executed layers. In PhyLoopNO, each of the three shared cores is visited twice.
Table 1. Trainable parameters and GFLOPs per example at depth eight.
| Benchmark | LinearNO parameters | PhyLoopNO parameters | LinearNO forward | PhyLoopNO forward | LinearNO forward + backward | PhyLoopNO forward + backward |
|---|---|---|---|---|---|---|
| Airfoil | 1,765,889 | 1,294,753 | 45.442 | 51.443 | 136.314 | 154.319 |
| Pipe | 1,765,889 | 1,210,841 | 67.092 | 71.557 | 201.260 | 214.653 |
| Plasticity | 1,799,428 | 1,328,292 | 12.833 | 14.500 | 38.390 | 43.392 |
| Darcy | 1,766,145 | 1,125,513 | 29.133 | 29.148 | 87.388 | 87.432 |
| Navier–Stokes | 3,377,921 | 905,121 | 29.991 | 12.479 | 89.513 | 37.207 |
| Elasticity | 585,217 | 556,833 | 1.626 | 2.143 | 4.876 | 6.429 |
| AirfRANS | 3,358,788 | 895,564 | 233.079 | 96.879 | 696.910 | 289.473 |
| ShapeNet-Car | 3,852,420 | 961,828 | 266.074 | 104.824 | 797.990 | 314.358 |
PhyLoopNO uses fewer parameters than LinearNO on all eight benchmarks. Evaluating the dense experts increases computation on some tasks. On Airfoil and Plasticity, for example, we consider the approximately 13% increase in forward cost a reasonable trade-off for the lower mean prediction error. Overall, PhyLoopNO lowers mean error on five of the six standard benchmarks. On Darcy, Navier–Stokes, AirfRANS, and ShapeNet-Car, it achieves lower mean field errors at comparable or lower computational cost.
Regarding reproducibility and standard deviations
Many recent neural operators reporting state-of-the-art results are based on Mamba [1, 2]. We have found some of their results difficult to reproduce consistently. For example, AMO’s official code repository [1] was empty when we checked.
We believe that adjacency in a Mamba scan does not necessarily imply proximity in physical space, even when the sequence is scanned in both directions as in LaMO [2]. We think this may be an important reason why the performance of Mamba-based neural operators can vary.
Both our model and the baseline show relatively large standard deviations across random seeds, particularly on Airfoil and Pipe. However, PhyLoopNO has a smaller standard deviation than LinearNO on five of the six standard benchmarks, including Airfoil (0.0006 vs. 0.0009), Pipe (0.0006 vs. 0.0008), and Plasticity (0.0003 vs. 0.0006). These results support the robustness of PhyLoopNO across training seeds.
The original submission already reported five-seed means for PhyLoopNO and our LinearNO reproduction. Tables 9 and 10 add standard deviations from those same runs, which explains why the means match exactly. The small mean improvement on Airfoil should still be read in light of that variability.
References
[1] Zeyuan Song and Zheyu Jiang. Adaptive Mamba Neural Operators. ICLR, 2026.
[2] Karn Tiwari, Niladri Dutta, N M Anoop Krishnan, and Prathosh Ap. Latent Mamba Operator for Partial Differential Equations. ICML, 2025.
Thank you for these clarifications and the additional experiments. I believe these should be incorporated into the final manuscript. I will maintain my positive rating.
Response to Reviewer fetP on expert gating, robustness, and computational cost
We sincerely thank you for recognizing the selective-sharing and expert mechanisms and for asking about their costs and the variability of the results.
Regarding physics-gated experts
In PhyLoopNO, “physics-gated” describes how the evolving field state weights experts shared across visits to one core. Let z be a normalized C-channel point feature carrying spatial context from slicing/deslicing. Visit r computes πr(z)=softmax(Wrz+br) and returns the pointwise mixture
Gr(z)=∑e=1Eπr,e(z)fe(z).
Each fe is a two-layer GELU FFN of hidden width F and processes every point. The PDE loss trains each router's E(C+1) parameters. Similar hidden states can receive similar mixtures within a visit. Even for the same z, a later visit can mix the shared experts differently. The residual adds Gr(z)/R at each of R visits. We omit a load-balancing loss, allowing unequal expert contributions across regions. We expanded Section 3.3 to explain this design.
Regarding result robustness
We now report five-seed means and SDs in Appendix C.6 (Tables 9–10). Table A gives relative L2 error on the six standard tasks. Industrial coefficient error and Spearman ρ refer to lift on AirfRANS and drag on ShapeNet-Car.
Table A. Five-seed test results (mean ± SD).
Airfoil, Plasticity and Darcy mean gaps are small relative to seed variability. Gains are larger on Navier–Stokes and Elasticity. Pipe favors LinearNO. Section 4.1 clarifies that all four mean field errors fall. Lift error rises slightly, drag error ties at the reported precision, and both rank correlations fall.
Regarding absolute parameter counts and FLOPs
Each shared expert is stored once and evaluated at every visit. Table B therefore pairs parameter counts with FLOPs. Section 4.2 and Appendix C.6–C.8 (Tables 11–14) now give counts by task, expert count (E=1,2,4) and depth (8–40 in steps of 8 on Airfoil, Darcy and Elasticity).
Table B. P = total parameters at 8/40 layers. G = eight-layer GFLOPs, forward / forward + backward. Industrial 40-layer entries are architecture counts.
From 8 to 40 layers, PhyLoopNO adds 46.26% fewer parameters than LinearNO on Darcy, 37.91% fewer on Airfoil and 18.70% fewer on Elasticity. Darcy uses one expert, Pipe three and the remaining tasks four.
Counts cover matrix and convolution operations across all eight executed layers of each model at batch size one (two FLOPs per multiply-accumulate), excluding activations, normalization, softmax, expert weighting and optimizer updates. We use one predicted step for Navier–Stokes, one time query for Plasticity and 32,000/32,186 points for AirfRANS/ShapeNet-Car.
Regarding the LinearNO reproduction gap
LinearNO reports three runs and gives no industrial SD. Its published AirfRANS volume error (0.0011) is lower than both means in Table A. Section 4.1 now specifies that PhyLoopNO improves on LinearNO in our common environment. The cause of the reproduction gap remains unresolved.
References
Hu et al. (2026). Transolver Is a Linear Transformer. AAAI.
Wu et al. (2024). Transolver. ICML.