pith. machine review for the scientific record. sign in

arxiv: 2605.02352 · v1 · submitted 2026-05-04 · 🪐 quant-ph

Recognition: 3 theorem links

· Lean Theorem

Geometric Quantum Physics Informed Neural Network

Hiromichi Matsuyama, Reza Safari, Wai-Hong Tam

Authors on Pith no claims yet

Pith reviewed 2026-05-08 18:34 UTC · model grok-4.3

classification 🪐 quant-ph
keywords geometric quantum machine learningphysics-informed neural networksequivariant quantum circuitsPDE solverssymmetry-aware ansatzesquantum neural networksinductive biasestwirling construction
0
0 comments X

The pith

Incorporating PDE symmetries into quantum circuits improves accuracy and reduces the number of trainable parameters.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper proposes geometric quantum physics-informed neural networks that build the symmetries of a partial differential equation directly into a quantum circuit ansatz. Equivariant generator sets and a twirling construction produce gates that keep model outputs compatible with those symmetries when initial and boundary data permit it. On a set of linear and nonlinear PDE benchmarks, these networks reach lower mean absolute error than both ordinary quantum PINNs and symmetry-adapted classical PINNs. They achieve this while using substantially fewer trainable parameters, indicating that geometric inductive biases can make quantum PDE solvers more efficient.

Core claim

We construct parametrized circuits that encode finite-group and compact Lie-group symmetries as inductive biases through problem-specific equivariant generator sets. Using a twirling-based construction, we derive symmetry-preserving gates that ensure that the model predictions respect the symmetries of the governing equation whenever the boundary and initial data are symmetry compatible. Across these benchmarks, GQPINNs achieve improved solution accuracy, as quantified by lower mean absolute error, while requiring substantially fewer trainable parameters.

What carries the argument

The twirling-based construction of symmetry-preserving gates from equivariant generator sets, which embeds the geometric structure of the PDE as an inductive bias inside the quantum-circuit ansatz.

If this is right

  • GQPINNs produce lower mean absolute error than standard QPINNs on the tested linear and nonlinear PDEs.
  • The networks require substantially fewer trainable parameters than either standard QPINNs or classical symmetry-adapted PINNs under matched training protocols.
  • Symmetry-aware quantum-circuit design supplies a systematic route to improved efficiency and generalization in quantum PDE solvers.
  • Geometric inductive biases can be incorporated into quantum-enhanced scientific machine learning through problem-specific equivariant gates.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • If the symmetry construction survives hardware noise, similar equivariant designs could reduce quantum resources needed for other symmetry-rich physics simulations.
  • The same twirling approach might be combined with classical symmetry reduction techniques to handle larger or higher-dimensional PDEs.
  • Testing the method on PDEs whose symmetries are only approximate would reveal how sensitive the accuracy gain is to exact symmetry compliance.
  • Hybrid classical-quantum pipelines could use the GQPINN ansatz only on symmetry sectors where the quantum advantage is largest.

Load-bearing premise

That the chosen equivariant generator sets and twirling construction can be realized on quantum hardware without noise or approximation errors that erase the symmetry advantage.

What would settle it

A benchmark on actual quantum hardware in which the reported accuracy gain or parameter reduction disappears once device noise is present.

Figures

Figures reproduced from arXiv: 2605.02352 by Hiromichi Matsuyama, Reza Safari, Wai-Hong Tam.

Figure 1
Figure 1. Figure 1: FIG. 1. Baseline QPINN ansatz based on the data re-uploading scheme [35]. The circuit alternates trainable blocks and encoding view at source ↗
Figure 2
Figure 2. Figure 2: FIG. 2 view at source ↗
Figure 3
Figure 3. Figure 3: FIG. 3 view at source ↗
Figure 4
Figure 4. Figure 4: FIG. 4. The extension of view at source ↗
Figure 5
Figure 5. Figure 5: FIG. 5. MAE of the QPINN, view at source ↗
Figure 7
Figure 7. Figure 7: FIG. 7. MAE of classical (PINN, SI-PINN) and quantum view at source ↗
Figure 8
Figure 8. Figure 8: FIG. 8. MAE of the QPINN baseline and the GQPINN ansatz view at source ↗
Figure 9
Figure 9. Figure 9: FIG. 9. Predictions of the GQPINN ansatz (Fig.4) (labeled GQPINN) compared with the analytical solution of the diffusion view at source ↗
Figure 10
Figure 10. Figure 10: FIG. 10. MAE of the GQPINN ansatz (Fig.4) prediction ver view at source ↗
Figure 11
Figure 11. Figure 11: FIG. 11 view at source ↗
Figure 12
Figure 12. Figure 12: FIG. 12. MAE of the QPINN baseline and the view at source ↗
Figure 14
Figure 14. Figure 14: FIG. 14. KL-divergence as a function of the number of layers view at source ↗
read the original abstract

Quantum physics-informed neural networks (QPINNs) have recently emerged as a promising framework for the solution of partial differential equations (PDEs), with several studies reporting improved convergence and accuracy relative to classical physics-informed neural networks (PINNs) at reduced training cost. Motivated by these advances, we introduce geometric quantum physics-informed neural networks (GQPINNs), a symmetry-aware extension of QPINNs in which the geometric structure of the underlying PDE is incorporated directly into the quantum-circuit ansatz. Building on the framework of geometric quantum machine learning, we construct parametrized circuits that encode finite-group and compact Lie-group symmetries as inductive biases through problem-specific equivariant generator sets . Using a twirling-based construction, we derive symmetry-preserving gates that ensure that the model predictions respect the symmetries of the governing equation whenever the boundary and initial data are symmetry compatible. We benchmark GQPINNs against standard QPINNs and symmetry-adapted classical PINN baselines under matched training protocols across a representative set of linear and nonlinear PDEs. Across these benchmarks, GQPINNs achieve improved solution accuracy, as quantified by lower mean absolute error, while requiring substantially fewer trainable parameters. These results identify symmetry-aware quantum-circuit design as an effective route toward improved efficiency and generalization in quantum PDE solvers and provide a systematic framework for incorporating geometric inductive biases into quantum-enhanced scientific machine learning.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript introduces geometric quantum physics-informed neural networks (GQPINNs) as a symmetry-aware extension of QPINNs. It encodes finite-group and compact Lie-group symmetries of the target PDE directly into the quantum-circuit ansatz via problem-specific equivariant generator sets and a twirling construction that produces symmetry-preserving gates. The resulting model is claimed to respect the PDE symmetries whenever initial/boundary data are compatible, and benchmarks on representative linear and nonlinear PDEs are reported to yield lower mean absolute error together with substantially fewer trainable parameters than both standard QPINNs and symmetry-adapted classical PINN baselines.

Significance. If the quantitative claims hold under scrutiny, the work supplies a systematic route for injecting geometric inductive biases into quantum PDE solvers. This could improve sample efficiency and generalization in quantum-enhanced scientific machine learning while remaining compatible with existing geometric quantum machine learning toolkits.

major comments (2)
  1. [Abstract] Abstract: the headline claims of 'improved solution accuracy, as quantified by lower mean absolute error' and 'substantially fewer trainable parameters' are stated without any numerical values, error bars, statistical tests, or even a summary table. Because these quantities are the sole evidence offered for the central contribution, their absence prevents any assessment of effect size or robustness.
  2. [Twirling construction and equivariant generators] Twirling construction (methods): the symmetry preservation is derived under the ideal, noiseless, infinite-shot limit. The manuscript benchmarks only in noiseless simulation; no analysis or experiments are supplied on how depolarizing, readout, or sampling noise degrades the enforced equivariance. This is load-bearing for any claim of hardware relevance.
minor comments (2)
  1. [Notation and construction] The precise definition of the equivariant generator sets for both finite and Lie groups would benefit from an explicit equation or worked example for at least one symmetry.
  2. [Benchmarks] The benchmark section should list the exact PDEs, circuit depths, optimizer hyperparameters, and number of shots used so that the reported MAE and parameter counts can be reproduced.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback. We address each major comment point by point below, proposing revisions where they strengthen the manuscript while maintaining the integrity of our contributions.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the headline claims of 'improved solution accuracy, as quantified by lower mean absolute error' and 'substantially fewer trainable parameters' are stated without any numerical values, error bars, statistical tests, or even a summary table. Because these quantities are the sole evidence offered for the central contribution, their absence prevents any assessment of effect size or robustness.

    Authors: We agree that the abstract would benefit from explicit quantitative indicators to better convey effect sizes. The detailed benchmark results, including mean absolute errors, parameter counts, error bars from multiple independent runs, and comparisons, are already reported with full tables and statistical context in Section IV. In the revised version we will update the abstract to include representative numerical values (e.g., typical MAE reductions and parameter savings across the linear and nonlinear PDE examples) while preserving its concise style. revision: yes

  2. Referee: [Twirling construction and equivariant generators] Twirling construction (methods): the symmetry preservation is derived under the ideal, noiseless, infinite-shot limit. The manuscript benchmarks only in noiseless simulation; no analysis or experiments are supplied on how depolarizing, readout, or sampling noise degrades the enforced equivariance. This is load-bearing for any claim of hardware relevance.

    Authors: The referee is correct that the twirling construction and symmetry-preservation proof are derived in the ideal, noiseless, infinite-shot limit, and all reported benchmarks use noiseless classical simulation of the circuits. The manuscript does not claim immediate hardware readiness; it positions GQPINNs as an algorithmic framework whose symmetry bias is compatible with existing geometric quantum machine learning toolkits. We will add a dedicated paragraph in the discussion section that analytically examines how common noise channels (depolarizing, readout, finite-shot sampling) can degrade the enforced equivariance and will outline mitigation strategies. Full noisy simulations or hardware experiments lie beyond the present scope and resources. revision: partial

Circularity Check

0 steps flagged

No circularity: forward ansatz construction with independent benchmarks

full rationale

The paper constructs GQPINNs by extending QPINNs with symmetry encoding via equivariant generators and twirling drawn from the existing geometric quantum machine learning framework. This is presented as a direct methodological step, followed by empirical benchmarking on linear and nonlinear PDEs that reports lower MAE and fewer parameters. No derivation step reduces the claimed accuracy or efficiency gains to a fitted quantity inside the same paper, a self-citation that bears the central result, or a redefinition that makes the output equivalent to the input by construction. The chain remains self-contained as a proposal validated externally by simulation results.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 1 invented entities

The central claim rests on standard quantum-circuit and group-representation assumptions plus the new claim that symmetry preservation improves PDE solution quality; no free parameters are explicitly fitted in the abstract description.

axioms (2)
  • domain assumption Quantum circuits can be made equivariant under finite or compact Lie groups by suitable choice of generator sets.
    Invoked when constructing symmetry-preserving gates from the geometric quantum machine learning framework.
  • domain assumption When boundary and initial data are symmetry-compatible, the model predictions will respect the PDE symmetries.
    Stated as the condition under which the twirling construction guarantees symmetry preservation.
invented entities (1)
  • GQPINN no independent evidence
    purpose: Symmetry-aware quantum-circuit ansatz for PDE solving
    New framework name and construction introduced in the paper.

pith-pipeline@v0.9.0 · 5536 in / 1492 out tokens · 72346 ms · 2026-05-08T18:34:08.604431+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

Reference graph

Works this paper leans on

66 extracted references · 11 canonical work pages · 3 internal anchors

  1. [1]

    Promoting the application of advanced quantum technology platforms to social issues

    To ensure a fair comparison despite the different parameter counts per trainable block, we report MAE as a function of the total number of trainable param- eters in Fig. 5. This allows us to assess whether the GQPINN ansatzes achieves improved accuracy even with fewer parameters. Figure 5 shows that both GQPINN ansatzes achieve substantially smaller MAE w...

  2. [2]

    Ayral, P

    T. Ayral, P. Besserve, D. Lacroix, and E. A. Ruiz Guzman, The European Physical Journal A59, 10.1140/epja/s10050-023-01141-1 (2023)

    work page doi:10.1140/epja/s10050-023-01141-1 2023

  3. [3]

    Blekos, D

    K. Blekos, D. Brand, A. Ceschini, C.-H. Chou, R.-H. Li, K. Pandya, and A. Summer, Physics Reports1068, 1 (2024)

    2024

  4. [4]

    Bauer, S

    B. Bauer, S. Bravyi, M. Motta, and G. K.-L. Chan, Chemical Reviews120, 12685 (2020)

    2020

  5. [5]

    Montanaro, npj Quantum Information2, 15023 (2016)

    A. Montanaro, npj Quantum Information2, 15023 (2016)

    2016

  6. [6]

    Grossmann, H.-G

    C. Grossmann, H.-G. Roos, and M. Stynes,Numerical Treatment of Partial Differential Equations(Springer, Berlin, Heidelberg, 2007)

    2007

  7. [7]

    N. A. Fallah, C. Bailey, M. Cross, and G. A. Taylor, Applied Mathematical Modelling24, 439 (2000)

    2000

  8. [8]

    A. W. Harrow, A. Hassidim, and S. Lloyd, Physi- cal Review Letters103, 10.1103/physrevlett.103.150502 (2009)

    work page doi:10.1103/physrevlett.103.150502 2009

  9. [9]

    A. M. Childs, J.-P. Liu, and A. Ostrander, Quantum5, 574 (2021)

    2021

  10. [10]

    D. W. Berry and P. C. S. Costa, Quantum8, 1369 (2024)

    2024

  11. [11]

    Ambainis, in29th International Symposium on Theo- retical Aspects of Computer Science (STACS 2012), Leib- niz International Proceedings in Informatics (LIPIcs), Vol

    A. Ambainis, in29th International Symposium on Theo- retical Aspects of Computer Science (STACS 2012), Leib- niz International Proceedings in Informatics (LIPIcs), Vol. 14, edited by C. D¨ urr and T. Wilke (Schloss Dagstuhl – Leibniz-Zentrum f¨ ur Informatik, 2012) pp. 636–647

    2012

  12. [12]

    A. M. Childs, R. Kothari, and R. D. Somma, SIAM Jour- nal on Computing46, 1920 (2017)

    1920

  13. [13]

    Montanaro and S

    A. Montanaro and S. Pallister, Phys. Rev. A93, 032324 (2016)

    2016

  14. [14]

    Wang and Z

    Q. Wang and Z. Zhang, Phys. Rev. A110, 012422 (2024)

    2024

  15. [15]

    A. M. Childs and J.-P. Liu, Communications in Mathe- matical Physics375, 1427 (2020)

    2020

  16. [16]

    S. Jin, N. Liu, and Y. Yu, Physical Review Letters133, 230602 (2024)

    2024

  17. [17]

    D. W. Berry, Journal of Physics A: Mathematical and Theoretical47, 105301 (2014)

    2014

  18. [18]

    D. W. Berry, A. M. Childs, and R. Kothari, in2015 IEEE 56th Annual Symposium on Foundations of Com- puter Science(2015) pp. 792–809

    2015

  19. [19]

    P. C. S. Costa, S. Jordan, and A. Ostrander, Phys. Rev. A99, 012323 (2019)

    2019

  20. [20]

    J.-P. Liu, H. Ø. Kolden, H. K. Krovi, N. F. Loureiro, K. Trivisa, and A. M. Childs, Proceedings of the National Academy of Sciences118, e2026805118 (2021)

    2021

  21. [21]

    F. Oz, R. K. S. S. Vuppala, K. Kara, and F. Gaitan, Quantum Information Processing21, 10.1007/s11128- 021-03391-8 (2022)

    work page doi:10.1007/s11128- 2022

  22. [22]

    Gaitan, npj Quantum Information6, 61 (2020)

    F. Gaitan, npj Quantum Information6, 61 (2020)

    2020

  23. [23]

    Itani, K

    W. Itani, K. R. Sreenivasan, and S. Succi, arXiv:2301.05762 (2023)

    work page arXiv 2023

  24. [24]

    Ljubomir, International Journal of Quantum Informa- tion20, 2150039 (2022)

    B. Ljubomir, International Journal of Quantum Informa- tion20, 2150039 (2022)

    2022

  25. [25]

    Preskill, Quantum2, 79 (2018)

    J. Preskill, Quantum2, 79 (2018)

    2018

  26. [26]

    Bharti, A

    K. Bharti, A. Cervera-Lierta, T. H. Kyaw, T. Haug, S. Alperin-Lea, A. Anand, M. Degroote, H. Heimonen, J. S. Kottmann, T. Menke, W.-K. Mok, S. Sim, L.- C. Kwek, and A. Aspuru-Guzik, Rev. Mod. Phys.94, 015004 (2022)

    2022

  27. [27]

    J. R. McClean, J. Romero, R. Babbush, and A. Aspuru- Guzik, New Journal of Physics18, 023023 (2016)

    2016

  28. [28]

    Demirdjian, D

    R. Demirdjian, D. Gunlycke, C. A. Reynolds, J. D. Doyle, and S. Tafur, Quantum Information Processing21, 322 (2022)

    2022

  29. [29]

    Bravo-Prieto, R

    C. Bravo-Prieto, R. LaRose, M. Cerezo, Y. Subasi, L. Cincio, and P. J. Coles, Quantum7, 1188 (2023)

    2023

  30. [30]

    A. J. Pool, A. D. Somoza, C. Mc Keever, M. Lubasch, and B. Horstmann, Phys. Rev. Res.6, 033257 (2024)

    2024

  31. [31]

    Lubasch, J

    M. Lubasch, J. Joo, P. Moinier, M. Kiffner, and D. Jaksch, Phys. Rev. A101, 010301 (2020)

    2020

  32. [32]

    Syamlal, C

    M. Syamlal, C. Copen, M. Takahashi, and B. Hall, arXiv:2406.18749 (2024)

    work page arXiv 2024

  33. [33]

    Pfeffer, F

    P. Pfeffer, F. Heyder, and J. Schumacher, Phys. Rev. Res. 4, 033176 (2022)

    2022

  34. [34]

    Pfeffer, F

    P. Pfeffer, F. Heyder, and J. Schumacher, Phys. Rev. Res. 5, 043242 (2023)

    2023

  35. [35]

    Kyriienko, A

    O. Kyriienko, A. E. Paine, and V. E. Elfving, Physical Review A103, 052416 (2021)

    2021

  36. [36]

    Siegl, S

    P. Siegl, S. Wassing, D. M. Mieth, S. Langer, and P. Beke- meyer, CEAS Aeronautical Journal16, 63 (2025)

    2025

  37. [37]

    Quantum-Enhanced Convergence of Physics-Informed Neural Networks

    N. Klement, V. Eyring, and M. Schwabe, arXiv:2601.15046 (2026)

    work page internal anchor Pith review Pith/arXiv arXiv 2026

  38. [38]

    Raissi, P

    M. Raissi, P. Perdikaris, and G. E. Karniadakis, Journal of Computational Physics378, 686 (2019)

    2019

  39. [39]

    S. Cai, Z. Mao, Z. Wang, M. Yin, and G. E. Karniadakis, Acta Mechanica Sinica37, 1727 (2021)

    2021

  40. [40]

    Wassing, S

    S. Wassing, S. Langer, and P. Bekemeyer, Computers & Fluids270, 106164 (2024)

    2024

  41. [41]

    G. E. Karniadakis, I. G. Kevrekidis, L. Lu, P. Perdikaris, S. Wang, and L. Yang, Nature Reviews Physics3, 422 (2021)

    2021

  42. [42]

    J. R. McClean, S. Boixo, V. N. Smelyanskiy, R. Babbush, and H. Neven, Nature Communications9, 4812 (2018), id: McClean2018

    2018

  43. [43]

    H. Qi, L. Wang, H. Zhu, A. Gani, and C. Gong, Quantum Information Processing22, 435 (2023), id: Qi2023

    2023

  44. [44]

    Larocca, S

    M. Larocca, S. Thanasilp, S. Wang, and et al., Nature Reviews Physics7, 174 (2025)

    2025

  45. [45]

    M. M. Bronstein, J. Bruna, Y. LeCun, A. Szlam, and P. Vandergheynst, IEEE Signal Processing Magazine34, 18 (2017)

    2017

  46. [46]

    M. M. Bronstein, J. Bruna, T. Cohen, and P. Veliˇ ckovi´ c, arXiv:2104.13478 (2021)

    work page internal anchor Pith review arXiv 2021

  47. [47]

    Cohen and M

    T. Cohen and M. Welling, inProceedings of The 33rd In- ternational Conference on Machine Learning, Proceed- ings of Machine Learning Research, Vol. 48 (PMLR,

  48. [48]

    Representation theory for geometric quantum machine learning.arXiv preprint arXiv:2210.07980, 2022

    M. Ragone, P. Braccia, Q. T. Nguyen, L. Schatzki, P. J. Coles, F. Sauvage, M. Larocca, and M. Cerezo, arXiv:2210.07980 (2023)

    work page arXiv 2023

  49. [49]

    Larocca, F

    M. Larocca, F. Sauvage, F. M. Sbahi, G. Verdon, P. J. Coles, and M. Cerezo, PRX Quantum3, 030341 (2022)

    2022

  50. [50]

    Q. T. Nguyen, L. Schatzki, P. Braccia, M. Ragone, P. J. Coles, F. Sauvage, M. Larocca, and M. Cerezo, PRX Quantum5, 020328 (2024)

    2024

  51. [51]

    J. J. Meyer, M. Mularski, E. Gil-Fuster, A. A. Mele, F. Arzani, A. Wilms, and J. Eisert, PRX Quantum4, 010328 (2023)

    2023

  52. [52]

    Schuld, R

    M. Schuld, R. Sweke, and J. J. Meyer, Phys. Rev. A103, 032430 (2021)

    2021

  53. [53]

    P´ erez-Salinas, A

    A. P´ erez-Salinas, A. Cervera-Lierta, E. Gil-Fuster, and J. I. Latorre, Quantum4, 226 (2020). 16

    2020

  54. [54]

    Jerbi, L

    S. Jerbi, L. J. Fiderer, H. Poulsen Nautrup, J. M. K¨ ubler, H. J. Briegel, and V. Dunjko, Nature Communications 14, 517 (2023)

    2023

  55. [55]

    Helsen,Quantum Information in the Real World: Diagnosing and Correcting Errors in Practical Quantum Devices, Ph.D

    J. Helsen,Quantum Information in the Real World: Diagnosing and Correcting Errors in Practical Quantum Devices, Ph.D. thesis, Delft University of Technol- ogy (2021),http://resolver.tudelft.nl/uuid: 312b719d-32bc-4219-82bb-8e6febc2abcc

    2021

  56. [56]

    Huang, M

    H.-Y. Huang, M. Broughton, M. Mohseni, R. Babbush, S. Boixo, J. R. McClean, H. Neven, M. Cerezo, and P. J. Coles, Science376, 1182 (2022)

    2022

  57. [57]

    D. C. Liu and J. Nocedal, Mathematical Programming 45, 503 (1989)

    1989

  58. [58]

    PennyLane: Automatic differentiation of hybrid quantum-classical computations

    V. Bergholm, J. Izaac, M. Schuld, C. Gogolin, S. Ahmed, R. Sweke, A. Mari, S. Cao, W. J. Zeng, and N. Killoran, arXiv:1811.04968 (2018)

    work page internal anchor Pith review arXiv 2018

  59. [59]

    S. Sim, P. D. Johnson, and A. Aspuru-Guzik, Advanced Quantum Technologies2, 10.1002/qute.201900070 (2019)

    work page doi:10.1002/qute.201900070 2019

  60. [60]

    Safari (2026), unpublished manuscript, in preparation

    R. Safari (2026), unpublished manuscript, in preparation

    2026

  61. [61]

    P. J. Olver,Applications of Lie Groups to Differential Equations(Springer-Verlag, New York, 1993)

    1993

  62. [62]

    L. Lu, P. Jin, G. Pang, Z. Zhang, and G. E. Karniadakis, Nature Machine Intelligence3, 218 (2021)

    2021

  63. [63]

    S. Wang, H. Wang, and P. Perdikaris, Science Advances 7, eabi8605 (2021)

    2021

  64. [64]

    Zhang, H

    Z.-Y. Zhang, H. Zhang, L.-S. Zhang, and L.-L. Guo, arXiv:2206.09299 (2022)

    work page arXiv 2022

  65. [65]

    W. Zhu, W. Khademi, E. G. Charalampidis, and P. G. Kevrekidis, Physica D: Nonlinear Phenomena434, 133264 (2022)

    2022

  66. [66]

    Zhang, J.-Y

    Z.-Y. Zhang, J.-Y. Li, and L.-L. Guo, Journal of Com- putational Physics523, 113680 (2025)

    2025