- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes PDE-JEPA for parametric PDE forecasting, combining predictive representation pretraining, latent trajectory geometry alignment, and a parameter-structured latent ODE. Experiments on nine PDE benchmarks, including parameter-shift evaluations, report improved forecasting accuracy. Representation probes and ablations investigate the distinction between physical informativeness and temporal predictability.
Critical strengths
1.The distinction between informative representations and representations suitable for accurate rollout is meaningful for scientific machine learning.
2.The reported gains are substantial, supported by module ablations, representation probes, and parameter-response analyses.
Critical weaknesses
1.The empirical comparisons require correction and clarification. Five baseline rows imported from Zebra reverse the Heat and Burgers entries, affecting Tables 1 and 26. Differences in temporal sampling, spatial resolution, and test-time conditioning also leave the comparability of borrowed results unclear.
2.The contribution of the geometry loss is not sufficiently isolated. PAG introduces a projector, auxiliary dynamics supervision, and additional training together. Existing ablations do not compare against the same setup with only the geometry loss removed, leaving the source of the improvement uncertain.
Questions for authors
-
Could you reconcile the reporting discrepancies in Tables 1 and 26, particularly the reversed Heat/Burgers baseline entries and Zebra’s Wave-2D reconstruction error of 0.0010 versus 0.010 in the original source? Do these corrections change the conclusions?
-
Are the compared methods evaluated using equivalent spatial resolutions, temporal sampling, forecast durations, and test-time conditioning information? Please clarify how directly cited baseline results are comparable to your setting.
-
On Vorticity and Wave-2D, how does PAG perform when the geometry loss is removed while keeping the projector, auxiliary dynamics loss, anchor loss, and training budget unchanged?
-
What do the seven conditioning dimensions for Burgers/Heat encode, and how is time-dependent forcing handled? For HeterNS, why is forcing frequency modeled through the linear term , given its nonlinear effect on the spatial forcing field?
4 comments
To address your concerns on model capacity and PDE prior, we add Table 2 into Appendix C.2, Table 20 from line 2169 to 2191. Regarding PDE priors, we listed below:
- Trajectory history: multiple frames as inputs.
- Current (latent) state: current single (latent) frame.
- Support trajectory: full trajectory as context.
- PDE parameters: physics parameter ().
Table 2: Model Details.
| FNO | GEPS | Zebra | Unisolver | LNS | MAE-PDE | |
|---|---|---|---|---|---|---|
| Capacity | 50M | 1M | 42M | 55M | 24M | 20M |
| PDE Prior | Trajectory history | Current state with a support trajectory | Target initial state with a support trajectory | Current state, PDE parameters | Current latent state and PDE parameters | Trajectory history |
| MPP | DPOT | Poseidon | LE-PDE | ENMA | PDE-JEPA | |
| Capacity | 115M | 30M | 10M | 20M | 60M | 24M |
| PDE Prior | Trajectory history | Trajectory History | Trajectory-history | Trajectory history with<br> a support trajectory | Trajectory History | Current latent state and PDE parameters |
To further address your concerns on training strategies and budget, we have conducted controlled ViT comparisons (Table 3), matching architecture, capacity, data settings, conditioning information, downstream training protocols, and training budgets.
Table 3 Strictly matched experiment on resolution, trajectory length, model capacity, PDE prior, training strategy and training budget.
| ID Rollout | OOD Rollout | ||
|---|---|---|---|
| ViT encoder+predictor | JEPA | 0.086 | 0.49 |
| JEPA+PAG | 0.040 | 0.39 | |
| JEPA+PAG + PSP | 0.034 | 0.28 | |
| ViT encoder+predictor | Reconstruct | 0.059 | 0.47 |
| Reconstruct+PAG | 0.063 | 0.62 | |
| Reconstruct+PAG + PSP | 0.057 | 0.43 | |
| ViT encoder+predictor | MAE | 0.12 | 0.51 |
| MAE+PAG | 0.17 | 0.59 | |
| MAE+PAG + PSP | 0.15 | 0.54 | |
| LNS | Original | 0.059 | 0.48 |
| LNS | Original+PAG | 0.062 | 0.62 |
| LNS | Original+PAG + PSP | 0.057 | 0.45 |
With PAG and PSP, JEPA achieves best ID/OOD errors, supporting its advantage within the tested framework. We have added this in the main paper in section 5.4.
CW2: Ablations for geo loss
To address the concerns about geo loss, we conduct experiments on Vorticity and Wave-2D on PAG without geo loss (as shown in Table 4).
| Vorticity ID | Vorticity OOD | Wave-2D ID | Wave-2D OOD | |
|---|---|---|---|---|
| PAG w/o geo loss | 0.083 | 0.491 | 0.35 | 0.50 |
| Table 4: PAG without geo loss experiment. |
Removing only this loss, with all other components and training budgets unchanged, increases ID/OOD errors from 0.040/0.397 to 0.083/0.491 on Vorticity and from 0.143/0.321 to 0.350/0.500 on Wave-2D. The geometry loss provides vital efforts on both datasets.
Q1: Writing mistakes
We apologize for the errors, and the conclusion will not be changed. . Since Zebra does not rank among the top two methods on either Burgers or Heat, correcting these values does not affect our conclusions regarding PDE-JEPA. For Wave-2D, correcting the reconstruction error from 0.001 to 0.01 reduces Zebra-R from 207 to 20.7. However, this remains higher than JEPA-R (8.72), and therefore does not change our conclusions. We have revised our manuscript.
Q2: Settings problem
Please refer to CW1.2.
Q3: Ablation on PAG losses
In Appendix D.3.2 Table 36, we find that removing anchor loss degrades representation's information. We further conduct experiments on loss ablations for PAG module (Table 2).
Table 2: PAG loss ablation.
| Vorticity ID | Vorticity OOD | Wave-2D ID | Wave-2D OOD | |
|---|---|---|---|---|
| Full PAG | 0.040 | 0.397 | 0.143 | 0.321 |
| Full PAG w/o dyn loss | 0.045 | 0.453 | 0.169 | 0.349 |
| Full PAG w/o anchor loss | 0.047 | 0.423 | 0.166 | 0.354 |
| Full PAG w/o geo loss | 0.083 | 0.491 | 0.355 | 0.498 |
Removing one loss at a time, with all other settings unchanged, increases ID/OOD errors, we find that geo loss matters the most. We add this results to Appendix D.3.2 paragraph "PAG loss ablations".
Q4.1: conditioning input for Burgers and Heat
We thank the reviewer for bringing this to our attention. This feedback has helped us improve the clarity of the manuscript.
The seven conditioning dimensions encode the viscosity/diffusivity and the forcing averaged over each prediction interval. For both Burgers and Heat, the condition vector is
\left[ \log\beta,\, S_{1,n},\,C_{1,n},\, S_{2,n},\,C_{2,n},\, S_{3,n},\,C_{3,n} \right].$$ For the transition interval $(t_n,t_{n+1})$, define $\Delta t_n=t_{n+1}-t_n$, $t_{\mathrm{mid},n}=(t_n+t_{n+1})/2$, and $\operatorname{sinc}(z)=\sin(z)/z$, with $\operatorname{sinc}(0)=1$. The coefficients are $$\begin{aligned} S_{\ell,n} &= \sum_{\substack{j=1,\ldots,5\\\\ l_j=\ell}} A_j \operatorname{sinc}\left(\frac{\omega_j\Delta t_n}{2}\right) \cos\left(\omega_j t_{\mathrm{mid},n}+\phi_j\right), \\\\ C_{\ell,n} &= \sum_{\substack{j=1,\ldots,5\\\\ l_j=\ell}} A_j \operatorname{sinc}\left(\frac{\omega_j\Delta t_n}{2}\right) \sin\left(\omega_j t_{\mathrm{mid},n}+\phi_j\right), \qquad \ell\in\\{1,2,3\\}. \end{aligned}$$ Thus, the five forcing modes $$A_j,\omega_j,l_j,\phi_j$$ listed in the appendix are aggregated by spatial harmonic into six interval-specific Fourier coefficients. $l_j$ selects the spatial-frequency channel, while temporal information enters through the midpoint phase and interval-averaging factor, without an additional time-conditioning dimension. Here, $$\beta$$ denotes viscosity for Burgers and thermal diffusivity for Heat. **We have added this to Appendix C.1.1 "Burgers and Heat: interval-dependent conditioning."** **Q4.1: PSP for HeterNS** We greatly thank the reviewer for giving us very useful suggestion. **The reviewer is correct: forcing frequency is not a linear amplitude coefficient in the governing equation.** We therefore **replace $mD(q)$ with a nonlinear conditional branch $D(q,m)$ (shown in Table 3).** > Table 3: HeterNS frequency module experiment. | | mD(q) | w/o mD(q) | D(q,m) | | :-----------------: | :---------: | :---------: | :---------: | | **ID** | 0.0089 | 0.0091 | 0.0083 | | **Visc./Force OOD** | 0.011/0.103 | 0.012/0.104 | 0.011/0.043 | Forcing-frequency OOD error decreases from 0.103 to 0.043, approximately 59%, while ID and viscosity OOD errors improve from 0.0089/0.011 to 0.0083/0.011 . Removing the forcing branch instead yields 0.0091/0.012/0.104, indicating limited benefit from the original affine branch. **We have revised Table 1, 2 in main paper and paragraph "HeterNS" in Appendix C.1.1.** ______Dear Reviewer iRK6,
As the discussion period is approaching its deadline, we would like to kindly follow up and ask whether you have had an opportunity to review our response, and whether there are any remaining questions or concerns that we could further address.
Your feedback, including both constructive suggestions and points of concern, has been invaluable in helping us improve our work. We have made every effort to carefully address each of your comments and clarify any potential misunderstandings. We sincerely value the opportunity for further discussion and would greatly appreciate any additional feedback you may have.
Thank you again for your time and thoughtful consideration.
Best regards,
Authors of Submission 8314
We appreciate the reviewer’s thoughtful assessment and constructive feedback. Below, we address the comments in detail and present additional experiments to further validate our approach and strengthen our findings.
CW1.1 Baseline transcription errors
We apologize for the mistakes and thank the reviewer for the detailed suggestion. The revision is made in Table 1 in the main paper and Table 28.
CW1.2: Heterogeneous experimental settings (Resolution, trajectory length, training strategies, model capacity, PDE priors, training budget.)
Clarification: The heterogeneous experimental settings primarily stem from differences in the original baseline configurations. For instance, ENMA uses a spatial resolution of 128 for Advection and Combined Equation, while Zebra conditions on a full trajectory under a given PDE parameter, compared to ENMA's three historical frames. Our initial goal was to preserve each baseline's original configuration for faithful reproduction, which inadvertently led to heterogeneous experimental settings.
To address your concerns regarding resolution and trajectory length, we have conducted additional experiments on major baselines with identical resolution and length settings with PDE-JEPA (as shown in Table 1).
PDE-JEPA still outperforms all baselines. We have also revised the report in Main paper Table 1, 2, Appendix Table 33 and configuration in Appendix Table 10, 11, 13, 14, 15, 17, 18.