- Rating
- 3
- Confidence
- 3
- Informativeness
- 3
- Presentation
- 3
- Soundness
- 3
Read review
Paper summary
LyapuFlow is a training-free method for guiding pretrained flow models using constraints evaluated at predicted endpoints. Its full controller computes a minimum-norm correction from a Lyapunov decrease condition, followed by velocity-relative clipping. The latent implementation uses a stop-gradient approximation and optionally restores full derivatives later. Experiments on four PDE tasks and image super-resolution and deblurring assess constraint satisfaction, sample fidelity, and computational cost.
Critical strengths
1.Clear formulation and practical relevance.
The paper clearly explains how endpoint predictions and a Lyapunov decrease condition yield adaptive feedback. Applying new observations or physical constraints without retraining the generative model is practically valuable.
2.Meaningful empirical support.
Experiments cover different PDE dynamics and multiple image restoration settings. Baseline comparisons, component ablations, and runtime measurements provide useful evidence supporting the complete sampler under the tested configurations.
Critical weaknesses
1.The contribution needs clearer positioning relative to prior work.
The control law follows a classical minimum-norm construction, so the contribution depends on its adaptation to generative sampling. MPC-Flow is particularly relevant because it also uses endpoint-based objectives for inference-time control of flow models. Comparing objectives, assumptions, derivative requirements, and computational costs would help qualify the introduction’s research-gap claim.
2.The benefits of the feedback rule are not fully isolated.
Baselines differ in correction location, scaling, derivatives, and clipping. During latent stop-gradient sampling, the controller becomes loss-normalized gradient guidance and no longer uses nominal-flow progress to gate intervention. As acknowledged by the authors, it does not generally guarantee decrease of the true Lyapunov function. A matched endpoint-guidance baseline would clarify its specific contribution. PDE errors before final projection and image measurement residuals would also strengthen the constraint-satisfaction evidence.
Questions for authors
1.How does LyapuFlow differ from prior endpoint-based control methods, particularly MPC-Flow, in its objective, assumptions, and computational requirements?
2.Could the authors provide a matched endpoint-guidance comparison and report PDE constraint errors before final projection and measurement residuals for images?
3.Can LyapuFlow be applied to other latent flow models, such as FLUX? What assumptions would be required, and would the stop-gradient approximation or gradient-switching schedule need to be adapted? Are results on another backbone available?
5 comments
Response to Reviewer H28o (2/3)
Feedback rule and constraint satisfaction (W2 and Q2)
(1) Matched endpoint-guidance ablation. The correction location and feedback rule are coupled: moving the same correction directly to the predicted endpoint would no longer implement the derived Lyapunov decrease condition. Endpoint-based methods are already included among our baselines. To isolate the contribution of the Lyapunov-based feedback gain, we ran an additional ablation comparing LyapuFlow against constant-coefficient gradient correction. Both methods use the same predicted terminal sample, constraint gradient, correction location, and trust-region clipping. The only difference is the feedback coefficient. Writing , the unbounded controls are
| Method | Update rule |
|---|---|
| LyapuFlow | |
| Constant-coefficient |
We evaluated both methods with all-step stopgrad on the same five AFHQ dog images for Gaussian deblurring. All experiments use SD3.5-Medium, CFG 2, 28 NFEs, seed 0, measurement noise , and trust-region ratio .
| Method | PSNR ↑ | SSIM ↑ | LPIPS ↓ |
|---|---|---|---|
| LyapuFlow () | 28.927 | 0.7881 | 0.1262 |
| LyapuFlow () | 29.007 | 0.7965 | 0.1220 |
| LyapuFlow () | 29.013 | 0.7952 | 0.1359 |
| Constant-coefficient () | 28.182 | 0.7553 | 0.1178 |
| Constant-coefficient () | 28.773 | 0.7886 | 0.1388 |
| Constant-coefficient () | 28.796 | 0.7897 | 0.1388 |
| Constant-coefficient () | 28.795 | 0.7898 | 0.1386 |
| Constant-coefficient () | 28.796 | 0.7898 | 0.1386 |
LyapuFlow achieves higher PSNR than all tested constant-coefficient settings and the best SSIM at . The constant-coefficient method obtains the lowest LPIPS at , but with lower PSNR and SSIM. Although this is a small ablation, these results suggest that adapting the correction magnitude to the current Lyapunov energy provides an advantage over the tested fixed-coefficient alternatives, even when velocity gradients are omitted.
(2) Image measurement residuals. We also study measurement consistency during sampling. The newly added control profiles in Appendix C.5 compare full gradients and stopgrad using the same image and measurement. The following table shows the results for one FFHQ motion-deblurring example.
| Velocity gradient | Residual norm, first → last | PSNR ↑ | SSIM ↑ | LPIPS ↓ |
|---|---|---|---|---|
| Full gradients | 761.99 → 45.04 (−94.09%) | 21.74 | 0.450 | 0.218 |
| 761.99 → 44.91 (−94.11%) | 27.86 | 0.725 | 0.117 |
Both settings reduce the measurement residual by approximately 94% in this example. Despite omitting velocity gradients, stopgrad achieves comparable residual reduction and better reconstruction quality. This supports the practical effectiveness of the approximation. However, it does not provide the same formal decrease guarantee as the full controller.
(3) PDE constraint errors before final projection. We added a before-and-after projection comparison for all methods in Appendix B.6. The table below summarizes LyapuFlow's constraint errors across the four PDE tasks. Each entry reports before → after final projection.
| Task | CE(IC) / | CE(CL/NCL) / |
|---|---|---|
| Heat | 2.031 → 0.000 | 5.040 → 0.001 |
| Burgers | 3.253 → 0.000 | 2.323 → 0.005 |
| RD | 1.051 → 0.000 | 1.442 → 0.000 |
| NS | 15.597 → 0.000 | 5.045 → 0.000 |
These results show that LyapuFlow already achieves low constraint errors before final projection. Projection further reduces the remaining violations. Importantly, as discussed in our response to Reviewer mfTc, LyapuFlow also achieves the lowest mean-field error across all four PDE tasks before projection, so its improvement in sample fidelity cannot be attributed to the final projection steps alone.
Response to Reviewer H28o (3/3)
Applicability to other latent flow models (Q3)
LyapuFlow can be applied to other latent flow models provided that the model supplies a velocity prediction and the constraint loss is differentiable through the decoder and measurement operator. The stop-gradient approximation does not require differentiating through the velocity network, while the gradient-switching schedule and feedback parameters may need adjustment for a different backbone.
To evaluate this, we ran additional experiments using FLUX.2, following the setup of MPC-Flow. We use 50 sampling steps and CFG scale 4, evaluating five images across three inverse-problem settings using 3 seeds (15 runs per method). LyapuFlow uses , trust ratio 1, and stopgrad throughout. MPC-Flow uses MPC-RHC () with 20 inner steps and learning rate 0.5, while FlowChef uses learning rate 0.5 and one inner step.
| Method | PSNR (dB) ↑ | SSIM ↑ | Seconds/image ↓ |
|---|---|---|---|
| LyapuFlow | 25.815 ± 2.550 | 0.7572 ± 0.0611 | 26.97 |
| MPC-Flow | 25.129 ± 1.835 | 0.7307 ± 0.0691 | 124.13 |
| FlowChef | 23.061 ± 0.857 | 0.6817 ± 0.0732 | 27.63 |
LyapuFlow achieves the highest mean PSNR and SSIM in this evaluation, while running approximately more than 4 times faster than MPC-Flow. It also outperforms FlowChef in reconstruction quality at similar runtime. These results provide initial evidence that LyapuFlow can be applied beyond the SD3.5-Medium backbone without changing its feedback formulation.
Response to Reviewer H28o (1/3)
We thank the reviewer for the constructive and detailed feedback.
MPC baselines (Q1 and W1)
We agree that the minimum-norm control construction is classical. Our contribution is to apply this construction to the constraint violation of a predicted terminal sample, allowing us to derive a closed-form feedback rule for pretrained generative flows. The following table compares related methods by their correction target, velocity-model derivatives, and optimization requirements.
LyapuFlow evaluates the constraint violation on a predicted terminal sample and computes the minimum-norm correction from a prescribed Lyapunov decrease condition. The correction is zero when the nominal flow already satisfies this condition. MPC-Flow instead optimizes a soft terminal objective and control effort at each sampling step, while HardFlow uses constrained trajectory optimization to enforce terminal feasibility.
LyapuFlow requires a differentiable constraint loss and an endpoint prediction, but does not require an optimization loop. Its full controller differentiates through the velocity model, while the stop-gradient approximation avoids this additional cost. We will clarify these distinctions and the corresponding computational requirements in the revised paper.