- Rating
- 3(+1)
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 3
- Soundness
- 2
Read review
Paper summary
This paper proposes DS-Flow, a learned dual-stream corrector for few-step diffusion sampling. Instead of repeatedly calling the denoiser within each coarse solver interval, DS-Flow reuses the current denoising direction and performs multiple lightweight micro-step corrections. A global branch operates in an online PCA subspace, while a local branch corrects spatial residuals in pixel space. The corrector is trained from dense teacher trajectories(e.g. 50step) and is designed to map naturally onto analog dynamical-system hardware, where the repeated micro-corrections are intended to be cheap. Experiments on CIFAR-10, ImageNet-64, and LSUN Bedroom at 5–10 NFE show improved FID over several solver and learned-correction baselines. The hardware latency and energy results are obtained from circuit-level simulation rather than a fabricated DS chip.
Critical strengths
-
Novel algorithm-hardware co-design.
The idea of combining learned diffusion correction with dedicated dynamical-system hardware is interesting and relatively novel. Most learned solvers focus only on the algorithmic side, while this work explicitly designs the corrector with efficient hardware execution in mind. -
Relatively strong few-step performance.
DS-Flow achieves strong results in the 5–10 NFE regime, outperforming several higher-order solvers and learned-correction methods such as AMED across multiple benchmarks. This supports the effectiveness of the proposed in-step correction strategy.
Critical weaknesses
-
The hardware co-design is not validated on actual hardware.
Hardware efficiency is a central motivation of the method, but all generation results are obtained in software and the DS latency/energy numbers come from circuit-level simulation rather than a fabricated end-to-end GPU–DS system. Since the claimed advantage relies heavily on making the 50 micro-corrections cheap, real hardware validation is important to support the practical claim. -
The comparison with recent learned few-step solvers is incomplete.
The paper mainly compares with methods such as AMED, PAS, and conventional ODE solvers, but misses more recent learned few-step approaches such as LD3 [1] and DyWeight [2]. These methods target the same low-NFE regime and also include a learning phase, so including them would be important for establishing the competitiveness of DS-Flow against more current baselines.
[1] Learning to Discretize Denoising Diffusion ODEs
[2] DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling
Questions for authors
-
Could the authors provide a more concrete validation of the proposed hardware co-design, ideally with an actual hardware prototype or hardware-in-the-loop implementation? Since the efficiency of the repeated micro-corrections is central to the motivation of DS-Flow, real end-to-end latency and energy measurements would substantially strengthen the paper beyond circuit-level simulation.
-
Could the authors compare DS-Flow with more recent learning-based few-step methods, such as LD3 [1] and DyWeight [2]? These methods target a similar low-NFE setting.
-
Since each denoiser evaluation is followed by up to 50 learned micro-corrections, could the authors report the actual end-to-end wall-clock cost of DS-Flow in the software/GPU setting? NFE alone does not capture this additional computation, so a matched-quality latency comparison would make the efficiency claim clearer.
-
Does DS-Flow require a separately trained corrector for each NFE setting? The paper appears to generate teacher trajectories for each dataset and NFE configuration. It would be useful to know whether a single corrector can generalize across different sampling budgets.
[1] Learning to Discretize Denoising Diffusion ODEs
[2] DyWeight: Dynamic Gradient Weighting for Few-Step Diffusion Sampling
5 comments
Response to Reviewer BVQk (2/3)
W2. Recent learned few-step solvers. Thank you for pointing us to LD3 and DyWeight, which we had not compared against; we are glad to add both. Their published numbers use settings that differ from ours, so we report each comparison together with its setting. All numbers use the same EDM checkpoints and 50k-sample FID.
LD3 (CIFAR-10 / ImageNet-64, as listed in DyWeight's comparison table; DS-Flow from Table 1):
| Method | Base solver | NFE 5 | NFE 6 | NFE 8 |
|---|---|---|---|---|
| LD3 | best of three third-order solvers at each NFE | 6.39 / 11.55 | 3.35 / 7.53 | 2.81 / 5.40 |
| DS-Flow | one first-order Euler solver | 4.55 / 10.67 | 3.23 / 7.60 | 2.57 / 4.33 |
LD3 learns the time discretization of a multi-step solver. As listed in DyWeight's table, its value at each NFE is the best over its base solvers; on CIFAR-10 these are DPM-Solver++(3M), iPNDM(3M) and UniPC(3M) (LD3, Table 18). Even with this choice, DS-Flow on a single first-order base is ahead in five of six settings.
DyWeight (CIFAR-10, NFE 5, FID / FD_DINOv2, measured by us with 50k samples):
| Matched setting | DyWeight | DS-Flow |
|---|---|---|
| Neither trained on Inception features (DyWeight with L2) | 7.27 / 255 | 4.51 / 260 |
| Both trained with DyWeight's Inception-feature loss (DS-Flow column: DS-Flow added on DyWeight's solver) | 3.02 / 228 | 2.85 / 201 |
DyWeight learns weights for combining past gradients and supervises the final sample in the features of the Inception network that FID itself uses, so part of its gain may be specific to FID (Kynkäänniemi et al., ICLR 2023); we therefore also report FD_DINOv2. With this objective it reports 3.02, 2.61 and 2.18 on CIFAR-10 and 6.30, 6.15 and 4.22 on ImageNet-64 at NFE 5, 6 and 8. Without it, DS-Flow has the lower FID and the two are within 2% on DINOv2 features (Stein et al., NeurIPS 2023), which neither method trains on; with it, the DS-Flow corrector is complementary and lowers both of DyWeight's scores further. DyWeight's own default setting (10K teacher samples) also gives 4.69 on ImageNet-64 at NFE 8 (its Table A.4), above DS-Flow's 4.33.
DS-Flow also works at a different level: LD3 and DyWeight improve the outer solver, i.e. where to step and how to combine past gradients, whereas DS-Flow refines the state within each step.
Response to Reviewer BVQk (3/3)
Q1. Prototype or hardware-in-the-loop validation. Thank you for the suggestion. A prototype or hardware-in-the-loop measurement needs the fabricated DS-Flow chip, which does not exist yet; we plan to tape it out next year. Until then, the circuit-level simulation in W1 follows the standard pre-silicon practice described there, since a fabrication cycle takes many months.
Q2. Comparison with LD3 and DyWeight. Thank you; please see W2. We will add both comparisons, with their settings, to the revision.
Q3. End-to-end wall-clock on GPU. Thank you for this request, which makes the efficiency claim clearer. CIFAR-10, per sample on one A100, with the corrector run on the GPU; FID is taken from Table 1:
| Method | NFE | FID | Latency per sample |
|---|---|---|---|
| GITS | 8 | 3.24 | 8.11 ms |
| PAS | 8 | 3.87 | 9.56 ms |
| DS-Flow | 8 | 2.70 | 10.12 ms |
| GITS | 10 | 2.49 | 10.32 ms |
| PAS | 10 | 2.84 | 12.07 ms |
At equal NFE=8, DS-Flow gives the best FID among these methods, and at matched quality its latency is comparable: GITS needs NFE=10 (10.32 ms) to pass DS-Flow's 2.70 at NFE=8 (10.12 ms), and PAS at NFE=10 (12.07 ms) remains worse. From the measured latencies above, the 50 micro-corrections take about 2 ms per sample on the GPU at NFE=8 (about 0.25 ms per interval), DS-Flow's gap to GITS, which adds negligible computation to its iPNDM base solver. On DS hardware they cost 1.4 µs per interval in simulation, about 11 µs per sample at NFE=8, so the end-to-end time is dominated by the denoiser calls.
Q4. One corrector per NFE. Thank you for the question. Yes, we currently train one corrector per (dataset, NFE) setting, with the same architecture and hyperparameters. The cost is small: about 58K parameters and about 3 A100-hours per setting on CIFAR-10, with the denoiser frozen. This does not limit DS-Flow's practical use: a deployment usually runs at a fixed NFE budget, and moving to another budget only means programming a different set of the same ~52K couplings into the same circuit (Appendix F). A corrector that generalizes across budgets is possible in principle: it would replace the learned interval embedding e_i with the interval's noise level and step size as continuous inputs and train on teacher trajectories from randomly sampled intervals, much as diffusion models are trained on random timesteps. We have not tested this and will note it as future work in Appendix H.
Thank you again for the thoughtful review and constructive questions. We hope these answers address your concerns, and we would be glad to discuss any point further. If any additional experiment would help, we would be happy to run it during the discussion period.
Response to Reviewer BVQk (1/3)
We sincerely thank Reviewer BVQk for the thorough and constructive review, and for recognizing the algorithm-hardware co-design as novel and the 5 to 10 NFE results as strong. We answer each point below.
W1. Validation on real hardware. Thank you for raising this important point. We agree that a fabricated DS-Flow chip does not exist yet; Section 4.1 and the Reproducibility Statement say so. The reported speedup and energy are nonetheless grounded in three ways:
The algorithm itself does not depend on the hardware: run on a GPU, DS-Flow remains competitive end to end (Q3).