- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
Because the sampler's transition density is diagonal-Gaussian, the log-density change decomposes exactly over latent positions, so the paper asks which positions should share a PPO clipping decision: FlowGRPO clips one global geometric-mean statistic that is blind to sign-cancelling spatial patterns, while pure positionwise ("1×1") clipping keeps local information but never coordinates related positions. FlowSAPO retains the exact 1×1 branch and adds a regional one — during rollout the model's own text attention grows connected, overlapping regions of similar-attending cells under a noise-dependent size cap, each region's local log-ratios are summed with inverse-coverage normalization (an exact conservation identity) and clipped at an area-dependent width, regions are frozen during replay, and the two branches mix at 0.75/0.25 under a shared scalar advantage; App. H analyses all three clipping scopes under a fixed-state Gaussian model.
Critical strengths
- The theoretical appendix is disciplined about its own scope to an unusual degree, which makes it trustworthy rather than decorative
- Experimental results indicates the effectiveness of the proposed method.
Critical weaknesses
-
A single training seed per setting, with the checkpoint picked at peak reward on the very quantity being optimized. App. B.4: "We fix the base training seed to 3407 for all experiments"; "we select the checkpoint with the highest evaluation reward for the training objective"; "we therefore do not require paired confidence intervals or estimates of variability across independent training runs". That rule inflates exactly the deltas in dispute, and several entries in the same tables run the other way: SD3.5 UnifiedReward 3.382 versus DiffusionNFT's 3.423, and on VBench both Object Class (0.749) and Background Consistency (0.973) fall below the untrained Wan2.1 base (0.772, 0.984). Comparability compounds it — FlowGRPO is run at clip width 1e-4 (images) / 1e-3 (videos) while 1×1 uses 0.10, and neither crossover is reported, so "global versus local" is partly a comparison of band widths.
-
No semantics-free control for a method titled "semantics-aware".
Questions for authors
Please run 2–3 independent training seeds for at least SD3.5/PickScore and Wan VQ+MQ, reporting mean ± std for FlowGRPO, 1×1 and FlowSAPO, and say whether the selected checkpoint would change under selection by final-step reward. This is the single addition that would move my rating.
7 comments
Response to Weakness 1 (Part 2): Metric Comparisons and Clipping Widths
Thank you for examining the metric-level comparisons and clipping configurations. We clarify the reported metric differences and provide additional clipping-width experiments. The new tests retain FlowSAPO’s advantage over 1×1 on all six DrawBench metrics at base widths of 0.2 and 0.7, showing that the gain extends beyond the default setting of 0.1.
1. Metric-specific comparisons.
For SD3.5 UnifiedReward in Table 1, FlowSAPO scores 3.382 versus DiffusionNFT’s 3.423, while exceeding the base model, FlowGRPO, and 1×1 at 3.094, 3.338, and 3.220. On FLUX.1 [dev], FlowSAPO outperforms DiffusionNFT on all six reported metrics, including UnifiedReward, 3.578 versus 3.568. The UnifiedReward gap therefore occurs in the evaluated SD3.5 configuration, while the FLUX comparison shows gains across all six metrics.
For Wan in the original Table 3, Background Consistency and Object Class are lower than the base model, but both exceed FlowGRPO under the same VQ/MQ reward: 0.973 versus 0.970 and 0.749 versus 0.741. FlowSAPO improves seven of eight reported VBench dimensions over FlowGRPO and six over the base model, alongside higher VQ and MQ rewards. These comparisons evaluate optimization methods under the same prescribed reward, with VBench providing an independent assessment.
2. Clipping definitions and sensitivity.
FlowGRPO’s clipping widths, for images and for videos, apply to a global weight obtained by averaging log-density changes across the latent space. Our width of 0.1 applies to exact positionwise density ratios, defining the local interval [0.9, 1.1]. The numerical widths therefore operate on different statistical scales. Moreover, changing a global threshold cannot recover local changes that cancel during global aggregation.
We preserve FlowGRPO’s baseline formulation and configuration. Its maintainer also reported that replacing the global mean with a sum remained unstable after adjusting the clipping coefficient (official discussion).
We additionally tested FlowSAPO with base clipping half-widths of 0.2 and 0.7, keeping the regional area exponent fixed at 0.7. As shown in Table R2, both wider settings retain the advantage over 1×1 on all six metrics, with PickScores of 23.824 and 23.834, close to the default 23.828. These controls are now included in Appendix L.5 (Table 12), with reference scores in Appendix L.4, Table 11.
Table R2. Clipping-width controls on SD3.5 Medium with PickScore training and DrawBench evaluation. All results use training seed 3407. Higher is better.
| Method and clipping setting | PickScore | CLIPScore | HPSv2.1 | Aesthetic | ImageReward | UnifiedReward |
|---|---|---|---|---|---|---|
| FlowGRPO, global width | 23.438 | 0.280 | 0.304 | 6.024 | 1.310 | 3.338 |
| FlowSAPO (1×1), local width 0.1 | 23.561 | 0.272 | 0.294 | 6.038 | 1.277 | 3.220 |
| FlowSAPO, base width 0.1 | 23.828 | 0.275 | 0.315 | 6.084 | 1.354 | 3.382 |
| FlowSAPO, base width 0.2 | 23.824 | 0.274 | 0.310 | 6.099 | 1.322 | 3.351 |
| FlowSAPO, base width 0.7 | 23.834 | 0.278 | 0.314 | 6.055 | 1.344 | 3.329 |
The improvement over 1×1 is retained at all three tested FlowSAPO widths. The default full-versus-1×1 comparison also uses the same local clipping width of 0.1, directly supporting the additional contribution of the regional branch.
Response to Weakness 2: A Semantics-Free Region Control
Thank you for calling for a direct test of semantic grouping. We have added a random connected-region control and a static SAM3 alternative on SD3.5 Medium, trained with PickScore and evaluated on DrawBench. Table R3 shows that random grouping underperforms 1×1 on all six metrics, whereas FlowSAPO improves all six and outperforms both regional alternatives.
Random regions without semantic member selection. At every rollout step, we record the original region size at each attention-cell seed. We then grow a replacement region from the same seed by uniformly sampling its eight-connected frontier until the recorded size is reached. Coverage is recomputed, and the objective and clipping rules are retained. This preserves connected aggregation, region sizes, and their area-dependent clipping widths while removing attention-guided member selection.
SAM3 as an alternative semantic grouping. We obtain SAM3 regions from each completed rollout image and reuse them at every denoising timestep. This provides an external semantic grouping method to compare with our regions derived from the generator’s text attention at each sampled state.
Both experiments and their results have been incorporated into Appendix L.4 (Table 11) of the revised manuscript.
Table R3. Region-construction controls on SD3.5 Medium with PickScore training and DrawBench evaluation. All results use training seed 3407. Higher is better.
| Method | PickScore | CLIPScore | HPSv2.1 | Aesthetic | ImageReward | UnifiedReward |
|---|---|---|---|---|---|---|
| FlowGRPO | 23.438 | 0.280 | 0.304 | 6.024 | 1.310 | 3.338 |
| FlowSAPO (1×1) | 23.561 | 0.272 | 0.294 | 6.038 | 1.277 | 3.220 |
| Random connected regions | 23.342 | 0.269 | 0.285 | 6.017 | 1.227 | 3.046 |
| SAM3 regions | 23.523 | 0.273 | 0.308 | 6.059 | 1.311 | 3.223 |
| FlowSAPO | 23.828 | 0.275 | 0.315 | 6.084 | 1.354 | 3.382 |
Across all six metrics, the ordering is FlowSAPO > SAM3 regions > random regions. Yet random regions remain below the positionwise baseline on every metric, showing that adding a regional loss with matched sizes and clipping widths is insufficient to obtain the gains. SAM3 improves over random grouping and raises PickScore above FlowGRPO, while our attention-derived construction further reaches 23.828 and exceeds SAM3 on all six metrics.
These controls directly establish the practical importance of region membership: semantic grouping is beneficial in this comparison, and our construction delivers the strongest results among the tested alternatives using the generator’s own attention.
Response to Weakness 1 (Part 1): Training Seeds and Checkpoint Selection
Thank you for the detailed comments on training variability and checkpoint selection. We have completed three independent training runs for every method in both requested settings and extended the SD3.5 training comparison. FlowSAPO improves all six DrawBench metrics and all eight reported VBench dimensions over 1×1 in the three-seed averages, and remains ahead of both baselines at the extended SD3.5 training endpoint.
1. Three independent training seeds.
We trained FlowGRPO, FlowSAPO (1×1), and full FlowSAPO with seeds 3407, 2025, and 2026 in both SD3.5 Medium with PickScore training and Wan2.1-T2V 1.3B with VQ/MQ training. Repeated runs keep each method’s training configuration, budget, and evaluation protocol fixed.
Tables R1a–R1b report mean ± standard deviation across independent training runs. These results are now included in Appendix L.3 (Tables 9 and 10).
Table R1a. SD3.5 Medium trained with PickScore and evaluated on DrawBench. Higher is better.
Table R1b. Wan2.1-T2V 1.3B trained with VQ/MQ and evaluated on VBench. Higher is better.
FlowSAPO also achieves higher means than FlowGRPO on five of six image metrics and seven of eight video dimensions, with motion smoothness tied at the reported precision. Its PickScore gain over FlowGRPO is 0.382, while its observed standard deviation is 0.051; its VBench standard deviations range from 0.002 to 0.008. The performance advantage is retained when training variability is measured directly.
2. Checkpoint selection and performance later in training.
We apply the same optimized-reward selection criterion within matched training budgets to our reproduced comparisons, including DiffusionNFT (Appendix B.4). We aim to demonstrate both higher rewards with fewer optimizer updates and a sustained advantage as training continues. We therefore extended the SD3.5 runs of FlowGRPO, 1×1, and FlowSAPO from 4,320 to 8,640 updates and report the subsequent evaluation curves.
FlowSAPO at 4,320 updates already exceeds FlowGRPO’s reward at 8,640 updates, and remains ahead of both baselines at the extended endpoint. The curves are available through this anonymous visualization link and are included in Appendix L.2 (Figure 18).
FlowSAPO also remains ahead of FlowGRPO at the final displayed evaluations in Figure 1(b) for Wan VQ/MQ, Figure 4(a) for Wan OCR, and Figure 8 for FLUX PickScore. These results substantiate the gains through independent training repetitions and sustained performance at fixed training endpoints.