- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
FlowCTS formulates distillation for flow models as matching student and reference trajectories from a shared starting state. A velocity-based upper bound yields weighted local losses over K subsequent states. K=1 reduces to velocity MSE at a student-visited state. The paper evaluates multi-reference distillation on SD3.5-Medium and an off-policy extension using straight image-noise paths. It reports better GenEval, OCR, and PickScore than a controlled transition-KL baseline. It also analyzes temporal weighting and finds that earlier supervision helps GenEval. The OPD student starts from averaged expert LoRA weights, as specified in Appendix C.1.
Critical strengths
-
The paper connects a simple trajectory objective to an implementable family of velocity losses. Appendices A and B derive the temporal weights explicitly. Appendix F also shows that the compared transition KL is a time-weighted velocity MSE. The controlled early/middle/late supervision experiment in Appendix G supports the practical relevance of the temporal allocation analysis for GenEval.
-
The controlled K=1 comparison is promising. Table 1 improves GenEval from 0.90 to 0.93, OCR from 0.90 to 0.92, and PickScore from 22.75 to 23.06 under a shared OPD pipeline. Table 3 also improves all four reported image-quality and preference metrics. The authors disclose that MAR is disabled for both objectives in Appendix C.1. This is a useful objective comparison, although it is not a comparison against the complete Flow-OPD system. The off-policy OCR improvement provides additional evidence beyond the main setting.
Critical weaknesses
-
The multi-step method is not specified precisely enough to reproduce or interpret. Section 3.3 defines h=(t_s-t_e)/K. For fixed endpoints, increasing K refines the discretization over the same interval. However, Sections 3.3 and 4.3 repeatedly interpret K as extending the supervision span. The paper does not specify how t_e is selected or how the interval changes with K. Appendix C.1 freezes reference predictions, but does not state whether the starting state and intermediate student states are detached. Backpropagating through x_i^theta in Equation 10 optimizes a different gradient from treating each state as fixed. These choices directly affect both the trajectory interpretation and the optimization-difficulty explanation for larger K.
-
The main results establish the value of local velocity matching more clearly than the added value of the trajectory construction. Most gains already occur at K=1, which removes the KL temporal weight. A related local velocity-MSE objective on routed student states also appears in DanceOPD, which the paper cites as concurrent work: https://arxiv.org/abs/2606.27377 . The multi-step extension remains a plausible contribution, but Table 1 shows only a 0.01 GenEval gain at K=2, unchanged OCR, and lower PickScore. Table 4 matches supervised evaluations, but does not isolate the derived weights from uniform multi-step weighting. Uncertainty for these small differences is not reported. Moreover, the headline gains over the pretrained model include an averaged expert-LoRA initialization whose standalone performance is missing. The controlled KL comparison remains informative, but it does not establish how much of the headline capability gain comes from FlowCTS itself.
Questions for authors
-
Clarification: How are t_s, t_e, and h chosen for each K? Which starting and intermediate states are detached, and which losses backpropagate through the student rollout? Please give the actual update algorithm for both OPD and SFT.
-
Assessment-relevant control: What are the scores of the averaged expert-LoRA initialization before OPD? How much improvement does each objective achieve from that common starting point?
-
Assessment-relevant control: Does trajectory-derived weighting outperform uniform weighting over identical multi-step states? Please report uncertainty and total compute for this comparison and the matched-evaluation K=1/K=2 control. Appendix D already averages generation seeds, but neither their count nor uncertainty is given.
-
Clarification: What exact normalization and unrounded values produce Table 1's Overall scores? Why does Figure 5's base-model reference appear near 0.64 rather than the 0.63 reported in Table 1?
3 comments
W2 & Q2: Initialization scores and the benefits of multi-step supervision
Thank you for highlighting the need to distinguish the gains from initialization, distillation, and multi-step supervision. We have evaluated the averaged adapter before distillation and report its scores below:
| Initialization | GenEval ↑ | OCR ↑ | PickScore ↑ |
|---|---|---|---|
| Averaged adapter | 0.7559 | 0.7769 | 22.226 |
Both objectives substantially improve upon this common initialization, bringing the student to approximately expert-level performance. Beyond these gains from distillation, the additional value of multi-step supervision lies in both training efficiency and final performance.
In our distillation setting, the teacher’s capabilities impose a practical bottleneck on performance gains, leaving limited room for further improvement once the student approaches expert performance, and K=1 already approaches expert performance on GenEval. Nevertheless, K=2 reaches expert performance at 660 updates, compared with 1,440 updates for K=1 in the reported comparison, and surpasses the expert by 1,020 updates. Reaching expert performance requires approximately 50 H200 GPU-hours for K=2, compared with 70 H200 GPU-hours for K=1. K=2 also achieves a higher final overall score, although the gains differ across metrics.
| Supervision steps | 660 updates | 1,020 updates | 1,440 updates |
|---|---|---|---|
| K=1 | 0.9231 | 0.9250 | 0.9304 |
| K=2 | 0.9313 | 0.9421 | 0.9419 |
We acknowledge that more trajectory supervision is not always better, and its benefits may depend on optimization difficulty, model capacity, and training data. Our primary focus is to identify a natural form of OPD supervision for flow models. The auxiliary Gaussian distributions used for KL matching encode teacher information through their velocity-dependent means, without providing the rich distributional supervision naturally available from next-token vocabulary distributions in text OPD. This motivates us to start from trajectory discrepancy and derive a tractable velocity objective. While DanceOPD derives the Gaussian KL–weighted MSE connection and supports unweighted velocity matching through ablations, we additionally analyze how KL-induced temporal weighting affects supervision allocation. We see understanding how these factors influence longer trajectory supervision as a compelling direction for future research, and hope our findings inspire further exploration of scaling supervision steps.
W2 & Q3 : Weighting ablation and evaluation uncertainty
The results in Appendix D are averaged over three generation seeds. For clarity, we report the mean and standard deviation for the two requested controlled comparisons below, and will provide the corresponding statistics for the remaining results in the revised appendix. Given the available compute during the rebuttal period, we conducted this experiment with a single GenEval expert and 320 training updates, evaluating each configuration using three generation seeds.
The trajectory-derived weights achieve higher GenEval scores at both K=2 and K=3 in this setting, providing empirical support for the weighting scheme. More broadly, our main focus is how to formulate supervision for flow-model OPD; the weights follow from the trajectory-based formulation. This comparison helps clarify their contribution within that framework.
| Supervision steps | Trajectory-derived weights | Uniform weights |
|---|---|---|
| K=2 | 0.920 ± 0.0026 | 0.914 ± 0.0032 |
| K=3 | 0.926 ± 0.0035 | 0.917 ± 0.0038 |
Q4: Clarifying the Overall score and Figure 5 reference line
Following the fixed rescaling convention in the Flow-GRPO, we divide the raw PickScore by 26 and compute:
Overall = (GenEval + OCR + PickScore / 26) / 3.
In Figure 5, the base-model reference line is positioned at 0.63, consistent with Table 1. Its dashed rendering and line width make it visually appear closer to 0.64. We will adjust the plotting style to make its position clear in the revised manuscript.
Best,
The Authors
Dear Reviewer pWPE
As we are approaching the last day of the rebuttal period, we would like to thank you again for your time and constructive feedback on our paper.
We have provided detailed responses to your concerns, including clarifications of time selection and gradient paths in OPD and SFT, evaluations of the averaged LoRA initialization and multi-step training efficiency, and weighting ablations with means and standard deviations across three generation seeds. We have also clarified the Overall score calculation and the reference-line placement in Figure 5.
We understand that this is a busy period. When convenient, we would greatly appreciate it if you could review our responses and let us know whether they have addressed your concerns. If any questions remain, we would be happy to provide further clarification or discussion before the rebuttal period closes.
Thank you again for your time and consideration.
Best regards, The Authors
Dear Reviewer pWPE
Thank you for your thoughtful review . We appreciate your concrete suggestions for clarifying the contributions of multi-step supervision, the weighting scheme, and the student initialization.
We clarify the time selection and gradient paths below and provide the update procedures for both OPD and SFT.
Time selection. Both OPD and SFT use the fixed step size h prescribed by the ten-step sampling schedule, independently of the supervision step count K. Starting from ts, we advance K steps with this spacing, giving te=ts−Kh. Thus, h=(ts−te)/K describes the selected interval, rather than refining a fixed interval as K increases. Before reaching the time boundary, increasing K extends the supervision span. The difference lies in how the starting state is obtained: OPD uses an online student rollout to reach ts, whereas SFT constructs the state by adding noise to a data sample at a randomly selected ts. We recognize that the step size affects supervision resolution and coverage; jointly exploring step size and supervision length is a promising direction for future work.
Gradient paths. Under the unified stop-gradient scheme, both OPD and SFT detach the starting state and all intermediate student states, while retaining gradients through the student velocity predictions at each supervised state. Each loss therefore updates the corresponding student prediction without backpropagating through preceding rollout transitions. OPD reference targets are computed without gradients using the frozen teacher; SFT uses the fixed data-derived target ϵ−z.
In our experiments, both OPD and SFT use the fixed step size h prescribed by the ten-step sampling schedule, independently of K.
OPD
SFT
K denotes the number of supervised velocity predictions over K integration intervals. Computing these losses requires only K−1 state updates, since the final endpoint is not itself supervised. We will add these details and revise the corresponding descriptions in the updated manuscript. Thank you for helping us make the method clearer and more reproducible.