- Rating
- 2
- Confidence
- 2
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes AuxPath-FM, which incorporates auxiliary variables with continuous & discrete distributions, inclouding endpoint-dependent auxiliary variables, into the path of flow matching, and presents the theoretical justification for the continuity equation and regression objective. By applying these auxiliary variables to conditional generation, the method presents the learned semantic auxiliary as an explicit drift component. This enables one-pass guidance, allowing the influence of the conditioning information to be adjusted using only a single backbone evaluation per sampling step. Experiments on datasets such as MNIST, CIFAR-10, and ImageNet demonstrate improvements in both conditional alignment and generation quality.
Critical strengths
-
This paper explores various auxiliary variables in flow matching and provides a theoretical foundation for them. It offers valuable insight by systematically categorizing the options available for designing paths.
-
One-pass guidance utilizing semantic auxiliary variables provides a useful control mechanism for conditional generation. This approach is practically significant, as it demonstrates the potential to improve generation quality without substantially increasing computational overhead.
Critical weaknesses
-
While this study offers valuable insights, the reasons for the performance gain are not sufficiently clear. Although some experiments show improvement, there is limited explanation clarifying the specific role of the proposed training method in these gains.
-
There is a lack of comparison based on similar computational costs (ex., Table 4). Since the proposed method and existing guidance approaches require different computational costs, it is difficult to determine whether it offers an advantage when using the same computational resources.
Questions for authors
-
Regarding weakness 1, could the author clarify the reasons for the observed performance gains, particularly the contribution of the proposed training method?
-
Are there any comparison results between the proposed method and existing guidance methods under comparable computational budgets?
4 comments
2. Generation quality at matched inference budgets.
At NFE=10, AuxPath-FM at auxiliary scale 2 improves FID, precision, and recall over the tested CFG settings. Each setting below uses 50,000 generated ImageNet-256 images and the original FID protocol. NFE counts conditional and unconditional backbone evaluations separately, including batched branches. Single-branch Euler sampling uses one evaluation per step; velocity CFG uses two:
| Method | CFG scale | Aux. scale | Sampling steps | NFE | FID ↓ | Precision ↑ | Recall ↑ |
|---|---|---|---|---|---|---|---|
| CFM | 1 | — | 10 | 10 | 38.7657 | 0.4188 | 0.6106 |
| CFG | 1.5 | — | 5 | 10 | 36.7015 | 0.3853 | 0.4002 |
| CFG | 2 | — | 5 | 10 | 28.3324 | 0.4445 | 0.2959 |
| AuxPath-FM | 1 | 1 | 10 | 10 | 33.9182 | 0.4456 | 0.5823 |
| AuxPath-FM | 1 | 2 | 10 | 10 | 27.3934 | 0.4706 | 0.5345 |
At guidance scale 2, AuxPath-FM achieves FID 27.3934 versus 28.3324 for CFG, with precision 0.4706 versus 0.4445 and recall 0.5345 versus 0.2959. Thus, the improvement includes both distributional fidelity and coverage at the same number of backbone evaluations. AuxPath-FM can use 10 integration steps within this budget, whereas two-branch CFG uses 5.
Performance across sampling budgets. AuxPath-FM improves FID over the matched CFM model at all four tested budgets. We evaluated the same checkpoints at 10, 20, 30, and 50 Euler steps with velocity CFG disabled, so each step uses one backbone evaluation:
| Sampling steps | NFE | CFM: FID ↓ | AuxPath w=1: FID ↓ | AuxPath w=2: FID ↓ |
|---|---|---|---|---|
| 10 | 10 | 38.7657 | 33.9182 | 27.3934 |
| 20 | 20 | 27.7283 | 24.9718 | 20.0395 |
| 30 | 30 | 24.7629 | 22.9552 | 18.4473 |
| 50 | 50 | 23.3294 | 21.6411 | 17.4678 |
At auxiliary scale 2, the 20-step result, FID 20.0395, is better than the 50-step CFM result of 23.3294; 30 steps further improve FID to 18.4473. Scale 1 also improves over CFM at every tested budget. These results complement the equal-NFE CFG comparison and show the quality–computation trade-off across the measured range.
The NFE=50 comparison against CFG requires 25 CFG integration steps. That matched-base evaluation is pending; the table above reports the completed CFM and AuxPath-FM results. We will add the 25-step CFG result when it is available.
Joint auxiliary guidance and CFG. Jointly tuning auxiliary guidance and velocity CFG improves generation quality: the best setting in our ImageNet-256 sweep reaches FID 4.1076. Both coefficients are adjusted on the same trained model. The following sweep uses 50 Euler steps and 50,000 generated images per setting under the original FID protocol:
| CFG scale | Aux. scale | Sampling steps | NFE | FID ↓ |
|---|---|---|---|---|
| 1 | 0.8 | 50 | 50 | 23.3339 |
| 1 | 0.9 | 50 | 50 | 22.4540 |
| 1 | 1 | 50 | 50 | 21.6411 |
| 1 | 2 | 50 | 50 | 17.4678 |
| 1.5 | 1 | 50 | 100 | 4.9719 |
| 1.5 | 1.5 | 50 | 100 | 4.8539 |
| 1.5 | 2 | 50 | 100 | 5.2349 |
| 2 | 0.8 | 50 | 100 | 4.1076 |
| 2 | 0.9 | 50 | 100 | 4.2334 |
| 2 | 1 | 50 | 100 | 4.3679 |
| 2 | 2 | 50 | 100 | 5.6816 |
At CFG=2, auxiliary scales 0.8, 0.9, and 1 give FIDs 4.1076, 4.2334, and 4.3679. At CFG=1.5, scale 1.5 gives 4.8539, while scale 2 gives 5.2349. The best tested auxiliary coefficient therefore depends on the velocity-guidance coefficient, and values below 1 are useful in the joint sampler. The 50-step configurations cost NFE=50 at CFG=1 and NFE=100 with two-branch CFG; the table makes this budget difference explicit.
Planned revision. Section 5.4 will include the equal-NFE comparison alongside Table 4, with separate columns for integration steps and NFE. Appendix D will include the sampling-budget curve and joint-guidance sweep. The accompanying discussion will connect generation quality to the corresponding computation budget.
I appreciate the author's rebuttal and the additional experiments.
I acknowledge that the proposed training method shows benefits at auxiliary strength 1. However, at strength 2, a frozen CFM using the same learned auxiliary performs comparably to or even better than the trained AuxPath-FM. Consequently, the substantive contribution of the additional training to the main performance gains remains unclear.
Could you please clarify how these results should be interpretred? Specifically, what additional advantages does the proposed training offer over simply applying sampling time guidance to a frozen backbone? Based on the evidence currently provided, I will maintain my original score.
Dear Reviewer ca3T,
Thank you for clarifying the training question. We assess its additional contribution using an equal-budget continuation experiment with a shared auxiliary network.
1. Matched training and its relation to the earlier results.
The earlier comparison used the original CFM without further backbone training and an existing adapted AuxPath-FM checkpoint. Its learned- evaluations shared the auxiliary network from that existing checkpoint.
For the matched control, both branches start from the original CFM and receive 40K additional steps with the remaining training settings matched. One learns on ordinary CFM paths; the other learns residual transport on auxiliary paths. Thus, the CFM control also receives 40K backbone updates. At inference, it uses translated-input auxiliary guidance, while the AuxPath branch uses its trained residual field. Both fixed backbones use the same from the new AuxPath branch's 40K checkpoint.
These FIDs correspond to new backbone and auxiliary weights, explaining their differences from the earlier results. The present table measures the training-path contribution at equal continuation budget. Both branches use 50-step Euler, CFG=1, NFE=50, and 50K samples.
| Auxiliary | CFM training + sampling-only guidance: FID ↓ | AuxPath training: FID ↓ | FID reduction |
|---|---|---|---|
| 1 | 24.14 | 23.23 | 0.91 |
| 1.5 | 20.38 | 20.16 | 0.22 |
| 3 | 20.51 | 20.44 | 0.08 |
Path training provides its largest additional benefit at the lower guidance strength. The gap narrows as guidance increases; reductions use unrounded FIDs.
Endpoint behavior at unit strength. At , translated-input sampling preserves the original CFM endpoint under exact integration. Using the original frozen backbone, 1,000 paired noise–label samples, CFG=1, and FP32, we compare it with ordinary CFM at each Euler step count. We average the per-sample endpoint L2 difference divided by the corresponding ordinary-CFM endpoint norm:
| Auxiliary | 10 Euler steps | 25 steps | 50 steps |
|---|---|---|---|
| Learned | 8.69% | 3.61% | 1.88% |
| Class mean | 9.29% | 3.86% | 2.02% |
The decreasing discrepancy is consistent with the endpoint-preserving coordinate transformation at unit strength.
2. Adaptation with larger auxiliary displacement.
We increased from to , raising its peak from 0.25 to 1. We jointly trained the backbone and for 300K steps from pretrained CFM-B/2. The baseline freezes the original backbone and uses class means. Both use 20-step Euler, CFG=1, NFE=20, and 50K images.
| Auxiliary | Frozen CFM + class means: FID ↓ | Jointly adapted backbone + learned : FID ↓ |
|---|---|---|
| 1 | 25.41 | 23.29 |
| 1.2 | 22.88 | 18.63 |
| 1.4 | 28.19 | 20.04 |
| 2 | 51.20 | 42.17 |
The complete adaptation scheme lowers FID by 4.25 and 8.15 at and . This comparison includes learning and adapting the backbone; the 40K control above isolates the training-path contribution.
3. Text-conditioned path learning.
A shared computes auxiliaries for new prompts without storing a mean for every text. This generalization serves both frozen and adapted variants; adaptation learns residual transport on the text-conditioned paths. Appendix F evaluates AuxPath-LoRA on SANA using BLIP-VQA, 30 held-out prompts, and 129 atomic questions. At , atomic accuracy reaches 85.27%, versus 80.62% for Standard LoRA; all-correct rates are 53.33% versus 40.00%. These results evaluate the complete learned approach.
4. Summary of contributions.
Finally, we summarize our three contributions.
(i) Theory: Wei–Ma Section 3.1 allows general path laws, while Appendix J.1 uses density-form integrals and Gaussian regularization with assumed limit exchanges. Stochastic interpolants' density analysis uses Gaussian auxiliary noise. Our test-function proof covers discrete, singular, and endpoint-dependent auxiliaries without density assumptions, establishing endpoint preservation and weak continuity for the proposed path family under finite first moments and absolutely continuous coefficients satisfying the endpoint constraints.
(ii) Auxiliary distributions: Wei–Ma's experiments use Gaussian-process streams; the cited stochastic-interpolants paper uses Gaussian auxiliary noise. They do not compare other auxiliary laws. Table 3 tests Gaussian, uniform, Laplace, Rademacher, and label-guided auxiliaries, including discrete noise and continuous non-Gaussian laws.
(iii) Learned semantic paths: Joint learning adapts auxiliary representations and residual transport for conditional generation, exposing an explicit velocity component for guidance.
We will add the new amplitude results to the appendix. We hope this framework supports further exploration of auxiliary distributions for flow learning, a direction we will continue pursuing. Thank you again for the constructive discussion.
The authors
Thank you for your time and suggestions on performance gains and matched-cost evaluation. We added controls separating auxiliary-path training from sampling-time guidance.
1. Contribution and sources of the performance gains.
AuxPath-FM makes the auxiliary distribution a design variable of an explicit, endpoint-preserving flow-matching path. The auxiliary may be discrete, learned, or coupled to the endpoints; our weak-transport and fixed-law regression guarantees do not require an auxiliary density. For conditional generation, this construction lets semantic information shape the transport path itself and exposes its effect as an explicit velocity component.
This path design supports both model adaptation and controllable generation. Training adapts the backbone to transport along the semantic path, while auxiliary CFG adjusts the explicit semantic component with one backbone prediction per integration step. It can also be combined with velocity CFG, giving the same model two independently adjustable controls. We assess training at unit auxiliary strength and sampling-time guidance by varying the coefficient with the checkpoint fixed.
Training and sampling controls. We compare ordinary CFM, frozen CFM with auxiliary guidance, and adapted AuxPath-FM. The learned-F rows reuse the same auxiliary network. All settings use 50 Euler steps, no velocity CFG, and 50,000 ImageNet-256 samples, evaluated with the original FID protocol.
Frozen CFM uses translated-input sampling. Adapted AuxPath-FM uses its native residual field trained on the auxiliary path.
At auxiliary scale 1, adapted AuxPath-FM achieves FID 21.6411, compared with 23.3294 for ordinary CFM and 23.0431 for frozen CFM with the same learned F. The benefit is therefore already present with the prescribed auxiliary term, before increasing its guidance coefficient. The paired DiT-B/2 experiment from random initialization also improves FID from 85.6556 to 83.6281 at scale 1. These comparisons support the contribution of backbone adaptation on the auxiliary path.
Keeping the adapted checkpoint fixed and increasing the auxiliary scale from 1 to 2 further improves FID from 21.6411 to 17.4678. Frozen CFM with the same learned F reaches 17.2810 at scale 2. These results identify a substantial sampling-time contribution alongside the unit-strength improvement of the adapted model. We thank the reviewer for encouraging these controls, which also motivated auxiliary guidance with no additional backbone training.
Why subtract the auxiliary displacement from the input. Let Fy=F(y) and c(0)=c(1)=0. Writing the auxiliary-path state as a translated CFM state gives
xt=zt+c(t)Fy,zt=xt−c(t)Fy.
The chain rule yields
x˙t=vCFM(xt−c(t)Fy,t,y)+c′(t)Fy.
Subtracting c(t)Fy therefore returns the input to the coordinates in which the frozen CFM was trained. Auxiliary CFG adjusts the explicit term:
\dot x_t=v_{\mathrm{CFM}}(x_t-c(t)F_y,t,y)+c'(t)F_w,$$ where $F_u$ is the null-condition auxiliary. The input translation uses $F_y$, so the guided dynamics in the original coordinates become $$\dot z_t=v_{\mathrm{CFM}}(z_t,t,y)+(w-1)c'(t)(F_y-F_u).$$ At $w=1$, the extra term vanishes. Since $c(0)=c(1)=0$, exact integration preserves the original CFM endpoint map. At $w=2$, the remaining term $c'(t)(F_y-F_u)$ changes the trajectory and can change the endpoint distribution without updating the backbone. A fixed empirical class mean is a valid deterministic auxiliary and avoids training an auxiliary network. Its FID of 16.8829 at scale 2 supports this simple choice for class-conditioned generation. Even when classes share a mean, the label-conditioned residual field can represent their different structures. Learned $F$ serves a broader conditioning interface: a shared map from text embeddings computes auxiliaries for new prompts on demand. This extends auxiliary design to text-to-image sampling, where storing an empirical mean for every possible description is impractical. **Planned revision.** Section 4.3 will explain how semantic path design supports backbone adaptation and controllable guidance. Section 5.4 will include these controls and distinguish training from guidance gains, with the coordinate derivation in Appendix B.