- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper studies the temporal coordinate sampling strategy in MeanFlow training. MeanFlow models the average velocity over an interval to enable few-step generation. The authors view the temporal interval as collocation points on a triangular domain and decompose the sampling process into a boundary-condition target and a interior-interval target. Based on this idea, the paper proposes Temporal Supervision Allocation (TSA), which first uses diagonal supervision to stabilize the boundary and then progressively introduces interior samples. While introducing interior samples, it uses a left-anchored interval law to control interval length and gradually expands from short intervals to the full interval. The method only changes the temporal sampling strategy and does not alter the rest of MeanFlow's training or inference pipeline. Experiments show certain advantages for few-step generation on DiT-B/2 with ImageNet.
Critical strengths
The problem definition is clear. It separates the two constants in MeanFlow's temporal sampling into two independent schedules, i.e., diagonal allocation and interval geometry, yielding a concise and easy-to-understand perspective. The method only modifies the sampling strategy without changing other components, making the algorithm simple to implement with low additional cost.
Critical weaknesses
- TSA actually optimizes a different weighted objective. Compared with fixed sampling, its gains may come from effective data sampling or schedule tuning rather than purely from a "progressive curriculum". From Table 2, replacing the interval sampling law from Min-Max with Left-Anchored (c→e) yields a solid performance improvement, whereas introducing the quadratic horizon schedule (e→f) instead leads to a degradation in 1-NFE FID.
- The experiments are relatively thin, and there are many hyper-parameters requiring manual tuning. Baseline comparisons are insufficient, AlphaFlow uses a different and target annealing. The evaluation setting is limited, all experiments are run only on the medium-scale DiT-B/2 (131M parameters) for 400k steps without classifier-free guidance (CFG), resulting in relatively high overall FID (between 36 and 44), which leaves a substantial gap from practical generation quality.
Questions for authors
- To validate the FID improvements of EbbFlow, it is recommended to use 3–5 training seeds and report the mean results with standard deviation of EbbFlow and baselines.
- Regarding hyper-parameter robustness. How sensitive is performance to , , and ?