- Rating
- 2
- Confidence
- 2
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper propose a few-step generation method, called IBFlow. It improves few-step text-to-image distillation through adaptive teacher-supervision timesteps and SNR-based CFG scheduling. Motivated by the Information Bottleneck principle, it reports gains over existing two-step baselines across three model backbones.
Critical strengths
- the training objective is simple and easy to understand.
Critical weaknesses
- I have checked the offical metrics reported in TwinFlow and ArcFlow, and found that the data in Tab.1 are obviously lower than their offically reported data.
Questions for authors
- the authors characterize the current injection paradigm as “blind”. Could they clarify why selecting a specific teacher-supervision timestep should be preferable to sampling across multiple timesteps? Given the stochasticity of training, it is unclear why the proposed selection rule provides more reliable supervision than a sampling strategy that covers a broader range of timesteps.
- In the proof of lemma 1, the equality (19) cannot be obviously obtained. Can authors provide more details?
- the benefit of Dyn appears modest. Could the authors repeat this ablation with at least three random seeds and report the mean and standard deviation to assess whether the improvement is statistically significant?