- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes Time-Warping Guidance(TWIG) , an inference-time guidance method for flow matching models. TWIG augments classifier-free guidance(CFG) with a second contrast velocity term using a transformed latent and time. The transformation is based on cached noise estimate from previous steps and an empirically identified time schedule. The method introduces a calibration parameter, hypothesized to target an optimal time.
Experiments report improvements over CFG and competitive results against existing guidance methods, including favourable human preferences, on two image-generation backbones. However, this comes at the price of significantly higher NFE or latency-- which is a key overhead to pay.
Critical strengths
-
The paper presents a novel geometric view about time-shifted guidance in diffusion/flow models, offering a conceptually straightforward way to improve inference-time guidance. TWIG is simple to implement and requires no additional auxiliary model. Experiments have validated the intuition.
-
The paper evaluates multiple quality, diversity, and compositionality metrics, as well as human preferences, and reports consistent gains over CFG across two backbones.
Critical weaknesses
-
The novelty lies mainly in the jointly time-warped latent construction and its scheduling, however the advantages over existing approaches needs to be better demonstrated and explained more clearly. Please address the questions in the "Questions for Authors" section.
-
TWIG's improvement on performance against baselines is modest, while requires significantly higher NFE. The main evaluation Table 1 only provides equal-NFE baseline on CFG, and most two-pass baselines use 100 NFE. In the meantime, TWIG uses 150 NFE. As a result, TWIG's advantage under equal NFE setting remains unclear.
Questions for authors
-
please explain the insight behind Lemma 2 on TWIG's performance? This lemma itself bounds the reconstructed latent - which is the network's input, on noise estimate . Two follow-ups questions on this lemma are: (1) How can we obtain the error bound on noise estimate? (2) How does the error bound on network input propagates to network output, i.e., the velocity prediction?
-
Since the method relies on Tweedie's formula for noise estimation, which works best for multi-step sampling scenario, how well does TWIG perform under few-step sampling regime?
-
Could the authors provide (at least some) results for equal NFE evaluation on two-pass baselines?
-
Per Eq.10, should approach as . But Figure 2 and Figure 4 show on the contrary. Please explain this.
-
Given TWIG requires one more forward run in each step compared to the vanilla CFG, please explain what role the second contrast term in TWIG provides.