- Rating
- 1
- Confidence
- 3
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper leverages the noise schedule as a control interface for image editing models. It introduces three contributions: ATS trains a lightweight policy that predicts a two-parameter schedule for each data pair; GeoTS performs best-of-N selection over geometry-normalized perturbations of a reference schedule; EditCal combines existing evaluators into a calibrated editing reward.
Critical strengths
- The statistics of experimental results is careful with paired bootstrap CIs.
- EditCal's calibrated, per-criterion failure probabilities are an interpretable alternative to scalar editing rewards.
Critical weaknesses
- ATS is neither new nor clearly effective. Its schedule family is simply FLUX's built-in time-shift function, and a single input-independent schedule recovers most of the gain. The remaining improvement is tiny and often not significant on Kontext.
- The other contributions do not hold up. GeoTS and EditCal offer little methodological novelty. GeoTS is worse than simple noise resampling on Kontext at equal cost (Table 12 in the appendix). EditCal is a calibrated ensemble of its strongest baselines, with small and untested gains.
Questions for authors
- Can you report the end-to-end inference time and compute cost? This should include the policy forward pass for ATS and the B full edits and reward evaluations for GeoTS?
- Is the improvement perceptible in a human user study?