- Rating
- 1
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 1
- Soundness
- 2
Read review
Paper summary
This paper studies how attribute binding evolves across model depth and denoising time in mmdits. Under a controlled two-object color-binding experiment, the author shows that in some cases the binding is initially correct before shifting to competing assignment. They further propose a training-free approach to penalize deviations from the initial correct bindings during the denoising process.
Critical strengths
- The finding that some binding failures are initially generated correctly but became inverted during the generation process is interesting. This also offers insights for other subfields, for example, a new explanation for why t2i models can improve binding capabilities through rl on GenEval.
- The observed geometry also supports a targeted intervention, and the intervention works well on sd3.5
Critical weaknesses
- Limited cross-model effectiveness. Gains are substantial on sd3.5 but relatively marginal on flux.1 ( −0.2 on t2i-compbench++) color (Appendix C.3). Evaluation on newer mmdits such as z-image or flux.2 klein would strengthen the generalization evidence.
- The analysis evaluated only on color binding with two-object prompts, which is too narrow. It remains unclear whether these findings generalize to other attributes (like texture/shape/size), or multi-object cases.
- FID against imagenet is difficult to interpret for this narrow set of compositional prompts. A human-preference reward like hpsv3 is better for evaluating image quality.
- Presentation issues. Some figures (e.g. Fig. 5), are blurry and difficult to inspect. Table captions (e.g., Tab.1 ) appear below the tables, which is against to the iclr requirements
Questions for authors
- How can you explain the substantially weaker gains on flux.1?
- What is the inference-time overhead of scout-and-replay steering relative to the baseline?
Dear Reviewers,
We appreciate your considerable effort in evaluating our work. We have taken your concerns seriously and are working on extensive additional experiments regarding benchmark extensions to other attribute types, comparison to baseline intervention methods, and image quality metrics. Unfortunately, this has not worked out in time for the rebuttal, but thanks to your input will make for a much stronger submission at a future venue.
Thank you for your constructive and helpful feedback!
Sincerely, The Authors