- Rating
- 3
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
This paper proposes S2AR, a training-free method for continuous attribute control in visual autoregressive models. Experimental results show effectiveness in content preservation and monotonic attribute control.
Critical strengths
-
This paper addresses continuous attribute control in visual autoregressive models. The research problem is clear.
-
This method adjusts the editing regions and generation scales according to different attributes.
Critical weaknesses
-
The results of the Ours differ between Table 1 and Table 2.
-
The scale routing weights are obtained from the reconstruction error of spatial response maps. They do not directly measure how much each generation scale affects the target attribute.
Questions for authors
-
Please explain why the full-method results differ between Table 1 and Table 2.
-
Please provide sensitivity analysis of scale. It would be helpful to compare the proposed scale weights with fixed-scale intervention and simpler scale weighting methods.
2 comments
(Part 2/2)
Q2. Sensitivity Analysis of Scale
To validate the effectiveness of our adaptive scale weighting strategy, we conducted two additional sets of comparative experiments: (1) Fixed-scale Intervention, where editing interventions are applied to different fixed scale ranges; and (2) Scale Weighting, including uniform weights and linearly increasing weights. We evaluate these settings on three editing tasks using ΔCLIP, DINO, and LPIPS as evaluation metrics.
First, regarding fixed-scale interventions, as the intervention shifts from lower-indexed to higher-indexed scales, ΔCLIP generally decreases across all three tasks, while DINO consistently increases and LPIPS decreases. This suggests that higher-indexed scales tend to preserve the original image content more effectively but struggle to achieve sufficient semantic editing. The optimal fixed scale range varies across tasks, indicating that the effectiveness of fixed-scale interventions is task-dependent. In contrast, our method achieves the highest ΔCLIP across all three tasks, demonstrating that adaptive scale allocation enables more effective semantic editing without requiring manual selection of task-specific scale ranges.
Table 2: Sensitivity analysis of fixed-step interventions across three tasks.
| Setting | Expr. ΔCLIP ↑ | Expr. DINO ↑ | Expr. LPIPS ↓ | Objects ΔCLIP ↑ | Objects DINO ↑ | Objects LPIPS ↓ | Scenes ΔCLIP ↑ | Scenes DINO ↑ | Scenes LPIPS ↓ |
|---|---|---|---|---|---|---|---|---|---|
| Ours | 0.048 | 0.941 | 0.238 | 0.037 | 0.824 | 0.218 | 0.068 | 0.765 | 0.286 |
| Steps 2–4 | 0.001 | 0.958 | 0.262 | 0.018 | 0.835 | 0.356 | 0.040 | 0.767 | 0.435 |
| Steps 5–7 | 0.018 | 0.974 | 0.088 | 0.002 | 0.958 | 0.103 | 0.006 | 0.921 | 0.152 |
| Steps 8–10 | 0.007 | 0.996 | 0.020 | 0.001 | 0.991 | 0.031 | 0.001 | 0.975 | 0.055 |
| Steps 11–13 | 0.001 | 0.999 | 0.004 | 0.001 | 0.998 | 0.008 | 0.000 | 0.993 | 0.016 |
Second, regarding scale weighting strategies, our adaptive weighting strategy achieves better content preservation while improving semantic editing performance. Although linearly increasing weights perform better on certain content preservation metrics, their semantic editing capability is notably limited. These results indicate that simple predefined weighting schemes cannot adequately accommodate the editing requirements of different inputs.
Table 3: Comparison of different scale weighting strategies across three tasks.
| Setting | Exp. ΔCLIP ↑ | Exp. DINO ↑ | Exp. LPIPS ↓ | Obj ΔCLIP ↑ | Obj DINO ↑ | Obj LPIPS ↓ | Scn ΔCLIP ↑ | Scn DINO ↑ | Scn LPIPS ↓ |
|---|---|---|---|---|---|---|---|---|---|
| Ours | 0.048 | 0.941 | 0.238 | 0.037 | 0.824 | 0.218 | 0.068 | 0.765 | 0.286 |
| Uniform weights | 0.034 | 0.920 | 0.269 | 0.017 | 0.809 | 0.360 | 0.048 | 0.750 | 0.440 |
| Linear weights | 0.016 | 0.972 | 0.190 | 0.003 | 0.907 | 0.225 | 0.006 | 0.881 | 0.254 |
We have added these comparative experiments and the corresponding sensitivity analysis results to the appendix. In addition, we have included a scale sensitivity analysis for the localization stage to further evaluate the impact of different scale selections on localization performance.
(Part 1/2)
We sincerely appreciate your recognition of our work and your constructive suggestions. We have carefully considered your feedback and address each of your comments below.
Q1. Discrepancy Between Table 1 and Table 2
We thank the reviewer for identifying this inconsistency and acknowledge that the original manuscript did not clearly specify the differing evaluation settings. Table 1 used all 168 CACBench prompts (8 per attribute), whereas Table 2 used 42 randomly sampled prompts (2 per attribute) to reduce the computational cost of extensive analysis experiments. Thus, the results were not directly comparable. To resolve this, we reran the ablations on all 168 prompts, updated Table 2 with task-specific results, and revised the corresponding analysis. The updated ablations show that removing spatial routing reduces controllability and structural preservation, as editing signals are no longer confined to attribute-relevant regions. Removing adaptive scale routing substantially weakens controllability, as a fixed injection schedule cannot accommodate attribute-specific scale requirements. For ease of reference, we provide the revised Table below (refer to Table 2 in the manuscript):
Table 1: Ablation study on all CACBench prompts across three tasks. (Best in bold, second best underlined.)