- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
ProOPD introduces process-guided on-policy distillation for iterative text-to-image generation in a unified BAGEL model. Frozen stage-specific teachers supervise the student’s own trajectories through textual distribution matching and visual velocity matching, combined with image-reward GRPO. Experiments on four benchmarks compare the method with joint SFT, reward-only training, and distillation-only training.
Critical strengths
-
ProOPD provides teacher supervision for both text and image generation on the student's own rollouts, while retaining a single model at inference.
-
The comparisons in Table 3 use the same initialization and rollout procedure. Adding process supervision to GRPO improves LongText by 3.66 points and WISE by 4.00 points. Table 6 also controls for differences in the initial images and plans when comparing refinement.
Critical weaknesses
-
I cannot tell whether the model has learned to diagnose errors and write better edit instructions, or mainly become a better image editor. Table 6 fixes the initial images and plans, but critique, replanning, and refinement still change together. This comparison evaluates the later stages as a whole, without separating gains from better reflection and edit instructions from gains in image editing.
-
The gains from adding GRPO to Pure OPD are uneven across benchmarks. In Table 3, ProOPD gains 1.95 points on OneIG text rendering and 1.70 on WISE, but only 0.31 on LongText, while scoring 0.36 points lower on GenEval++. These results are reported at a single 160-update checkpoint. It is unclear whether the relative performance remains similar over training or reflects different convergence rates.
Questions for authors
-
How much of the refinement gain comes from better reflection and edit instructions, and how much from improved image editing? A comparison that combines the SFT and ProOPD textual outputs with each model’s image editor, using the same initial images, would help separate these contributions.
-
How was the 160-update checkpoint in Table 3 selected, and how does the relative performance of ProOPD, Pure OPD, and GRPO change over training? Please also compare their training costs.
-
Which models or data sources produced the reference images and stage-specific textual supervision used for SFT? Please summarize the retained example counts for each specialist teacher and the generation/editing mixture for the refinement teacher. Beyond the reported image-quality and prompt-satisfaction filtering, how was the consistency of initial plans with reference images and edit instructions with accepted refined images validated?
-
Which models and criteria were used to construct the semantic and quality checks for GRPO rewards, and how were verifier responses and OCR outputs converted into reward scores?
For future work, I would like to see performance over several refinement rounds and a comparison with an external VLM guiding the image generator at a comparable inference budget.
Additional comment on related work:
I also suggest discussing related work on learning and evaluating reflection-guided image refinement. R³-Bench [1] separately evaluates visual error diagnosis and the effectiveness of corrective instructions. RL-RIG [2] uses Reflection-GRPO to train an editing-instruction actor and an image editor in separate stages. Reflect-DiT [3] learns to refine generations using previous images and feedback from an external VLM. These works provide useful context for positioning ProOPD’s stage-specific distillation and for distinguishing improvements in reflection from improvements in image editing.
References:
[1] Junjie Wang et al. Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation. ICML, 2026.
[2] Tianyu Wang et al. RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection. arXiv:2602.19974, 2026.
[3] Shufan Li et al. Reflect-DiT: Inference-Time Scaling for Text-to-Image Diffusion Transformers via In-Context Reflection. ICCV, 2025.
7 comments
Thank you very much for following up, and for the time and care you have put into reviewing our work. All additional evaluations are now complete, and we will post a full response to all of your questions as soon as possible.
Response to Reviewer bcU2 (1/4)
We sincerely thank the reviewer for the detailed review and constructive feedback. We address each point below.
W1/Q1. Contributions of textual instruction and image editing
We conducted a 2×2 crossover, combining SFT and ProOPD textual instruction (critique and edit instructions) with each model’s image editor. All four conditions use identical SFT initial plans and images. Each set of critiques and edit instructions is reused unchanged across both editors, with paired editing noise. Stopped samples retain their initial images.
| Textual instruction | Image editor | WISE | LongText | OneIG Align | OneIG Text | Reasoning | Style | Diversity |
|---|---|---|---|---|---|---|---|---|
| SFT | SFT | 69.40 | 58.33 | 83.87 | 73.49 | 32.48 | 44.49 | 21.15 |
| SFT | ProOPD | 70.20 | 65.12 | 85.07 | 77.78 | 32.49 | 44.43 | 19.36 |
| ProOPD | SFT | 66.10 | 59.46 | 83.31 | 75.93 | 32.75 | 44.42 | 21.80 |
| ProOPD | ProOPD | 71.20 | 66.72 | 85.24 | 79.35 | 32.67 | 44.49 | 19.64 |
With textual instruction fixed, replacing the SFT editor with the ProOPD editor improves LongText by 6.79–7.26 points, OneIG Text by 3.42–4.29 points, and WISE by 0.80–5.10 points. With the editor fixed, replacing SFT textual instruction with ProOPD textual instruction improves LongText by 1.13–1.60 points and OneIG Text by 1.57–2.44 points. Its WISE effect depends on the editor: −3.30 points with the SFT editor and +1.00 point with the ProOPD editor.
These results show that improved image editing (refinement) provides the larger text-rendering gains, while learned textual instruction (critique and replaning/editing) contributes additional gains and interacts with the editor. Other OneIG dimensions show mixed changes. This control measures the downstream effectiveness of textual instruction, including stopping decisions.
Could you please respond to the remaining questions before the discussion closes? If the additional evaluations are still in progress, a brief update would also be helpful. Thank you.