- Rating
- 2(+1)
- Confidence
- 4
- Informativeness
- 1
- Presentation
- 2
- Soundness
- 1
Read review
Paper summary
This paper proposes VA-SVG, a post-training framework that introduces generative visual alignment into autoregressive SVG code generation. Starting from a pretrained SVG generator, the method trains a diffusion branch conditioned on the MLLM’s continuous code representations to reconstruct corresponding raster images. It then freezes the diffusion branch and conditioning projector, and updates the MLLM through token-level cross-entropy and alignment between projected intermediate DiT features and DINO features of the model’s rendered SVG predictions. The auxiliary visual branch is used only during training, preserving standard autoregressive inference. Experiments on the Icon and Illustration subsets of MMSVG-Bench evaluate Text-to-SVG and Image-to-SVG generation, with improvements over CE-only post-training demonstrated on the Icon subset, particularly in reconstruction quality.
Critical strengths
-
The proposed framework brings differentiable visual supervision into SVG code generation in the SFT stage. Because the auxiliary diffusion branch is used only during training, the model keeps standard autoregressive inference. This makes the approach practically appealing, as it improves visual fidelity without adding an inference-time feedback loop.
-
Table 2 provides encouraging evidence that visual alignment improves over CE-only post-training. On MMSVG-Bench Icon, LPIPS drops from 0.205 to 0.101, and SSIM rises from 0.902 to 0.925. Notably, these gains appear on metrics other than DINO, which is used as the supervision signal.
Critical weaknesses
-
Section 3.2 argues that diffusion provides a stronger visual prior, yet visual alignment training uses the MLLM’s own rendered predictions as alignment targets. It is unclear why the projected DiT features are not additionally aligned with features of the ground-truth images, which could provide direct corrective supervision to the MLLM. The paper lacks justification for this target choice and a comparison with ground-truth alignment, leaving the role of the claimed stronger visual prior insufficiently established.
-
Evaluation is limited to MMSVG-Bench, leaving generalization to other benchmarks insufficiently established. Additional evaluation on SArena, UniSVG, or the SVG-Stack test set would strengthen the evidence. Moreover, the RL baseline’s training configuration and reward formulation are not specified, making the comparison in Table 2 difficult to assess or reproduce.
-
Reinforcement learning methods can use reward signals beyond visual quality, such as image–text alignment and code efficiency. They can also use SVG validity checks to substantially reduce degenerate repetition in generated code, where SVG-specific models keep emitting the same digit or character. This makes RL-based approaches strong baselines for this task. Table 1 reports SVGen's performance on MMSVG-Bench, but this comparison is not entirely fair because SVGen was not trained on the same data. To show that VA-SVG is effective, the authors should retrain SVGen on the MMSVG dataset and compare the two methods under the same training data. The authors should also compare VA-SVG with CTRL-S on SArena, so the evaluation covers more than one benchmark.
Questions for authors
-
Could the authors explain why only the MLLM's rendered predictions are used as alignment targets, rather than ground-truth images? Could the authors also report how performance changes when the projected DiT features are additionally aligned with ground-truth image features?
-
Could the authors describe the algorithm, reward formulation, and training configuration of the RL baseline in Table 2? Could the authors also clarify whether its initialization, training data, and computational budget are comparable to those of VA-SVG?
-
Could the authors clarify the size of the code-generation pretraining dataset? Section 4.1 reports approximately 1.3M training examples, whereas Appendix A and Table 3 report 1.67M samples. It would be helpful to know which number is correct, or whether the two numbers refer to different subsets.
-
Could the authors report results on additional benchmarks, such as SArena, UniSVG, or the SVG-Stack test set, to assess generalization beyond MMSVG-Bench?
-
Could the authors clarify whether the SVGen results in Table 1 were obtained from an existing checkpoint or from a retrained model? To better assess VA-SVG's advantages over RL-based methods, it would be helpful to retrain SVGen on the same training data as VA-SVG and compare the two methods under this setting. Alternatively, a comparison with CTRL-S on SArena under a consistent evaluation protocol would also be very helpful.