Hugging Face Daily PapersHangyu Ran, Yuhao Zheng, Yingying Zhang1 min readpaperadvanced
RULER: Instance-aware Rubric Rewards for SVG Generation
Summary
RULER introduces an instance-aware rubric reward system for generating SVG code from natural language, addressing the lack of faithful evaluation signals. It uses a VLM to score rendered SVGs against a text-derived rubric, achieving significant performance improvements over existing methods without needing ground truth or human preference data.
- Scalar metrics like CLIP and Aesthetic scores are poor evaluation signals for stylized vector graphics and lead to reward hacking in RL.
- A multi-axis, instance-aware rubric, scored by a VLM, correlates much better with human judgment for SVG generation.
- RULER uses this VLM-scored rubric as a fine-grained reward signal for reinforcement learning, optimizing via Group Relative Policy Optimization.
- The method requires no paired SVG ground truth or human preference labels, as rubrics are generated solely from text instructions.
Engineers working on generative AI for design tools or vector graphics will find this valuable for improving model evaluation and training efficiency in open-ended generation tasks.
8/10