AIBullisharXiv – CS AI · Mar 166/10
🧠
Visual-ERM: Reward Modeling for Visual Equivalence
Researchers introduce Visual-ERM, a multimodal reward model that improves vision-to-code tasks by evaluating visual equivalence in rendered outputs rather than relying on text-based rules. The system achieves significant performance gains on chart-to-code tasks (+8.4) and shows consistent improvements across table and SVG parsing applications.