SOURCE-LINKED INTELLIGENCE

GDB-Reward: From Evaluation Metrics to Training Rewards for Graphic Design

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Text-to-image models excel at natural image synthesis but struggle with graphic design, where success depends on satisfying precise constraints on typography, layout, color, and visual communication. While prompt optimization offers an attractive alternative to expensive diffusion model fine-tuning, learning prompts for frozen image generators requires informative reward functions despite the entirely non-differentiable generation process. Reinforcement learning does not require differentiable objectives; it requires only scalar rewards capable of ranking candidate outputs. This raises a simpl

Read original source ↗ Open in workspace

recordType

paper

region

Global