Preprint
Oct 2026
Blame Errant Words, Not the Canvas: Defect-Aware Spatial Credit Assignment for Visual Text Generation
Recent reinforcement learning approaches have improved visual text generation, yet generated images still suffer from incorrect wording and malformed glyphs. We identify two coupled limitations: recognition-based rewards often overlook visible glyph defects, while whole-image scalar feedback obscures the uneven quality...
Su-Jie Hu, Huai-Song Zhang, Pu-Jing Yang et al.
· 2 citations