TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards 事件

TextAlign: Preference Alignment for Text Rendering with Hierarchical Rewards arXiv:2605.19320v2 Announce Type: replace Abstract: Faithful text rendering remains a persistent weakness of large text-to-image generative models, as it requires both semantic instruction following and fine-grained glyph-level structure. Prior methods often improve this ability through architecture-specific modules or encoder modifications, which complicate deployment across foundation models. We study text rendering