The paper introduces TextDART, a defect-aware reward model that evaluates individual text regions for semantic correctness and glyph quality, and SCANNER, a method that uses these regional judgments to provide spatially differentiated policy feedback. This approach addresses limitations of previous reinforcement learning methods that overlook glyph defects and obscure regional quality. Experiments on existing benchmarks and the new PolyText-Bench show state‑of‑the‑art performance in text accuracy and glyph fidelity.
arXiv:2608. 19637v1 Announce Type: new Abstract: Text editing in product posters entails inserting new text or replacing existing text while preserving product appearance, background content, and global composition.
Text editing in product posters entails inserting new text or replacing existing text while preserving product appearance, background content, and global composition. Despite recent progress in instruction-based image editing, general-purpose models remain unreliable in this setting: they often omit or incorrectly render the target text, place it over salient products or pre-existing content, and produce structurally distorted or visually inconsistent glyphs.
TextAlign is a post‑training preference‑alignment framework that improves text rendering in large text‑to‑image generative models without changing the generator architecture. It uses a hierarchical vision‑language model to reward global, word, and glyph‑level accuracy, converting binary defect judgments into a scalar preference signal that can be optimized with GRPO or DPO. Experiments on FLUX.1‑dev and Z‑Image‑Turbo demonstrate higher OCR‑based text accuracy while preserving overall generation quality, outperforming several foundation and text‑rendering baselines.
arXiv:2606. 17979v1 Announce Type: new Abstract: Existing RL post-training methods for text-to-image generation usually convert the final-image reward into a single scalar advantage and apply it with the same strength to the entire generative trajectory.
arXiv:2609.37569v1 Announce Type: new Abstract: Rendering accurate Chinese text remains challenging for text-to-image models. Existing OCR-based reinforcement-learning rewards compare decoded transcr...
arXiv:2609.36598v1 Announce Type: new Abstract: A video can exhibit convincing motion and photorealism yet fail immediately when visual text collapses. Unlike generic scene content, visual text is un...
arXiv:2603.07119v3 Announce Type: replace Abstract: Recent text-to-image models have improved global realism, but text rendering remains a persistent failure mode: images may look convincing overall,...
Rendering accurate Chinese text remains challenging for text-to-image models. Existing OCR-based reinforcement-learning rewards compare decoded transcripts with target strings. Such rewards overlook t...
arXiv:2601.03468v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a standard approach for post-training large language models and, more recently, for improving image generati...
The paper presents CycleGRPO, a reinforcement learning framework that unifies region understanding and localization for multimodal large language models (MLLMs). By treating the MLLM as both actor and critic, the method generates region captions and immediately grounds them back into spatial coordinates, using a token‑level cycle‑consistency reward that obviates the need for textual ground truths. Experiments on SAMTok demonstrate that CycleGRPO can bootstrap region captioning, VQA, grounded dialogue, and referring segmentation simultaneously, achieving consistent performance gains without task‑specific fine‑tuning.
TikZilla is a new approach to generating TikZ code from textual descriptions, built on a larger, higher‑quality dataset called DaTikZ‑V4 that includes LLM‑generated figure descriptions. The method uses a two‑stage pipeline: supervised fine‑tuning of small Qwen models (3B and 8B) followed by reinforcement learning with an image encoder that provides semantically faithful reward signals. Human evaluations show that TikZilla outperforms its base models by 1.5–2 points on a 5‑point scale, beats GPT‑4o by 0.5 points, and matches GPT‑5 in image‑based tests while remaining much smaller.
The paper presents a post‑training approach for text‑to‑image models that combines a preference reward, trained on large human preference data, with rubric‑based rewards that assess prompt faithfulness and other desirable traits. The authors show that a simple reward composition strategy outperforms a naive weighted average, leading to significant Elo gains on the Arena leaderboard for models like Flux2dev and Ideogram‑4. They also release Arena‑T2I‑Training, a 1K subset of data to aid reproducible research in post‑training.