The paper investigates how rendered text in image generation models can leak semantic information, acting as an unintended control channel. By separating the visual prompt from the text, the authors measure how text semantics influence generated images and show that harmful meanings can persist even when the main prompt is benign. They also propose a mitigation strategy that limits unsafe semantic transfer while maintaining correct text rendering.
By Feifei Li, Runjie Wang, Xiaohan Zhang, Zhenxing Qian, Mi Wen, Mi Zhang
The paper introduces Orthogonal Drift Correction (ODC), an inference-time guidance method that mitigates semantic drift in text-to-image generation without retraining or extra user input. ODC operates in two stages: first it detects drift by comparing the generated image to the prompt in a shared vision-language embedding space, isolates the orthogonal component of the drift, and converts it back into text; second it refines the text conditioning for a second generation pass using an adaptive rank-reduced concept removal module. Experiments show ODC improves prompt-image alignment, raising CLIP scores by up to 5.4% on COALBench-300 and PartiPrompts, and boosting the 3-in-1 score by 4.5% on T2I-CompBench’s complex subset.
By Kasra Kamali, Basim Azam, Tuan Duong Trinh, Jean Honorio, Naveed Akhtar
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...
By Ziying Zhang, Litao Li, Junchao Liao, Tianyi Zeng, Siyu Zhu, Long Qin, Zhenghao Zhang
VTR-Bench is a new benchmark designed to evaluate how well video generation models render text within scenes. It includes 300 prompts across five real-world scenarios such as advertisements and scientific videos, and uses an automated pipeline with human alignment to assess text fidelity and scene/motion requirements. Experiments on 11 state‑of‑the‑art models show that even the best performer has a word error rate of 0.250, underscoring widespread challenges in visual text rendering.
By Yu Huang, Jungang Li, Zhiyuan Wang, Yonghua Hei, Song Dai, Jiayu Yang, Deyuan Liu, Xiang Zheng, Xiaoshuang Shi, Hao Cheng, Kaidi Xu
TextVBench is a new benchmark and evaluation framework for assessing how well video generation models render and preserve text. It introduces two tracks—TextVBench‑T2V for prompt‑specified text creation and maintenance, and TextVBench‑Ref2V for preserving text from reference images—using a multi‑target, multi‑instance spatiotemporal correspondence approach. The framework employs target‑conditioned candidate selection, supports multiple OCR regions per target, and separates spatial and temporal fidelity, summarizing results with a length‑weighted harmonic score and detailed diagnostics.
By Ruiqiang Zhang, Hengyi Wang, Chang Liu, Guanjie Wang, Zehua Ma, Weiming Zhang
arXiv:2505. 16915v3 Announce Type: replace-cross Abstract: While recent Text-to-Image (T2I) models show impressive capabilities in synthesizing images from brief descriptions, they struggle with the long, detailed prompts required for professional applications.
By Qirui Jiao, Daoyuan Chen, Yilun Huang, Xika Lin, Ying Shen, Yaliang Li
arXiv:2608. 07435v1 Announce Type: cross Abstract: Vision-language models (VLMs) are improving rapidly, but benchmark development lags behind, making weaknesses hard to identify.
By Zixuan Lan, Luzhe Sun, Matthew R. Walter, Jiawei Zhou
arXiv:2610.09823v1 Announce Type: new
Abstract: Dense visual text requires image generators to reproduce long strings across multiple regions with correct placement and legibility. As short-string re...
By Deyuan Liu, Yihao Hu, Jingxuan Zhang, Xingying Li, Jun Xie, Jiacheng Liu, Jungang Li, Yu Huang, Xuanyi Liu, Yue Ding, Zecheng Wang, Lei Zhao, Mingda Wang, Zhenglin Cheng, Peng Sun, Tao Lin
Spatial instruction following has become a crucial requirement for text-to-image (T2I) generation. A common challenge arises when directional expressions are interpreted under different frames of reference.
arXiv:2610.19551v1 Announce Type: new
Abstract: Text-to-image models increasingly generate readable Chinese text that still contains local rendering defects, such as a character with an extra or miss...
By Yiyang Chen, Guo-Hua Wang, Yaoli Liu, Qing-Guo Chen, Zhao Xu, Weihua Luo, Xiujun Ma
arXiv:2607. 28967v1 Announce Type: cross Abstract: Prompt tuning adapts vision--language models with few trainable parameters, but existing approaches trade off efficiency and adaptation: static textual prompts can overfit source classes, image-conditioned prompts add per-instance computation, and multimodal tuning modifies the visual branch.
By Pouya Parsa, Raoof Zare Moayedi, Seongjin Choi
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,...
By Kirill Koltsov, Aleksandr Gushchin, Anastasia Antsiferova, Dmitriy Vatolin