The paper investigates how long, richly detailed prompts cause modern text-to-image models to lose diversity, even when many visual aspects are unspecified. It introduces PromptMoG, a training‑free method that samples prompt embeddings from a Mixture‑of‑Gaussians distribution to restore diversity while preserving semantic fidelity. The authors also present LPD‑Bench, a benchmark for evaluating fidelity and diversity under long, semantically dense prompts, and demonstrate PromptMoG’s effectiveness on four large diffusion models.
By Bo-Kai Ruan, Teng-Fang Hsiao, Ling Lo, Yi-Lun Wu, Hong-Han Shuai
RAP (Reconstruct A Poster) is a new dataset and benchmark for generating conference posters from research papers, comprising over 25,000 verified paper‑poster pairs from 2022‑2026. Each pair is annotated with a three‑level content taxonomy and converted into styled HTML/CSS markup through an automated derendering pipeline, enabling objective render‑and‑compare evaluation. The corpus supports both inference and training, with a retrieval‑based PosterRAG pipeline and a supervised‑fine‑tuned model, and is publicly available via an online demo.
By Haonan Han, Yukang Lin, Minliang Lin, Haoxian Tan, Jun-Yan He, Rui Yang, Zhi-Qi Cheng, Jie Hu, Guanglu Wan, Xiu Li
UReason is a benchmark that evaluates how well unified multimodal models (UMMs) align textual reasoning with image generation. It contains 2,000 human‑curated instances across five reasoning‑intensive tasks—Code, Arithmetic, Spatial, Attribute, and Text—and compares direct generation, reasoning‑guided generation, and decontextualized generation. The study finds that while reasoning‑guided generation improves over direct generation, decontextualized generation consistently outperforms it, indicating that the visual semantics in textual reasoning are not reliably reflected in the generated images.
By Cheng Yang, Chufan Shi, Bo Shui, Yaokang Wu, Muzi Tao, Huijuan Wang, Ivan Yee Lee, Yong Liu, Xuezhe Ma, Taylor Berg-Kirkpatrick
T-DIG is a text-conditioned diversity framework that enables users to generate multiple images from a single prompt and then request variations along specific axes—such as background, style, or clothing—using natural language. The system employs an LLM policy to produce K axis-conditioned prompts or edit instructions for a frozen image generator or editor, trained with GRPO and a diversity reward. T‑DIG works with open‑weight, distilled, and proprietary models, and the authors release a new dataset of human‑written axes and real user interactions to benchmark text‑conditioned diversity.
By Simran Khanuja, Rohit Gandikota, Gaurav Parmar, Graham Neubig
The paper introduces T23D-CompBench, a new benchmark for fine‑grained text‑to‑3D quality assessment that includes 3,600 textured meshes generated from ten state‑of‑the‑art models and 129,600 human ratings. It also proposes Rank2Score, a two‑stage rank‑learning metric that first trains with supervised contrastive regression and curriculum learning, then refines predictions using mean opinion scores to better align with human judgments. Experiments show Rank2Score outperforms existing metrics and can be used as a reward function for generative model optimization.
By Bingyang Cui, Yujie Zhang, Qi Yang, Zhu Li, Yiling Xu
arXiv:2307.00852v3 Announce Type: replace
Abstract: The natural language generation domain has witnessed great success thanks to Transformer models. Although they have achieved state-of-the-art gener...
By Yueen Ma, Dafeng Chi, Jingjing Li, Kai Song, Yuzheng Zhuang, Irwin King