English
Related papers

Related papers: OVERT: A Benchmark for Over-Refusal Evaluation on …

200 papers

Recent advances in diffusion models have significantly enhanced the quality of image synthesis, yet they have also introduced serious safety concerns, particularly the generation of Not Safe for Work (NSFW) content. Previous research has…

Computer Vision and Pattern Recognition · Computer Science 2025-09-15 Yaopei Zeng , Yuanpu Cao , Bochuan Cao , Yurui Chang , Jinghui Chen , Lu Lin

Text-to-Image (T2I) generative models have revolutionized content creation but remain highly sensitive to prompt phrasing, often requiring users to repeatedly refine prompts multiple times without clear feedback. While techniques such as…

Computer Vision and Pattern Recognition · Computer Science 2025-07-30 Chieh-Yun Chen , Min Shi , Gong Zhang , Humphrey Shi

Large language models exhibit safety degradation in non-English languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds several safety-driving factors into one, obscuring the specific cause(s) of safety…

Computation and Language · Computer Science 2026-05-19 Max Zhang , Ameen Patel , Sang T. Truong , Sanmi Koyejo

Text-to-image (T2I) models have achieved remarkable progress, yet they continue to struggle with complex prompts that require simultaneously handling multiple objects, relations, and attributes. Existing inference-time strategies, such as…

Computer Vision and Pattern Recognition · Computer Science 2026-01-22 Shantanu Jaiswal , Mihir Prabhudesai , Nikash Bhardwaj , Zheyang Qin , Amir Zadeh , Chuan Li , Katerina Fragkiadaki , Deepak Pathak

Text-to-image (T2I) models are increasingly used for synthetic dataset generation, but generating effective synthetic training data for classification remains challenging. Fine-tuning a T2I model with a few real examples can help improve…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 William Yang , Xindi Wu , Zhiwei Deng , Esin Tureci , Olga Russakovsky

We propose T2I-ReasonBench, a benchmark evaluating reasoning capabilities of text-to-image (T2I) models. It consists of four dimensions: Idiom Interpretation, Textual Image Design, Entity-Reasoning and Scientific-Reasoning. We propose a…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Kaiyue Sun , Rongyao Fang , Chengqi Duan , Xian Liu , Xihui Liu

Despite the integration of safety alignment and external filters, text-to-image (T2I) generative systems are still susceptible to producing harmful content, such as sexual or violent imagery. This raises serious concerns about unintended…

Cryptography and Security · Computer Science 2025-12-09 Boheng Li , Junjie Wang , Yiming Li , Zhiyang Hu , Leyi Qi , Jianshuo Dong , Run Wang , Han Qiu , Zhan Qin , Tianwei Zhang

Despite recent advances in text-to-image generation, models still struggle to accurately render prompt-specified text with correct spatial layout -- especially in multi-span, structured settings. This challenge is driven not only by the…

Computer Vision and Pattern Recognition · Computer Science 2026-04-28 Dongxing Mao , Yilin Wang , Linjie Li , Zhengyuan Yang , Alex Jinpeng Wang

Recently, Text-to-Image (T2I) generation models have achieved significant advancements. Correspondingly, many automated metrics have emerged to evaluate the image-text alignment capabilities of generative models. However, the performance…

Computer Vision and Pattern Recognition · Computer Science 2024-12-30 Shuhao Han , Haotian Fan , Jiachen Fu , Liang Li , Tao Li , Junhui Cui , Yunqiu Wang , Yang Tai , Jingwei Sun , Chunle Guo , Chongyi Li

Recent text-to-image (T2I) generation models have advanced significantly, enabling the creation of high-fidelity images from textual prompts. However, existing evaluation benchmarks primarily focus on the explicit alignment between…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Wenchao Zhang , Jiahe Tian , Runze He , Jizhong Han , Jiao Dai , Miaomiao Feng , Wei Mi , Xiaodan Zhang

Despite the impressive synthesis quality of text-to-image (T2I) diffusion models, their black-box deployment poses significant regulatory challenges: Malicious actors can fine-tune these models to generate illegal content, circumventing…

Computer Vision and Pattern Recognition · Computer Science 2025-03-31 Zhuomeng Zhang , Fangqi Li , Chong Di , Hongyu Zhu , Hanyi Wang , Shilin Wang

Rapid advances in text-to-image (T2I) generation have raised higher requirements for evaluation methodologies. Existing benchmarks center on objective capabilities and dimensions, but lack an application-scenario perspective, limiting…

Artificial Intelligence · Computer Science 2025-09-23 Xiaojing Dong , Weilin Huang , Liang Li , Yiying Li , Shu Liu , Tongtong Ou , Shuang Ouyang , Yu Tian , Fengxuan Zhao

Text-to-image (T2I) synthesis has recently achieved significant advancements. However, challenges remain in the model's compositionality, which is the ability to create new combinations from known components. We introduce Winoground-T2I, a…

Computer Vision and Pattern Recognition · Computer Science 2023-12-12 Xiangru Zhu , Penglei Sun , Chengyu Wang , Jingping Liu , Zhixu Li , Yanghua Xiao , Jun Huang

Text-to-image (TTI) models are increasingly used in professional, educational, and creative contexts, yet their outputs often embed and amplify social biases. This paper investigates gender representation in six state-of-the-art open-weight…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Franck Vandewiele , Remi Synave , Samuel Delepoulle , Remi Cozot

Text-to-image (T2I) models excel on single-entity prompts but struggle with multi-entity scenes, often exhibiting attribute leakage, identity entanglement, and subject omissions. We present a principled theoretical framework that steers…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Eric Tillmann Bill , Enis Simsar , Thomas Hofmann

User prompts for generative AI models are often underspecified, leading to a misalignment between the user intent and models' understanding. As a result, users commonly have to painstakingly refine their prompts. We study this alignment…

Artificial Intelligence · Computer Science 2025-10-27 Meera Hahn , Wenjun Zeng , Nithish Kannen , Rich Galt , Kartikeya Badola , Been Kim , Zi Wang

Safety alignment approaches in large language models (LLMs) often lead to the over-refusal of benign queries, significantly diminishing their utility in sensitive scenarios. To address this challenge, we introduce FalseReject, a…

Computation and Language · Computer Science 2025-07-16 Zhehao Zhang , Weijie Xu , Fanyou Wu , Chandan K. Reddy

TIPO (Text-to-Image Prompt Optimization) introduces an efficient approach for automatic prompt refinement in text-to-image (T2I) generation. Starting from simple user prompts, TIPO leverages a lightweight pre-trained model to expand these…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Shih-Ying Yeh , Yi Li , Sang-Hyun Park , Giyeong Oh , Xuehai Wang , Min Song , Youngjae Yu , Shang-Hong Lai

Despite rapid advancements in text-to-image (T2I) models, their safety mechanisms are vulnerable to adversarial prompts, which maliciously generate unsafe images. Current red-teaming methods for proactively assessing such vulnerabilities…

Computer Vision and Pattern Recognition · Computer Science 2025-10-29 Yufan Liu , Wanqian Zhang , Huashan Chen , Lin Wang , Xiaojun Jia , Zheng Lin , Weiping Wang

Large-scale pre-trained generative models are taking the world by storm, due to their abilities in generating creative content. Meanwhile, safeguards for these generative models are developed, to protect users' rights and safety, most of…

Cryptography and Security · Computer Science 2024-10-14 Guanlin Li , Kangjie Chen , Shudong Zhang , Jie Zhang , Tianwei Zhang