图像生成

Real-Time Cooked Food Image Synthesis and Visual Cooking Progress Monitoring on Edge Devices

边缘设备上的实时烹饪食品图像合成与视觉烹饪进程监控

Jigyasa Gupta, Soumya Goyal, Anil Kumar, Ishan Jindal

机构 * Samsung R&D Institute India（三星印度研发院） 纠错

专题命中 文生图 ：image synthesis(title)；image generation(abstract)；分类 cs.CV

AI总结 本文提出了一种边缘高效的生成模型，通过引入基于烤箱的烹饪进程数据集和领域特定的CIS度量标准，实现了在边缘设备上实时合成逼真烹饪食品图像并监控烹饪进程。

Comments 13 pages, 11 figures

T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model

T2I-RiskyPrompt：用于评估、攻击和防御文本到图像模型安全性的基准

Chenyu Zhang, Tairen Zhang, Lanjun Wang, Ruidong Chen, Wenhui Li, Anan Liu

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

AI总结 T2I-RiskyPrompt提出了一种用于评估文本到图像模型安全性的综合基准，通过层次化风险分类和原因驱动的检测方法，全面评估了多种模型和防御策略的安全性能。

Comments AAAI 2026

Reason2Attack: Jailbreaking Text-to-Image Models via LLM Reasoning

通过LLM推理进行文本到图像模型的劫持：Reason2Attack

Chenyu Zhang, Lanjun Wang, Yiwen Ma, Wenhui Li, An-An Liu

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

AI总结 Reason2Attack通过将劫持攻击融入LLM后训练过程，提升生成对抗性提示的推理能力，实现更高效的文本到图像模型攻击

Comments Noted that This paper includes model-generated content that may contain offensive or distressing material

DIR-TIR: Dialog-Iterative Refinement for Text-to-Image Retrieval

Zongwei Zhen, Biqing Zeng

机构 * South China Normal University School of Artificial Intelligence（南方科技大学人工智能学院） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Generating an Image From 1,000 Words: Enhancing Text-to-Image With Structured Captions

Eyal Gutflaish, Eliran Kachlon, Hezi Zisman, Tal Hacham, Nimrod Sarid, Alexander Visheratin, Saar Huberman, Gal Davidi, Guy Bukchin, Kfir Goldberg, Ron Mokady

机构 * BRIA AI（BRIA人工智能） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Hallucination as an Upper Bound: A New Perspective on Text-to-Image Evaluation

Seyed Amir Kasaei, Mohammad Hossein Rohban

机构 * Department of Computer Engineering, Sharif University of Technology（谢里夫理工大学计算机工程系） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments Accepted at GenProCC NeurIPS 2025 Workshop

AutoPrompt: Automated Red-Teaming of Text-to-Image Models via LLM-Driven Adversarial Prompts

Yufan Liu, Wanqian Zhang, Huashan Chen, Lin Wang, Xiaojun Jia, Zheng Lin, Weiping Wang

机构 * Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所） ； School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络安全学院） ； School of Cyberspace, Hangzhou Dianzi University（杭州电子科技大学网络空间学院） ； Nanyang Technological University（南洋理工大学） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments Accepted by ICCV 2025

Prompt fidelity of ChatGPT4o / Dall-E3 text-to-image visualisations

Dirk HR Spennemann

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Multilingual Text-to-Image Person Retrieval via Bidirectional Relation Reasoning and Aligning

Min Cao, Xinyu Zhou, Ding Jiang, Bo Du, Mang Ye, Min Zhang

机构 * School of Computer Science and Technology, Soochow University（苏州大学计算机科学与技术学院） ； School of Computer Science, Wuhan University（武汉大学计算机学院） ； Key Laboratory of New Generation Artificial Intelligence Technology & Its Interdisciplinary Applications (Southeast University), Ministry of Education, China（新 generation 人工智能技术及交叉应用重点实验室（东南大学），教育部，中国） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments Final version published in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI). Xplore link: https://ieeexplore.ieee.org/document/11199360

I2I-Mamba: Multi-modal medical image synthesis via selective state space modeling

Omer F. Atli, Bilal Kabas, Fuat Arslan, Arda C. Demirtas, Mahmut Yurt, Onat Dalmaz, Tolga Çukur

机构 * Department of Electrical and Electronics Engineering, and National Magnetic Resonance Research Center, Bilkent University（电子工程系和国家磁共振研究中心，比尔肯特大学） ； Department of Electrical Engineering, Stanford University（电气工程系，斯坦福大学） 纠错

专题命中 文生图 ：image synthesis(title,abstract)；分类 cs.CV

Comments 12 pages, 6 figures

EFSA: Episodic Few-Shot Adaptation for Text-to-Image Retrieval

Muhammad Huzaifa, Yova Kementchedjhieva

机构 * MBZUAI（马尔堡人工智能研究所） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Unified Cross-Modal Medical Image Synthesis with Hierarchical Mixture of Product-of-Experts

Reuben Dorent, Nazim Haouchine, Alexandra Golby, Sarah Frisken, Tina Kapur, William Wells

机构 * Harvard Medical School and the Brigham and Women’s Hospital（哈佛医学院和布里洛妇产科医院） ； MIND Team, Inria Saclay, Université Paris-Saclay, Palaiseau, France and Sorbonne Université, Institut du Cerveau - Paris Brain Institute - ICM, CNRS, Inria, Inserm, AP-HP, Hôpital de la Pitié Salpêtrière（MIND团队、Inria Saclay、巴黎萨克雷大学、Palaiseau，法国以及索邦大学、巴黎脑研究所-ICM、CNRS、Inria、Inserm、AP-HP、皮蒂埃萨勒普蒂耶医院） ； Massachusetts Institute of Technology（麻省理工学院） 纠错

专题命中 文生图 ：image synthesis(title,abstract)；分类 cs.CV

Comments Accepted in IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)

Med-K2N: Flexible K-to-N Modality Translation for Medical Image Synthesis

Feng Yuan, Yifan Gao, Yuehua Ye, Haoyue Li, Xin Gao

机构 * University of Science and Technology of China（中国科学技术大学） ； Suzhou Institute of Biomedical Engineering and Technology（苏州生物医学工程与技术研究所） ； Chinese Academy of Sciences（中国科学院） ； The Third Affiliated Hospital of Sun Yat-sen University（中山大学第三附属医院） 纠错

专题命中 文生图 ：image synthesis(title,abstract)；分类 cs.CV

Comments ICLR2026 under review

Segmentor-Guided Counterfactual Fine-Tuning for Locally Coherent and Targeted Image Synthesis

Tian Xia, Matthew Sinclair, Andreas Schuh, Fabio De Sousa Ribeiro, Raghav Mehta, Rajat Rasal, Esther Puyol-Antón, Samuel Gerber, Kersten Petersen, Michiel Schaap, Ben Glocker

机构 * Department of Computing, Imperial College London, UK（帝国理工学院 computing 部, 英国） ； Heartflow, Inc., Mountain View, CA, USA（Heartflow 公司, 美国） 纠错

专题命中 文生图 ：image synthesis(title)；image generation(abstract)；分类 cs.CV

Comments Accepted at MICCAI 2025

Reinforcement Learning-Based Prompt Template Stealing for Text-to-Image Models

Xiaotian Zou

机构 * Xiaotian Zou 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments 10 pages, 3 figures

Group Critical-token Policy Optimization for Autoregressive Image Generation

Guohui Zhang, Hu Yu, Xiaoxiao Ma, JingHao Zhang, Yaning Pan, Mingde Yao, Jie Xiao, Linjiang Huang, Feng Zhao

机构 * University of Science and Technology of China（中国科学技术大学） ； Shanghai Innovation Institute（上海创新研究院） ； Fudan University（复旦大学） ； CUHK（香港中文大学） ； Beihang University（北京航空航天大学） 纠错

专题命中 文生图 ：image generation(title)；text-to-image(abstract)；分类 cs.CV

Comments Code is available at https://github.com/zghhui/GCPO

Multimodal Prompt Decoupling Attack on the Safety Filters in Text-to-Image Models

Xingkai Peng, Jun Jiang, Meng Tong, Shuai Li, Weiming Zhang, Nenghai Yu, Kejiang Chen

机构 * University of Science and Technology of China（中国科学技术大学） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

CIDER: A Causal Cure for Brand-Obsessed Text-to-Image Models

Fangjian Shen, Zifeng Liang, Chao Wang, Wushao Wen

机构 * School of Computer Science（计算机科学学院） ； Engineering, Sun Yat-sen University, Guangzhou, China（工程学院，中山大学，广州，中国） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments 5 pages, 7 figures, submitted to ICASSP2026

Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models

Jisung Hwang, Jaihoon Kim, Minhyuk Sung

机构 * KAIST（韩国科学技术院） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments Accepted to NeurIPS 2025

Regeneration Based Training-free Attribution of Fake Images Generated by Text-to-Image Generative Models

Meiling Li, Zhenxing Qian, Xinpeng Zhang

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments The paper has been withdrawn by the authors because the proposed approach is currently undergoing optimization and improvement. We are refining the methodology to achieve more robust and convincing results, and a revised version will be submitted once the enhancements are completed

CompSlider: Compositional Slider for Disentangled Multiple-Attribute Image Generation

Zixin Zhu, Kevin Duarte, Mamshad Nayeem Rizve, Chengyuan Xu, Ratheesh Kalarot, Junsong Yuan

机构 * University at Buffalo（布法罗大学） ； Adobe Inc. (ASML)（Adobe公司） 纠错

专题命中 文生图 ：image generation(title)；text-to-image(abstract)；分类 cs.CV

Comments Accepted by ICCV 2025

Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries

Yin Wu, Quanyu Long, Jing Li, Jianfei Yu, Wenya Wang

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments 21 pages, 6 figures, 17 tables

Zero-Residual Concept Erasure via Progressive Alignment in Text-to-Image Model

Hongxu Chen, Zhen Wang, Taoran Mei, Lin Li, Bowei Zhu, Runshi Li, Long Chen

机构 * The Hong Kong University of Science and Technology（香港科学与技术大学） ； University of Science and Technology of China（中国科学技术大学） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

PLA: Prompt Learning Attack against Text-to-Image Generative Models

Xinqi Lyu, Yihao Liu, Yanjie Li, Bin Xiao

机构 * The Hong Kong Polytechnic University（香港理工大学） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments 10 pages, 3 figures, and published to ICCV2025

Democratizing Text-to-Image Masked Generative Models with Compact Text-Aware One-Dimensional Tokens

Dongwon Kim, Ju He, Qihang Yu, Chenglin Yang, Xiaohui Shen, Suha Kwak, Liang-Chieh Chen

机构 * ByteDance Seed（字节跳动种子） ； POSTECH 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments ICCV 2025. Project page at https://tacju.github.io/projects/maskgen.html

T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation

Chieh-Yun Chen, Min Shi, Gong Zhang, Humphrey Shi

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments ICCV 2025

CylinderPlane: Nested Cylinder Representation for 3D-aware Image Generation

Ru Jia, Xiaozhuang Ma, Jianji Wang, Nanning Zheng

专题命中 文生图 ：image generation(title)；image synthesis(abstract)；分类 cs.CV

Comments 5 pages, 4 figures, to be published

Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models

Charvi Rastogi, Tian Huey Teh, Pushkar Mishra, Roma Patel, Ding Wang, Mark Díaz, Alicia Parrish, Aida Mostafazadeh Davani, Zoe Ashwood, Michela Paganini, Vinodkumar Prabhakaran, Verena Rieser, Lora Aroyo

机构 * Google DeepMind（谷歌DeepMind） ； Google Research（谷歌研究） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments 28 pages, 16 figures

Why Settle for Mid: A Probabilistic Viewpoint to Spatial Relationship Alignment in Text-to-image Models

Parham Rezaei, Arash Marioriyad, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban

机构 * Department of Computer Engineering（计算机工程系） ； Sharif University of Technology（谢赫·伊斯兰技术大学） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments 12 main pages, 18 figures, and 16 tables

Mask-aware Text-to-Image Retrieval: Referring Expression Segmentation Meets Cross-modal Retrieval

Li-Cheng Shen, Jih-Kang Hsieh, Wei-Hua Li, Chu-Song Chen

机构 * National Taiwan University（国立台湾大学） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；分类 cs.CV

Comments ICMR 2025