图像生成

PRISM: A Unified Framework for Photorealistic Reconstruction and Intrinsic Scene Modeling

Alara Dirik, Tuanfeng Wang, Duygu Ceylan, Stefanos Zafeiriou, Anna Frühstück

机构 * Imperial College London（伦敦帝国理工学院） ； Adobe Research（Adobe研究院） 纠错

专题命中 文生图 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；image editing(abstract)

IterInv: Iterative Inversion for Pixel-Level T2I Models

Chuanming Tang, Kai Wang, Joost van de Weijer

专题命中 文生图 ：image generation(abstract)；text-to-image(abstract)；diffusion(abstract)；image editing(abstract)

Comments Accepted paper at ICME 2024

PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation

PixJail：面向文本到图像越狱评估的自演化论文到流水线复现

Leyi Sheng, Han Sun, Zhen Sun, Yuntao Yue, Jinlin Wu, Xinlei He, Jiaheng Wei

机构 * The Hong Kong University of Technology and Science (Guangzhou)（香港科技与应用科技大学（广州）） ； East China Normal University（华东师范大学） ； Shanghai Qi Zhi Institute（上海启智研究院） ； Wuhan University（武汉大学） ； Institute of Deep Perception Technology, JITRI（视觉感知技术研究院，JITRI） ； CAIR, Hong Kong Institute of Science and Innovation (HKISI)（创新科技研究院，香港科学与创新研究院（HKISI）） ； MAIS, Institute of Automation, Chinese Academy of Sciences（自动化研究所，中国科学院） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；image generation(abstract)

AI总结 提出PixJail框架，通过自演化论文到流水线代理，自动构建攻击模块和可运行评估流水线，忠实复现原始实验结果，平均误差仅2.1%。

Text-to-Image Generative AI for Modeling and Simulation: Methods, Opportunities, and Applications

面向建模与仿真的文本到图像生成式人工智能：方法、机遇与应用

Philippe J. Giabbanelli

机构 * National Center for Collaboration in Medical Modeling & Simulation and Office of Enterprise Research & Innovation（医学建模与模拟协作国家中心和企业研究与创新办公室） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；image generation(abstract)

AI总结 本教程介绍文本到图像生成技术如何支持建模与仿真的多个任务，包括概念模型沟通、仿真结果可视化、教育材料生成及多尺度仿真中的异构模型接口，并提供实用工作流。

Comments To appear at the 2026 Winter Simulation Conference

DreamReader: An Interpretability Toolkit for Text-to-Image Models

DreamReader: 一种用于文本到图像模型的可解释性工具包

Nirmalendu Prakash, Narmeen Oozeer, Michael Lan, Luka Samkharadze, Phillip Howard, Roy Ka-Wei Lee, Dhruv Nathawani, Shivam Raval, Amirali Abdullah

机构 * Singapore University of Technology and Design（新加坡科技设计大学） ； Martian ； Thoughtworks ； NVIDIA ； Harvard University（哈佛大学） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

AI总结 DreamReader提出了一种统一框架，通过可组合的表示操作分析扩散模型的可解释性，引入三种新干预机制，通过实验展示其在文本到图像模型中的应用，推动可解释性研究。

Beyond Content: How Grammatical Gender Shapes Visual Representation in Text-to-Image Models

超越内容：语法性别如何塑造文本到图像模型中的视觉表示

Muhammed Saeed, Shaina Raza, Ashmal Vayani, Muhammad Abdul-Mageed, Ali Emami, Shady Shehata

专题命中 文生图 ：text-to-image(title,abstract)；image generation(abstract)

AI总结 研究揭示语法性别对文本到图像模型中视觉表示的显著影响，通过跨语言实验展示不同语法性别对性别表示的系统性影响。

Religious Bias Landscape in Language and Text-to-Image Models: Analysis, Detection, and Debiasing Strategies

Ajwad Abrar, Nafisa Tabassum Oeshy, Mohsinul Kabir, Sophia Ananiadou

机构 * Islamic University of Technology（伊斯兰技术大学） ； The University of Manchester（曼彻斯特大学） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；image generation(abstract)

Journal ref AI & Society (2025)

Combinational Backdoor Attack against Customized Text-to-Image Models

Wenbo Jiang, Jiaming He, Hongwei Li, Rui Zhang, Hanxiao Chen, Meng Hao, Haomiao Yang, Qingchuan Zhao, Guowen Xu

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

Testing chatbots on the creation of encoders for audio conditioned image generation

Jorge E. León, Miguel Carrasco

专题命中 文生图 ：image generation(title)；diffusion(abstract)；image synthesis(abstract)

Evaluating and comparing gender bias across four text-to-image models

Zoya Hammad, Nii Longdon Sowah

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

Prompting Away Stereotypes? Evaluating Bias in Text-to-Image Models for Occupations

Shaina Raza, Maximus Powers, Partha Pratim Saha, Mahveen Raza, Rizwan Qureshi

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

Transformed Low-rank Adaptation via Tensor Decomposition and Its Applications to Text-to-image Models

Zerui Tao, Yuhta Takida, Naoki Murata, Qibin Zhao, Yuki Mitsufuji

机构 * RIKEN AIP（RIKEN人工智能研究所） ； Sony AI（索尼人工智能） ； Sony Group Corporation（索尼集团） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

Comments ICCV 2025

Test-time Prompt Refinement for Text-to-Image Models

Mohammad Abdul Hafeez Khan, Yash Jain, Siddhartha Bhattacharyya, Vibhav Vineet

机构 * Florida Institute of Technology（佛罗里达理工学院） ； Microsoft Research（微软研究院） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；image generation(abstract)

Comments Accepted to ICCV 2025, MARS2 Workshop. Total 14 pages, 12 figures and 3 tables

Varif.ai to Vary and Verify User-Driven Diversity in Scalable Image Generation

M. Michelessa, J. Ng, C. Hurter, B. Y. Lim

专题命中 文生图 ：image generation(title,abstract)；text-to-image(abstract)

Comments DIS2025, code available at github.com/mario-michelessa/varifai

From Easy to Hard: Building a Shortcut for Differentially Private Image Synthesis

Kecen Li, Chen Gong, Xiaochen Li, Yuzhong Zhao, Xinwen Hou, Tianhao Wang

机构 * University of Virginia（弗吉尼亚大学） ； University of Chinese Academy of Sciences（中国科学院大学） ； Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所） 纠错

专题命中 文生图 ：image synthesis(title,abstract)；diffusion(abstract)

Comments Accepted at IEEE S&P (Oakland) 2025; code available at https://github.com/SunnierLee/DP-FETA; revised proofs in App.A

GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models

Zilong Wang, Xiang Zheng, Xiaosen Wang, Bo Wang, Xingjun Ma, Yu-Gang Jiang

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

Comments 27 pages, 7 figures

T2I-Eval-R1: Reinforcement Learning-Driven Reasoning for Interpretable Text-to-Image Evaluation

Zi-Ao Ma, Tian Lan, Rong-Cheng Tu, Shu-Hang Liu, Heyan Huang, Zhijing Wu, Chen Xu, Xian-Ling Mao

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

IPGO: Indirect Prompt Gradient Optimization for Parameter-Efficient Prompt-level Fine-Tuning on Text-to-Image Models

Jianping Ye, Michel Wedel, Kunpeng Zhang

机构 * University of Maryland, College Park（马里兰大学学院公园分校） 纠错

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

Comments 9 pages, 2 figures, 4 tables

Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models

Shawn Shan, Jenna Cryan, Emily Wenger, Haitao Zheng, Rana Hanocka, Ben Y. Zhao

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

Comments USENIX Security 2023

YINYANG-ALIGN: Benchmarking Contradictory Objectives and Proposing Multi-Objective Optimization based DPO for Text-to-Image Alignment

Amitava Das, Yaswanth Narsupalli, Gurpreet Singh, Vinija Jain, Vasu Sharma, Suranjana Trivedy, Aman Chadha, Amit Sheth

专题命中 文生图 ：text-to-image(title,abstract)；image generation(abstract)

Image-Perfect Imperfections: Safety, Bias, and Authenticity in the Shadow of Text-To-Image Model Evolution

Yixin Wu, Yun Shen, Michael Backes, Yang Zhang

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

Comments To Appear in the ACM Conference on Computer and Communications Security, October 14-18, 2024

Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models

Mor Ventura, Eyal Ben-David, Anna Korhonen, Roi Reichart

专题命中 文生图 ：text-to-image(title,abstract)；image generation(abstract)

Comments Project page: https://venturamor.github.io/CulText2IWeb/

Interpretations, Representations, and Stereotypes of Caste within Text-to-Image Generators

Sourojit Ghosh

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

Comments Upcoming Publication, AIES 2024

Situating the social issues of image generation models in the model life cycle: a sociotechnical approach

Amelia Katirai, Noa Garcia, Kazuki Ide, Yuta Nakashima, Atsuo Kishimoto

专题命中 文生图 ：image generation(title,abstract)；text-to-image(abstract)

Can MLLMs Perform Text-to-Image In-Context Learning?

Yuchen Zeng, Wonjun Kang, Yicong Chen, Hyung Il Koo, Kangwook Lee

专题命中 文生图 ：text-to-image(title,abstract)；image generation(abstract)

Comments Accepted at COLM 2024

Automatic Jailbreaking of the Text-to-Image Generative AI Systems

Minseon Kim, Hyomin Lee, Boqing Gong, Huishuai Zhang, Sung Ju Hwang

专题命中 文生图 ：text-to-image(title,abstract)；image generation(abstract)

Comments Under review

Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Models

Shawn Shan, Wenxin Ding, Josephine Passananti, Stanley Wu, Haitao Zheng, Ben Y. Zhao

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

Comments IEEE Security and Privacy 2024

PrompTHis: Visualizing the Process and Influence of Prompt Editing during Text-to-Image Creation

Yuhan Guo, Hanning Shao, Can Liu, Kai Xu, Xiaoru Yuan

专题命中 文生图 ：text-to-image(title,abstract)；image generation(abstract)

SneakyPrompt: Jailbreaking Text-to-image Generative Models

Yuchen Yang, Bo Hui, Haolin Yuan, Neil Gong, Yinzhi Cao

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)

Comments To appear in the Proceedings of the IEEE Symposium on Security and Privacy (Oakland), 2024

Language Agents for Detecting Implicit Stereotypes in Text-to-image Models at Scale

Qichao Wang, Tian Bian, Yian Yin, Tingyang Xu, Hong Cheng, Helen M. Meng, Zibin Zheng, Liang Chen, Bingzhe Wu

专题命中 文生图 ：text-to-image(title,abstract)；diffusion(abstract)