图像生成 - arXivDaily 专题

2511.07741 2025-11-12 cs.CR cs.SE 78%

Provable Repair of Deep Neural Network Defects by Preimage Synthesis and Property Refinement

Jianan Ma, Jingyi Wang, Qi Xuan, Zhen Wang

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

Comments 20 pages, full version of the paper accepted by CCS 2025

2510.27361 2025-11-03 cs.SI cs.CY 78%

Back to the Communities: A Mixed-Methods and Community-Driven Evaluation of Cultural Sensitivity in Text-to-Image Models

Sarah Kiden, Oriane Peter, Gisela Reyes-Cruz, Maira Klyshbekova, Sena Choi, Aislinn Gomez Bergin, Maria Waheed, Damian Eke, Tayyaba Azim, Sarvapali Ramchurn, Sebastian Stein, Elvira Perez Vallejos, Kate Devlin, Joel E Fischer

专题命中文生图：text-to-image(title,abstract)

2510.12254 2025-10-15 cs.LG 78%

FedMMKT:Co-Enhancing a Server Text-to-Image Model and Client Task Models in Multi-Modal Federated Learning

Ningxin He, Yang Liu, Wei Sun, Xiaozhou Ye, Ye Ouyang, Tiegang Gao, Zehui Zhang

机构 * Institute for AI Industry Research, Tsinghua University（人工智能产业研究院，清华大学）； School of Software Engineering, Nankai University（软件工程学院，南开大学）； Department of Computing, Hong Kong Polytechnic University（计算机学院，香港理工大学）； AsiaInfo Technologies（亚信息科技）； China-Austria Belt and Road Joint Laboratory on Artificial Intelligence and Advanced Manufacturing, Hangzhou Dianzi University（人工智能与先进制造联合实验室，杭州电子科技大学）

专题命中文生图：text-to-image(title,abstract)

2510.11314 2025-10-14 cs.CL 78%

Template-Based Text-to-Image Alignment for Language Accessibility: A Study on Visualizing Text Simplifications

Belkiss Souayed, Sarah Ebling, Yingqiang Gao

机构 * University of Zurich（苏黎世大学）

专题命中文生图：text-to-image(title,abstract)

2510.06525 2025-10-09 cs.LG cs.CR 78%

Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security

Ali Naseh, Anshuman Suri, Yuefeng Peng, Harsh Chaudhari, Alina Oprea, Amir Houmansadr

机构 * University of Massachusetts Amherst（马萨诸塞大学阿默斯特分校）； Northeastern University（东北大学）

专题命中文生图：text-to-image(title,abstract)

Comments Accepted at Lock-LLM Workshop, NeurIPS 2025

2509.12446 2025-09-25 cs.MA cs.AI 78%

PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization

Dawei Xiang, Wenyan Xu, Kexin Chu, Tianqi Ding, Zixu Shen, Yiming Zeng, Jianchang Su, Wei Zhang

机构 * University of Connecticut（康涅狄格大学）； Central University of Finance and Economics（中央财经大学）； Baylor University（贝勒大学）

专题命中文生图：text-to-image(title,abstract)

Comments Accepted to EMNLP 2025 System Demonstration Track

2509.17907 2025-09-23 cs.AI 78%

MEF: A Systematic Evaluation Framework for Text-to-Image Models

Xiaojing Dong, Weilin Huang, Liang Li, Yiying Li, Shu Liu, Tongtong Ou, Shuang Ouyang, Yu Tian, Fengxuan Zhao

机构 * ByteDance Seed（字节跳动种子）

专题命中文生图：text-to-image(title,abstract)

2507.16207 2025-09-16 cs.HC cs.AI cs.CY 78%

A Human-Centered Approach to Identifying Promises, Risks, & Challenges of Text-to-Image Generative AI in Radiology

Katelyn Morrison, Arpit Mathur, Aidan Bradshaw, Tom Wartmann, Steven Lundi, Afrooz Zandifar, Weichang Dai, Kayhan Batmanghelich, Motahhare Eslami, Adam Perer

专题命中文生图：text-to-image(title,abstract)

Comments 10 pages of main content, Appendix attached after references, accepted to AAAI/ACM AIES 2025

2503.14681 2025-09-01 cs.CR cs.AI 78%

DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis

Chen Gong, Kecen Li, Zinan Lin, Tianhao Wang

机构 * University of Virginia, USA（弗吉尼亚大学）； Microsoft Research, USA（微软研究院）

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

Comments Accepted at CCS 2025; The first two authors contributed equally; code available at https://github.com/2019ChenGong/DPImageBench

2412.14174 2025-08-26 cs.HC 78%

Steering Large Text-to-Image Model for Abstract Art Synthesis: Preference-based Prompt Optimization and Visualization

Aven-Le Zhou, Wei Wu, Yu-Ao Wang, Kang Zhang

专题命中文生图：text-to-image(title,abstract)

Comments arXiv admin note: text overlap with arXiv:2402.06389

2508.09293 2025-08-14 cs.CY cs.AI 78%

Ethical Medical Image Synthesis

Weina Jin, Ashish Sinha, Kumar Abhishek, Ghassan Hamarneh

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

2507.17922 2025-07-25 cs.LG cs.AI 78%

From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models

Jessica Quaye, Charvi Rastogi, Alicia Parrish, Oana Inel, Minsuk Kahng, Lora Aroyo, Vijay Janapa Reddi

专题命中文生图：text-to-image(title,abstract)

2506.21874 2025-06-30 cs.CR cs.AI 78%

On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling

Stanley Wu, Ronik Bhaskar, Anna Yoo Jeong Ha, Shawn Shan, Haitao Zheng, Ben Y. Zhao

机构 * University of Chicago（芝加哥大学）

专题命中文生图：text-to-image(title,abstract)

Comments ACM Conference on Computer and Communications Security 2025

2506.15008 2025-06-19 cs.HC cs.AI 78%

Insights Informed Generative AI for Design: Incorporating Real-world Data for Text-to-Image Output

Richa Gupta, Alexander Htet Kyaw

专题命中文生图：text-to-image(title,abstract)

Comments 15 Pages, 6 figures, CAAD Futures 2025

2506.07282 2025-06-10 cs.CY 78%

Adultification Bias in LLMs and Text-to-Image Models

Jane Castleman, Aleksandra Korolova

专题命中文生图：text-to-image(title,abstract)

Comments Accepted to the ACM Conference on Fairness, Accountability, and Transparency (FAccT '25)

2506.03735 2025-06-05 cs.CL cs.AI cs.HC 78%

Generating Pedagogically Meaningful Visuals for Math Word Problems: A New Benchmark and Analysis of Text-to-Image Models

Junling Wang, Anna Rutkiewicz, April Yi Wang, Mrinmaya Sachan

专题命中文生图：text-to-image(title,abstract)

Comments Findings of the Association for Computational Linguistics: ACL 2025

2506.03234 2025-06-05 cs.LG cs.AI cs.CR 78%

BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF

Kaiwen Duan, Hongwei Yao, Yufei Chen, Ziyun Li, Tong Qiao, Zhan Qin, Cong Wang

机构 * City University of Hong Kong（香港城市大学）； Zhejiang University（浙江大学）； KTH Royal Institute of Technology（皇家理工学院）； Hangzhou Dianzi University（杭州电子科技大学）

专题命中文生图：text-to-image(title,abstract)

2505.20692 2025-05-28 cs.HC cs.AI cs.CL 78%

Can we Debias Social Stereotypes in AI-Generated Images? Examining Text-to-Image Outputs and User Perceptions

Saharsh Barve, Andy Mao, Jiayue Melissa Shi, Prerna Juneja, Koustuv Saha

专题命中文生图：text-to-image(title,abstract)

2505.08804 2025-05-15 cs.CR cs.LG 78%

TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis

Longtian Wang, Xiaofei Xie, Tianlin Li, Yuhan Zhi, Chao Shen

机构 * School of Cyber Science and Engineering, Xi’an Jiaotong University（网络安全科学与工程学院，西安交通大学）； Singapore Management University（新加坡管理学院）； Nanyang Technological University（南洋理工大学）

专题命中文生图：text-to-image(title,abstract)

Comments 13 pages, 5 figures

2503.19252 2025-04-01 cs.HC 78%

MIRAGE: Multi-model Interface for Reviewing and Auditing Generative Text-to-Image AI

Matheus Kunzler Maldaner, Wesley Hanwen Deng, Jason Hong, Ken Holstein, Motahhare Eslami

专题命中文生图：text-to-image(title,abstract)

Comments 4 pages, 3 figures. Presented at the AAAI Conference on Human Computation and Crowdsourcing (HCOMP), 2024. Available at https://www.humancomputation.com/assets/wip_2024/HCOMP_24_WIP_4.pdf

Journal ref AAAI Conference on Human Computation and Crowdsourcing (HCOMP), Demo Track, 2024

2503.11113 2025-03-17 cs.HC 78%

Vipera: Towards systematic auditing of generative text-to-image models at scale

Yanwei Huang, Wesley Hanwen Deng, Sijia Xiao, Motahhare Eslami, Jason I. Hong, Adam Perer

专题命中文生图：text-to-image(title,abstract)

Comments Accepted to CHI Late-Breaking Work (LBW) 2025

2502.19771 2025-03-14 cs.CY cs.AI 78%

The erasure of intensive livestock farming in text-to-image generative AI

Kehan Sheng, Frank A. M. Tuyttens, Marina A. G. von Keyserlingk

专题命中文生图：text-to-image(title,abstract)

2412.07808 2025-03-11 cs.LG cs.AI 78%

Boosting Alignment for Post-Unlearning Text-to-Image Generative Models

Myeongseob Ko, Henry Li, Zhun Wang, Jonathan Patsenker, Jiachen T. Wang, Qinbin Li, Ming Jin, Dawn Song, Ruoxi Jia

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

Comments The Thirty-Eighth Annual Conference on Neural Information Processing Systems

2503.00791 2025-03-04 cs.HC 78%

Expandora: Broadening Design Exploration with Text-to-Image Model

DaEun Choi, Kihoon Son, Hyunjoon Jung, Juho Kim

专题命中文生图：text-to-image(title,abstract)

Comments Accepted to CHI'25 LBW

2310.16613 2025-02-06 cs.CR 78%

On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts

Yixin Wu, Ning Yu, Michael Backes, Yun Shen, Yang Zhang

专题命中文生图：text-to-image(title,abstract)

Comments To Appear in the 34th USENIX Security Symposium, August 13-15, 2025

2408.03946 2025-01-22 cs.HC cs.AI 78%

Prompting for products: Investigating design space exploration strategies for text-to-image generative models

Leah Chong, I-Ping Lo, Jude Rayan, Steven Dow, Faez Ahmed, Ioanna Lykourentzou

专题命中文生图：text-to-image(title,abstract)

Comments 12 pages, 7 figures

Journal ref Des. Sci. 11 (2025) e2

2312.12933 2025-01-14 cs.SE 78%

ACTesting: Automated Cross-modal Testing Method of Text-to-Image Software

Siqi Gu, Chunrong Fang, Quanjun Zhang, Zhenyu Chen

专题命中文生图：text-to-image(title,abstract)

Comments 22 pages

2412.12212 2024-12-18 cs.CR cs.AI cs.CL 78%

Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization

Portia Cooper, Harshita Narnoli, Mihai Surdeanu

专题命中文生图：text-to-image(title,abstract)

2411.10448 2024-12-13 cs.HC cs.AI 78%

Goetterfunke: Creativity in Machinae Sapiens. About the Qualitative Shift in Generative AI with a Focus on Text-To-Image

Jens Knappe

专题命中文生图：text-to-image(title,abstract)

Comments 3 figures (images), 33 pages typo, minor layout and text format issues fixed

2411.18699 2024-12-02 cs.CR cs.CL 78%

An indicator for effectiveness of text-to-image guardrails utilizing the Single-Turn Crescendo Attack (STCA)

Ted Kwartler, Nataliia Bagan, Ivan Banny, Alan Aqrawi, Arian Abbasi

专题命中文生图：text-to-image(title,abstract)

1. 文生图 3490 篇

Provable Repair of Deep Neural Network Defects by Preimage Synthesis and Property Refinement

Back to the Communities: A Mixed-Methods and Community-Driven Evaluation of Cultural Sensitivity in Text-to-Image Models

FedMMKT:Co-Enhancing a Server Text-to-Image Model and Client Task Models in Multi-Modal Federated Learning

Template-Based Text-to-Image Alignment for Language Accessibility: A Study on Visualizing Text Simplifications

Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security

PromptSculptor: Multi-Agent Based Text-to-Image Prompt Optimization

MEF: A Systematic Evaluation Framework for Text-to-Image Models

A Human-Centered Approach to Identifying Promises, Risks, & Challenges of Text-to-Image Generative AI in Radiology

DPImageBench: A Unified Benchmark for Differentially Private Image Synthesis

Steering Large Text-to-Image Model for Abstract Art Synthesis: Preference-based Prompt Optimization and Visualization

Ethical Medical Image Synthesis

From Seed to Harvest: Augmenting Human Creativity with AI for Red-teaming Text-to-Image Models

On the Feasibility of Poisoning Text-to-Image AI Models via Adversarial Mislabeling

Insights Informed Generative AI for Design: Incorporating Real-world Data for Text-to-Image Output

Adultification Bias in LLMs and Text-to-Image Models

Generating Pedagogically Meaningful Visuals for Math Word Problems: A New Benchmark and Analysis of Text-to-Image Models

BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF

Can we Debias Social Stereotypes in AI-Generated Images? Examining Text-to-Image Outputs and User Perceptions

TokenProber: Jailbreaking Text-to-image Models via Fine-grained Word Impact Analysis

MIRAGE: Multi-model Interface for Reviewing and Auditing Generative Text-to-Image AI

Vipera: Towards systematic auditing of generative text-to-image models at scale

The erasure of intensive livestock farming in text-to-image generative AI

Boosting Alignment for Post-Unlearning Text-to-Image Generative Models

Expandora: Broadening Design Exploration with Text-to-Image Model

On the Proactive Generation of Unsafe Images From Text-To-Image Models Using Benign Prompts

Prompting for products: Investigating design space exploration strategies for text-to-image generative models

ACTesting: Automated Cross-modal Testing Method of Text-to-Image Software

Finding a Wolf in Sheep's Clothing: Combating Adversarial Text-To-Image Prompts with Text Summarization

Goetterfunke: Creativity in Machinae Sapiens. About the Qualitative Shift in Generative AI with a Focus on Text-To-Image

An indicator for effectiveness of text-to-image guardrails utilizing the Single-Turn Crescendo Attack (STCA)