Text to Image Model
Text-to-image models generate images from textual descriptions, aiming to achieve high fidelity, creativity, and safety. Current research focuses on improving image-text alignment, mitigating biases and safety issues (like generating harmful content or being vulnerable to jailbreaks), and enhancing model generalizability and efficiency through techniques such as diffusion models, fine-tuning strategies, and vector quantization. These advancements have significant implications for various fields, including art, design, and medical imaging, but also raise ethical concerns regarding bias, safety, and potential misuse requiring ongoing investigation and development of robust mitigation strategies.
256papers
Papers - Page 7
August 1, 2024
Jailbreaking Text-to-Image Models with LLM-Based Agents
Yingkai Dong, Zheng Li, Xiangtao Meng, Ning Yu, Shanqing GuoShandong University●CISPA Helmholtz Center for Information Security●Netflix Eyeline StudiosA new approach for encoding code and assisting code understanding
Mengdan Fan, Wei Zhang, Haiyan Zhao, Zhi JinPeking University
July 17, 2024
Direct Unlearning Optimization for Robust and Safe Text-to-Image Models
Yong-Hyun Park, Sangdoo Yun, Jin-Hwa Kim, Junho Kim, Geonhui Jang, Yonghyun Jeong, Junghyo Jo, Gayoung LeeReliable and Efficient Concept Erasure of Text-to-Image Diffusion Models
Chao Gong, Kai Chen, Zhipeng Wei, Jingjing Chen, Yu-Gang Jiang
July 9, 2024
June 30, 2024
Chest-Diffusion: A Light-Weight Text-to-Image Model for Report-to-CXR Generation
Peng Huang, Xue Gao, Lihong Huang, Jing Jiao, Xiaokang Li, Yuanyuan Wang, Yi GuoLLM4GEN: Leveraging Semantic Representation of LLMs for Text-to-Image Generation
Mushui Liu, Yuhang Ma, Yang Zhen, Jun Dan, Yunlong Yu, Zeng Zhao, Zhipeng Hu, Bai Liu, Changjie Fan
June 25, 2024