Automated Black-box Prompt Engineering for Personalized Text-to-Image Generation
Carnegie Mellon University(卡内基梅隆大学);University of Pennsylvania(宾夕法尼亚大学);Sony AI(索尼人工智能);Sony Group Corporation(索尼集团);Bosch Center for AI(博世人工智能中心)
Yutong He, Alexander Robey, Naoki Murata, Yiding Jiang, Joshua Nathaniel Williams, George J. Pappas, Hamed Hassani, Yuki Mitsufuji, Ruslan Salakhutdinov, J. Zico Kolter
Prompt engineering is an effective but labor-intensive way to control text-to-image (T2I) generative models. Its time-intensive nature and complexity have spurred the development of algorithms for automated prompt generation. However, these methods often struggle with transferability across T2I models, require white-box access to the underlying model, or produce non-intuitive prompts. In this work, we introduce PRISM, an algorithm that automatically produces human-interpretable and transferable prompts that can effectively generate desired concepts given only black-box access to T2I models. Inspired by large language model (LLM) jailbreaking, PRISM leverages the in-context learning ability of LLMs to iteratively refine the candidate prompt distribution built upon the reference images. Our experiments demonstrate the versatility and effectiveness of PRISM in generating accurate prompts for objects, styles, and images across multiple T2I models, including Stable Diffusion, DALL-E, and Midjourney.
Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion Recognition
Graduate School of Information Science(信息科学研究生学校);Technology, Hokkaido University, Sapporo 060-0814, Japan(技术,北海道大学,札幌060-0814,日本);Office of Institutional Research, Hokkaido University, Sapporo 060-0808, Japan(机构研究办公室,北海道大学,札幌060-0808,日本);Faculty of Information Science(信息科学学院)
Automated Detection of Pre-training Text in Black-box LLMs
Key Laboratory of Trustworthy Distributed Computing and Service (MoE), Beijing University of Posts and Telecommunications, China(可信分布式计算与服务重点实验室,北京邮电大学,中国);Zhongguancun Laboratory, China(中关村实验室,中国)
Exploring the Potential of LLMs as Personalized Assistants: Dataset, Evaluation, and Analysis
Department of Electrical and Computer Engineering, Seoul National University(电子与计算机工程系,首尔国立大学);Interdisciplinary Program in Artificial Intelligence, Seoul National University(人工智能跨学科计划,首尔国立大学);AIIS, ASRI, INMC, and ISRC, Seoul National University(人工智能研究所、人工智能研究机构、智能网络中心和智能系统研究组,首尔国立大学)
Personalized Learning Path Planning with Goal-Driven Learner State Modeling
Department of Computer Science and Technology, Beijing National Research Center for Information Science and Technology(计算机科学与技术系,信息科学国家研究中心);Tsinghua University(清华大学);Institution of Education(教育研究所);Department of Statistics and Data Science(统计与数据科学系)
Slide2Text: Leveraging LLMs for Personalized Textbook Generation from PowerPoint Presentations
East China Normal University(华东师范大学);Shanghai Institute of Artificial Intelligence for Education(上海人工智能教育研究院);School of Computer Science and Technology, East China Normal University(华东师范大学计算机科学与技术学院)
Towards AI enabled automated tracking of multiple boxers
Indian Institute of Technology Madras(印度马德拉斯理工学院);Indian Institute of Technology Gandhinagar(印度甘地讷格尔理工学院);Liverpool John Moores University(利物浦约翰摩尔大学);Inspire Institute of Technology(因斯派尔理工学院)
The Hatching-Box: A Novel System for Automated Monitoring and Quantification of Drosophila melanogaster Developmental Behavior
Institute of Geoinformatics(地理信息研究所);University of Münster(穆尔斯特大学);Faculty of Mathematics & Computer Science(数学与计算机科学学院);Institute of Neuro- and Behavioral Biology(神经生物学与行为生物学研究所)
DART: An Automated End-to-End Object Detection Pipeline with Data Diversification, Open-Vocabulary Bounding Box Annotation, Pseudo-Label Review, and Model Training
YOLO3D: End-to-end real-time 3D Oriented Object Bounding Box Detection from LiDAR Point Cloud
Valeo AI Research(法雷奥人工智能研究院)
三维空间中的目标检测与分类是自动驾驶中的一项关键任务。LiDAR传感器用于提供周围环境的3D点云重建,而实时的3D对象限界框检测任务仍然是一个强大的算法挑战。在本文中,我们建立在2D透视图像空间中的一次性回归元架构的成功基础上,并将其扩展到从LiDAR点云生成定向3D对象边界框。我们的主要贡献是将YOLO v2的损失函数扩展为包括偏航角、笛卡尔坐标中的3D盒中心和盒的高度作为直接回归问题。该公式实现了实时的性能,这对于自动驾驶至关重要。我们的测试结果在KITTI基准测试中显示出令人鼓舞的数字,在Titan X GPU上实现了实时的性能(40 fps)。