CARPRT: Class-Aware Zero-Shot Prompt Reweighting for Black-Box Vision-Language Models
CARPRT:用于黑盒视觉语言模型的类感知零样本提示重加权
Ruijiang Dong, Zesheng Ye, Jianzhong Qi, Lei Feng, Feng Liu, Gang Niu, Masashi Sugiyama
机构
*
University of Melbourne(墨尔本大学)
;
Southeast University(东南大学)
;
RIKEN Center for Advanced Intelligence Project(理化学研究所先进智能项目中心)
;
The University of Tokyo(东京大学)
Distributed Sparse Interventions in Language Models
语言模型中的分布式稀疏干预
Maximilian S. Ernst, Lorenz Linhardt, Aaron Peikert, Oliver Eberle
机构
*
Max Planck School of Cognition(马克斯·普朗克认知学院)
;
Center for Lifespan Psychology, Max Planck Institute for Human Development(马克斯·普朗克人类发展研究所寿命心理学中心)
;
Machine Learning Group, Technische Universität Berlin(柏林工业大学机器学习小组)
;
Berlin Institute for the Foundations of Learning and Data (BIFOLD)(柏林学习与数据基础研究所)
机构
*
Alibaba Group(阿里巴巴集团)
;
Fudan University(复旦大学)
;
University College London(伦敦大学学院)
;
Nanyang Technological University(南洋理工大学)
;
University of Oxford(牛津大学)
机构
*
School of Computer Science and Engineering, Beihang University(北航计算机科学与工程学院)
;
Beijing Digital Native Digital City Research Center(北京数字原生数字城研究中心)
;
School of Computer Science, Peking University(北京大学计算机学院)
;
School of Artificial Intelligence, Beijing University of Posts and Telecommunications(北京邮电大学人工智能学院)
Unveiling the Fragility of Vision-Language Models: Multi-Modal Adversarial Synergy via Texture-Constrained Perturbations and Cross-Modal Optimization
揭示视觉-语言模型的脆弱性:通过纹理约束扰动和跨模态优化的多模态对抗协同
Xiang Fang, Wanlong Fang, Changshuo Wang
机构
*
School of Software Engineering, Huazhong University of Science and Technology(华中科技大学软件学院)
;
Nanyang Technological University, Singapore(新加坡南洋理工大学)
;
University College London(伦敦大学学院)
Adversarial Water-Filling: Theory, Algorithms and Foundation Model
对抗性注水:理论、算法与基础模型
Xindi Tong, Chee Wei Tan, H. Vincent Poor
机构
*
College of Computing and Data Science (CCDS), Nanyang Technological University, Singapore(南洋理工大学计算与数据科学学院(CCDS),新加坡)
;
Princeton University, United States(普林斯顿大学,美国)