Filtering Memorization from Parameter-Space in Diffusion Models
从参数空间过滤记忆化在扩散模型中
Yu Zhe, Yang Jiayan, Wei Junhao, Yu-Lin Tsai, Wang Chen
机构
*
RIKEN AIP(理化学研究所Advanced Institute for Peripheral Research)
;
Science of Tokyo(东京科学大学)
;
University of California, Berkeley(加州大学伯克利分校)
;
Zhejiang University(浙江大学)
Replication in Visual Diffusion Models: A Survey and Outlook
视觉扩散模型中的复制:一项综述与展望
Wenhao Wang, Yifan Sun, Zongxin Yang, Zhengdong Hu, Zhentao Tan, Yi Yang
机构
*
Australian Artificial Intelligence Institute, University of Technology Sydney(澳大利亚人工智能研究所,悉尼技术大学)
;
Baidu Inc.(百度公司)
;
College of Computer Science and Technology, Zhejiang University(计算机科学与技术学院,浙江大学)
AtomBench: A Benchmarking Framework for Generative Crystal Reconstruction Models in Conventional Superconductors
AtomBench:传统超导体中生成晶体重建模型的基准测试框架
Charles Rhys Campbell, Aldo H. Romero, Kamal Choudhary
机构
*
Department of Physics and Astronomy, West Virginia University(物理与天文学系,西弗吉尼亚大学)
;
Department of Materials Science and Engineering, Whiting School of Engineering, The Johns Hopkins University(材料科学与工程系,韦廷工程学院,约翰霍普金斯大学)
CommentsWithdrawn by the authors. The proof of the coefficient-robust Schwarz preconditioner requires substantial revision, including clarification of the owner-selected bubble transform construction and the assumptions on variable polynomial degrees. The authors will prepare a revised version
Comments20 pages, 11 figures (Universe Special Issue: 10th Anniversary of Universe: Studying the Strongly Interacting Matter in Nuclear Reactions from Intermediate to Ultra-Relativistic Energies)
机构
*
Lausanne University Hospital (CHUV) and University of Lausanne(拉沃斯大学医院(CHUV)和拉沃斯大学)
;
Massachusetts General Hospital(麻省总医院)
;
Athinoula A. Martinos Center for Biomedical Imaging(阿提诺拉A.马丁诺斯生物医学成像中心)
Imbalance-Robust and Sampling-Efficient Continuous Conditional GANs via Adaptive Vicinal Learning and Auxiliary Regularization
通过自适应邻域学习和辅助正则化实现不平衡鲁棒且采样高效的连续条件生成对抗网络
Xin Ding, Yun Chen, Yongwei Wang, Kao Zhang, Sen Zhang, Peibei Cao, Xiangxue Wang
机构
*
School of Artificial Intelligence/School of Future Technology, Nanjing University of Information Science & Technology, Nanjing, China(人工智能学院/未来技术学院,南京信息科学技术大学)
;
Perceptual and Generative AI Lab, Nanjing University of Information Science & Technology, Nanjing, China(感知与生成人工智能实验室,南京信息科学技术大学)
;
College of Media, Zhejiang University, Hangzhou, China(传媒学院,浙江大学)
;
College of Computer Science and Technology, Zhejiang University, Hangzhou, China(计算机科学与技术学院,浙江大学)
MAME: Multidimensional Adaptive Metamer Exploration with Human Perceptual Feedback
MAME:基于人类感知反馈的多维自适应同态体探索
Mina Kamao, Hayato Ono, Ayumu Yamashita, Kaoru Amano, Masataka Sawayama
机构
*
Graduate School of Information Science and Technology(信息科学与技术研究生学校)
;
The University of Tokyo(东京大学)
;
Graduate School of System Informatics(系统信息科学研究生学校)
;
Kobe University(大阪大学)
;
Hokkaido University(北海道大学)
;
Prometech CG Research(Prometech CG研究所)