LGQ: Learnable Geometric Quantization for Image Tokenization
LGQ:用于图像令牌化的可学习几何量化
Idil Bilge Altun, Mert Onur Cakiroglu, Elham Buxton, Mehmet Dalkilic, Hasan Kurban
机构
*
Luddy School of Informatics, Computing and Engineering, Indiana University Bloomington(印第安纳大学布卢明顿分校信息学、计算与工程学院)
;
Department of Computer Science, University of Illinois Springfield(伊利诺伊大学斯普林菲尔德分校计算机科学系)
;
College of Science and Engineering, Hamad Bin Khalifa University, Doha, Qatar(哈马德·本·卡伊夫大学多哈校区科学与工程学院)
Comments15 pages, 17 Figures Code contributions and significant writing and editing contributions by Sanskriti Shindadkar, Clyde Villacrusis, Jasper Andrews Code contributions by Brandon Yan
Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms
视频生成模型作为世界模型:高效的范式、架构和算法
Muyang He, Hanzhong Guo, Junxiong Lin, Yizhou Yu
机构
*
School of Computing and Data Science, The University of Hong Kong(计算与数据科学学院,香港大学)
;
Hong Kong Generative AI Research and Development Center(香港生成式人工智能研究与开发中心)