Masked Generative
Masked generative modeling is a rapidly advancing area of machine learning focused on generating various data types (images, videos, audio, text, 3D models) by predicting masked portions of input sequences. Current research emphasizes transformer-based architectures, often incorporating techniques like vector quantization and hierarchical tokenization to improve efficiency and fidelity. This approach offers significant advantages in speed and scalability compared to traditional autoregressive methods, leading to improved performance in diverse applications such as text-to-image synthesis, video generation, and anomaly detection in time series data.
Papers
DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models
Xiaoxiao He, Ligong Han, Quan Dao, Song Wen, Minhao Bai, Di Liu, Han Zhang, Martin Renqiang Min, Felix Juefei-Xu, Chaowei Tan, Bo Liu, Kang Li, Hongdong Li, Junzhou Huang, Faez Ahmed, Akash Srivastava, Dimitris Metaxas
Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis
Jinbin Bai, Tian Ye, Wei Chow, Enxin Song, Qing-Guo Chen, Xiangtai Li, Zhen Dong, Lei Zhu, Shuicheng Yan
Masked Generative Priors Improve World Models Sequence Modelling Capabilities
Cristian Meo, Mircea Lica, Zarif Ikram, Akihiro Nakano, Vedant Shah, Aniket Rajiv Didolkar, Dianbo Liu, Anirudh Goyal, Justin Dauwels