Views
No views yet
Yuang Ai*, Jiaming Han*, Shaobin Zhuang*, Weijia Mao, Xuefeng Hu, Ziyan Yang, Zhenheng Yang, Huaibo Huang†, Xiangyu Yue†, Hao Chen*†‡* Equal Contribution † Corresponding Author ‡ Project LeadFor visual generation, discrete autoregressive models often struggle with poor tokenizer reconstruction, difficulties in sampling from large vocabularies, and slow token-by-token generation speeds. We present BitDance, which addresses these challenges via a large-vocabulary binary tokenizer, a binary diffusion head for sampling in large discrete space, and a next-patch diffusion paradigm that enables efficient multitoken prediction. BitDance is an open-source discrete autoregressive foundation model with 14B parameters, trained on large-scale multimodal tokens. While maintaining the standard language modeling paradigm for text tokens, BitDance employs a next-patch diffusion paradigm for visual tokens to predict multiple tokens in parallel—up to 64 per step. This unified multimodal framework is simple, scalable, and capable of efficiently generating high-resolution, photorealistic images.
1@article{ai2026bitdance,
2 title = {BitDance: Scaling Autoregressive Generative Models with Binary Tokens},
3 author = {Ai, Yuang and Han, Jiaming and Zhuang, Shaobin and Hu, Xuefeng and Yang, Ziyan and Yang, Zhenheng and Huang, Huaibo and Yue, Xiangyu and Chen, Hao},
4 journal = {arXiv preprint arXiv:2602.14041},
5 year = {2026}
6}