Sign up to save your podcasts
Or
Share Vision Bridge Transformer at Scale
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Vision Bridge Transformer at Scale
🤗 Upvotes: 31 | cs.CV, cs.AI
Authors:
Zhenxiong Tan, Zeqing Wang, Xingyi Yang, Songhua Liu, Xinchao Wang
Title:
Vision Bridge Transformer at Scale
Arxiv:
http://arxiv.org/abs/2511.23199v1
Abstract:
We introduce Vision Bridge Transformer (ViBT), a large-scale instantiation of Brownian Bridge Models designed for conditional generation. Unlike traditional diffusion models that transform noise into data, Bridge Models directly model the trajectory between inputs and outputs, creating an efficient data-to-data translation paradigm. By scaling these models to 20B and 1.3B parameters, we demonstrate their effectiveness for image and video translation tasks. To support this scale, we adopt a Transformer architecture and propose a variance-stabilized velocity-matching objective for robust training. Together, these advances highlight the power of scaling Bridge Models for instruction-based image editing and complex video translation.
View all episodes
By Jingwen Liang, Gengyu Wang🤗 Upvotes: 31 | cs.CV, cs.AI
Authors:
Zhenxiong Tan, Zeqing Wang, Xingyi Yang, Songhua Liu, Xinchao Wang
Title:
Vision Bridge Transformer at Scale
Arxiv:
http://arxiv.org/abs/2511.23199v1
Abstract:
We introduce Vision Bridge Transformer (ViBT), a large-scale instantiation of Brownian Bridge Models designed for conditional generation. Unlike traditional diffusion models that transform noise into data, Bridge Models directly model the trajectory between inputs and outputs, creating an efficient data-to-data translation paradigm. By scaling these models to 20B and 1.3B parameters, we demonstrate their effectiveness for image and video translation tasks. To support this scale, we adopt a Transformer architecture and propose a variance-stabilized velocity-matching objective for robust training. Together, these advances highlight the power of scaling Bridge Models for instruction-based image editing and complex video translation.