Rectified Flow
A generative modeling method based on ordinary differential equations. It learns a velocity field that transports a simple distribution to the data distribution along approximately straight trajectories, allowing generation with fewer sampling steps than diffusion models.
Timeline (last 90 days)
FoldScape's generation strategy is divided into two steps: first, hierarchical, sliding-window one-dimensional inter-residue distance regression reconstructs the three-dimensional chain, and then, through chain assembly and sampling, a rectified flow decoder outputs the conformational ensemble.
Rectified flow is a class of generative models based on ordinary differential equations that learns a velocity field to transport a simple distribution along approximately straight trajectories to the data distribution, and can complete generation with fewer sampling steps than diffusion models.
All Facts (2)
FoldScape's generation strategy is divided into two steps: first, hierarchical, sliding-window one-dimensional inter-residue distance regression reconstructs the three-dimensional chain, and then, through chain assembly and sampling, a rectified flow decoder outputs the conformational ensemble.
50%UnverifiedRectified flow is a class of generative models based on ordinary differential equations that learns a velocity field to transport a simple distribution along approximately straight trajectories to the data distribution, and can complete generation with fewer sampling steps than diffusion models.
50%