Comment by kelseyfrog
4 days ago
Flow matching is iterative in the sense that it predicts a dv(t)/dt at each step as it integrates toward x_0.
4 days ago
Flow matching is iterative in the sense that it predicts a dv(t)/dt at each step as it integrates toward x_0.
It's iterative in a sense of solving differential equation iteratively. While recurrent networks are iterative in sense of putting a for loop around a bunch of if-s.
It's also in the sense that initial latent vector is Gaussian noise. The transformer loop is de-noising latent space. They just happen to be doing the equivalent of predicting x_0 directly.