Search Results for author:
Found 2 papers, 1 papers with code
Precise Knowledge Transfer via Flow Matching
We name this framework Knowledge Transfer with Flow Matching (FM-KT), which can be integrated with a metric-based distillation method with any form (\textit{e. g.} vanilla KD, DKD, PKD and DIST) and a meta-encoder with any available architecture (\textit{e. g.} CNN, MLP and Transformer).
Catch-Up Distillation: You Only Need to Train Once for Accelerating Sampling
On CIFAR-10, we obtain a FID of 2. 80 by sampling in 15 steps under one-session training and the new state-of-the-art FID of 3. 37 by sampling in one step with additional training.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
