Flow matching models follow a two-stage process of navigation across data modes then refinement to nearest samples, revealed by exact computation of the oracle marginal velocity field.
Improved techniques for training score-based generative models.Advances in neural information processing systems, 33:12438–12448, 2020
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2025 2representative citing papers
Cross-matrix Krylov projection reuses shared subspaces from seed matrices to accelerate score pre-computation in diffusion models, delivering 15.8-43.7% time savings and up to 115x speedup versus DDPM baselines.
citing papers explorer
-
From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity
Flow matching models follow a two-stage process of navigation across data modes then refinement to nearest samples, revealed by exact computation of the oracle marginal velocity field.
-
Efficient Score Pre-computation for Diffusion Models via Cross-Matrix Krylov Projection
Cross-matrix Krylov projection reuses shared subspaces from seed matrices to accelerate score pre-computation in diffusion models, delivering 15.8-43.7% time savings and up to 115x speedup versus DDPM baselines.