A unified derivation of energy guidance for general flow matching yields an asymptotically exact Monte Carlo method, approximate gradient methods, and training losses that recover DPS, LGD, and PiGDM as special cases.
Is conditional generative modeling all you need for decision-making? In The Eleventh International Conference on Learning Representations, 2023
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Guidance of Flow Matching
A unified derivation of energy guidance for general flow matching yields an asymptotically exact Monte Carlo method, approximate gradient methods, and training losses that recover DPS, LGD, and PiGDM as special cases.