FMRG is a training-free single-trajectory guidance framework for flow-based models that matches or exceeds baselines on reward-guided tasks and inverse problems using as few as 3 NFEs.
Since x0 ∼N(0, 1) andx OC 0 =x M 0 = (a−µ 1)/σ1 by Proposition C.11, we havey 0 ∼N −(a−µ 1)/σ1
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance
FMRG is a training-free single-trajectory guidance framework for flow-based models that matches or exceeds baselines on reward-guided tasks and inverse problems using as few as 3 NFEs.