Safety
Learning omega-Powered Conditional Distributions with Importance-Weighted Flow Matching
arXiv:2610.16419v1 Announce Type: cross Abstract: Classifier-Free Guidance (CFG) with guidance scale gamma is commonly motivated by the omega-powered conditional distribution obtained by setting omega
arXiv:2610.16419v1 Announce Type: cross Abstract: Classifier-Free Guidance (CFG) with guidance scale gamma is commonly motivated by the omega-powered conditional distribution obtained by setting omega=gamma, but CFG does not, in general, sample from this distribution exactly. We study whether the powered target can instead be learned explicitly. We introduce Importance-Weighted Conditional Flow Matching (IW-CFM), which reweights conditional flow-matching examples using density ratios obtained from frozen conditional and unconditional flow models. With exact normalized weights, the resulting objective has the same gradient as flow matching on the powered target; in practice, we use self-normalized estimation and a regularized empirical approximation for high-dimensional data. On synthetic distributions, IW-CFM recovers analytical powered targets for which numerically matched CFG, gamma=omega, exhibits a visible mismatch. On ImageNet, an amortized lightweight corrector achieves better alignment than fixed- and matched-guidance CFG with the corresponding weighted and filtered reference distributions. We additionally present an exploratory CLIP analysis of powered-density rankings on real ImageNet data. Aggregate shifts across selected prompt-specific contrasts coexist with heterogeneous classwise responses, including nonmonotonic trajectories. These results provide a practical route for studying and approximating model-defined powered conditional distributions.
Related
- Classifier-Free Guidance in Flow Matching: Non-Autonomous Potentials, Overshoot, and Posterior-Mean Control
- Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning
- MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives
- Long-Tail Adaptive Flow Matching with Explicit Conditional Consistency Guidance for Precise Multimodal Face Synthesis
Source: arXiv cs.CV | 2026-10-14