5 papers · 1 filter
Classifier-Free Guidance in Flow Matching: Non-Autonomous Potentials, Overshoot, and Posterior-Mean Control
Jishen Peng, Zheng Ma
Classifier-free guidance (CFG) improves conditional generation in Flow Matching, but strong guidance can distort the generated distribution and reduce diversity. We provide a geome…
Geometry-Aware Diffusion Guidance via Curvature-Adaptive Tubular Correction
Enze Jiang, Jinwei He, Zheng Ma
Gradient-guided diffusion samplers provide flexible priors for inverse problems and conditional generation, but strong guidance can move the sampling trajectory into regions where…
Analytic Distribution of Classifier-Free Guidance for Schedule Design
Enze Jiang, Zheng Ma
Classifier-free guidance (CFG) is the default mechanism for conditional generation in diffusion models, but the distribution sampled by its deterministic guided dynamics is not cap…
Decoupled Latent Optimization of Diffusion Models for Full Waveform Inversion
Chen Min, Zheng Ma
Full waveform inversion (FWI) recovers subsurface velocity from seismic recordings by solving a severely ill-posed, nonconvex PDE-constrained optimization. Classical regularizers s…
Robust Physics-Guided Diffusion for Full-Waveform Inversion
Jishen Peng, Enze Jiang, Zheng Ma +1
We develop a robust physics-guided diffusion framework for full-waveform inversion that combines a score-based generative prior with likelihood guidance computed through wave-equat…