Measurement-Consistent Langevin Corrector for Stabilizing Latent Diffusion Inverse Problem Solvers

arXiv:2601.04791v3 Announce Type: replace Abstract: While latent diffusion models (LDMs) have emerged as powerful priors for inverse problems, existing LDM-based solvers frequently suffer from instability. In this work, we first identify the instability as a discrepancy between the solver dynamics and stable reverse diffusion dynamics learned by the diffusion model, and show that reducing this gap stabilizes the solver. Building on this, we introduce extit{Measurement-Consistent Langevin Corrector (MCLC)}, a theoretically grounded plug-and-play stabilization module that remedies the LDM-based inverse problem solvers through measurement-consistent Langevin updates. Compared to prior approaches that rely on linear manifold assumptions, which often fail to hold in latent space, MCLC provides a principled stabilization mechanism, leading to more stable and reliable behavior in latent space.

Related

• DMin: Scalable Training Data Influence Estimation for Diffusion Models
• RectifiedHR: Enable Efficient High-Resolution Synthesis via Energy Rectification
• From Navigation to Refinement: Revealing the Two-Stage Nature of Flow-based Diffusion Models through Oracle Velocity
• BlendFusion -- Scalable Synthetic Data Generation for Diffusion Model Training

Source: arXiv cs.CV | 2026-04-13