paper-with-me

홈 › Papers

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

2026-01-08 · Lee Hyoseok, Sohwi Lim, Eunju Cha, Tae-Hyun Oh arxiv

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 \textit{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.

📄 PDF Abstract BibTeX arXiv:2601.04791

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Metropolis-Adjusted Diffusion Models

2026-05-10 · Kevin H. Lam, Tyler Farghly, Christopher Williams, Jun Yang 외 arxiv

Sampling from score-based diffusion models incurs bias due to both time discretisation and the approximation of the score function. A common strategy for reducing this bias is to apply corrector steps based on the unadju…

Discrete Predictor-Corrector Diffusion Models for Image Synthesis

2022-09-29 · ICLR Anonymous Submission 2022 9 · Anonymous

We introduce Discrete Predictor-Corrector diffusion models (DPC), extending predictor-corrector samplers in Gaussian diffusion models to the discrete case. Predictor-corrector samplers are a class of samplers for diffusi…

Conditional Image GenerationImage Generation

FlowLPS: Langevin-Proximal Sampling for Flow-based Inverse Problem Solvers

2025-12-08 · Jonghyun Park, Jong Chul Ye arxiv

Deep generative models are powerful priors for imaging inverse problems, but training-free solvers for latent flow models face a practical finite-step trade-off. Optimization-heavy methods quickly improve measurement con…

Continuous-Time Probabilistic Correctors for Uncertainty-Aware Physics-Based Spacecraft Trajectory Forecasting

2026-06-19 · Muhammad Bilal Shahid, Zhanhong Jiang, Soumik Sarkar, Cody Fleming arxiv

Long-horizon spacecraft trajectory forecasting suffers from error accumulation due to the absence of corrective observations in the forecast regime, making reliable uncertainty estimation crucial for safety-critical deci…

Trajectory Forecasting

Generative Shape Reconstruction with Geometry-Guided Langevin Dynamics

2026-03-27 · Linus Härenstam-Nielsen, Dmitrii Pozdeev, Thomas Dagès, Nikita Araslanov 외 arxiv

Reconstructing complete 3D shapes from incomplete or noisy observations is a fundamentally ill-posed problem that requires balancing measurement consistency with shape plausibility. Existing methods for shape reconstruct…