WEIRDO: WEak resIdual Regularized DOob's h-transform diffusion alignment

arXiv:2609.39531 · math.ST, cs.LG, stat.TH · Submitted 2026-09-30 · Read on arXiv

math.ST, cs.LG, stat.TH

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/alexdenker/DEFT

Terminology

• Alignment — 1× in this paper · explained in 1 episode
• Doob's h-transform — 1× in this paper · explained in 2 episodes

Sources

• Inference-Time Alignment for Diffusion Models via Variationally Stable Doob's Matching
• Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis Approach
• Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review

Related papers

• Conformal Prediction for Dyadic Regression Under Complex Missingness
• Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF Kernel
• Bentkus-type asymptotic e-values
• High-Dimensional Asymptotics of Differentially Private PCA
• A proximal gradient algorithm for composite log-concave sampling
• KL Convergence Guarantees for Score diffusion models under minimal data assumptions