arXiv:2602. 05533v3 Announce Type: replace Abstract: We study conditional generation in diffusion models under hard constraints, where generated samples must satisfy prescribed events with probability one.
arXiv:2601. 08379v2 Announce Type: replace-cross Abstract: Pre-trained diffusion models have emerged as powerful generative priors for both unconditional and conditional sample generation, yet their outputs often deviate from the characteristics of user-specific target data.
arXiv:2606. 06179v1 Announce Type: cross Abstract: Score-based diffusion models are typically trained by minimizing the $L^2$ score matching error, and standard theoretical analyses rely on this quantity to bound the sampling discrepancy between the learned and target distributions.
The paper investigates when to activate classifier‑free guidance (CFG) in diffusion models by treating the diffusion trajectory as a time‑dependent information bottleneck. It shows that the usefulness of conditional information increases after a critical stage defined by a Fisher‑information balance, and proposes a training‑free dynamic CFG strategy that activates guidance based on a stochastic process of score statistics. Experiments across various architectures and tasks confirm that this adaptive rule improves effectiveness, robustness, and general applicability while offering a principled explanation for dynamic guidance.
arXiv:2603.22364v4 Announce Type: replace Abstract: Diffusion models achieve strong generative performance but often rely on classifier-free guidance (CFG), an inference-time intervention that modifi...
The paper investigates how repeatedly training score-based diffusion models on synthetic data can cause their outputs to drift from the target distribution. It provides theoretical upper and lower bounds on the divergence accumulated over successive training rounds, distinguishing regimes based on score estimation error and the fraction of fresh data used. Empirical experiments on synthetic data and images support the theoretical findings.
arXiv:2608. 18237v1 Announce Type: cross Abstract: Estimating the difference of two Stein's score functions is a fundamental problem in generative modeling.
arXiv:2610.19802v1 Announce Type: new Abstract: Negative guidance of diffusion models generates samples that avoid an undesired condition, specified either by reference samples or by a conditional sc...
The paper studies memorization and generalization in conditional diffusion models using a random-feature conditional score model in a high-dimensional setting. It derives asymptotic expressions for training and test losses, showing that in overparameterized regimes wider models better predict the condition-dependent mean but also exhibit reduced within-condition variance, a behavior termed "malign generalization." The analysis also reveals that more informative conditions cause training samples to be memorized at smaller widths, with experimental validation on U‑Net architectures.
Understanding the mechanism behind why diffusion models memorize their training data remains an open question in generative modeling. In this paper, we examine this question from two perspectives: (a)...
The paper addresses the challenge of guiding conditioned generative models that are diffusion processes with singular diffusion coefficients, where traditional conditional densities may be nonexistent or non‑smooth. It proposes using causal optimal transport to construct approximate loss functions that identify a minimum‑entropy control for guidance, relying on the predictable representation property of conditioned diffusion processes and well‑posed martingale problems à la Üstünel.
arXiv:2610.19042v1 Announce Type: new Abstract: Understanding the mechanism behind why diffusion models memorize their training data remains an open question in generative modeling. In this paper, we...