The paper presents a theoretical analysis of score mismatch in discrete diffusion models, deriving a KL divergence upper bound that quantifies the bias introduced when the training and target distributions differ. It examines partial-observation constraints such as text infilling and sentence completion, showing that the Conditional SEDD sampler can incur a bias that grows with dimension, vocabulary size, and compatibility. To mitigate this, the authors propose a Randomized Hard Clamping (RHC) sampler for coordinatewise set constraints, demonstrating through experiments that it effectively reduces bias and improves sampling performance.
arXiv:2608.20635v1 Announce Type: cross Abstract: Discrete diffusion models have demonstrated strong performance across a range of datasets, including natural language data and graph-structured data....
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:2608.25505v2 Announce Type: replace-cross Abstract: Masked diffusion models generate sequences in rounds, predicting several masked positions at once. Fewer rounds can accelerate decoding, but...
arXiv:2607. 16685v1 Announce Type: cross Abstract: Conditional diffusion models have become a powerful and flexible framework for learning complex conditional distributions from labeled data.
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...
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...
arXiv:2607. 14398v1 Announce Type: cross Abstract: Constrained generative models aim to produce samples that satisfy complex feasibility constraints while remaining faithful to the data distribution.
arXiv:2605. 00161v2 Announce Type: replace Abstract: Diffusion language models (DLMs) are an attractive alternative to autoregressive models because they promise sublinear-time, parallel generation, yet practical gains remain elusive as high-quality samples still demand hundreds of refinement steps.
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:2606. 13240v1 Announce Type: cross Abstract: A key strength of diffusion models lies in their flexibility, since their outputs can be controlled at sampling time through guidance.
arXiv:2607. 23226v1 Announce Type: new Abstract: Despite the empirical success of score-based diffusion models, a complete theoretical understanding of how finite-sample learning, network parameterization, and numerical discretization jointly dictate generative quality remains underdeveloped.
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.