This paper proposes a semi-supervised framework, RepG, for conditional generative modeling using stochastic interpolation and low-dimensional latent representations.

The paper proposes a unified, constrained optimization framework using KL divergence and likelihood constraints to achieve effective and principled unlearning in diffusion models.

DASH introduces a dual-branch distillation framework to effectively compress class-conditional diffusion models by independently supervising both score branches, significantly preserving guidance fide…

The paper proposes Alignment-Guided Score Matching (AGSM), a lightweight, reward-free post-training method that integrates contrastive alignment guidance directly into the score-matching objective of…

The paper proposes a semi-relaxed Gromov-Wasserstein objective to estimate the latent connectivity structure of large-scale networks, achieving statistically consistent and efficient recovery of the u…

GiPL proposes a novel two-branch framework combining iterative pseudo-label self-training and generative data augmentation to significantly improve Cross-Domain Few-Shot Object Detection by better uti…

The paper introduces D3IM, a novel parameter-free sampler that enables direct revision of visible tokens in Masked Diffusion Language Models, and proposes SCOPE to mitigate the model's tendency to per…

This paper establishes a connection between neural network approximation of score functions and approximation of probability distributions generated by reverse diffusion models.

The paper introduces DSL-LLaDA, a method that lightly adapts a pre-trained masked diffusion language model to perform continuous denoising in embedding space, significantly improving text generation q…

This paper evaluates the consistency and effectiveness of decoding methods for diffusion large language models (dLLMs) across diverse evaluation settings and reveals their sensitivity to prompt templa…

The paper introduces SARDI, a novel, training-free framework that uses low-confidence 'lookahead' tokens generated during the denoising process of discrete diffusion language models to dynamically gui…

The paper introduces a histogram-regularized latent diffusion model to synthesize highly realistic and subtype-specific pulmonary nodules in 3D CT volumes, addressing the limitations of existing metho…

The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion L…

The paper proposes using a mask-conditioned latent diffusion model to generate synthetic, labeled TEM images for data augmentation, achieving small but measurable performance improvements in defect de…

This paper introduces gradient inference, a new approach to developing sound and efficient gradient estimators for probabilistic programs by reducing gradient estimation to a related probabilistic inf…

The paper proposes VRPO, a reinforcement learning-based optimization strategy that replaces static alignment losses in diffusion models, significantly improving both convergence and image fidelity.

The paper introduces PRISM, a method for decoding preference signals from noisy latents using a lightweight Query-based Aggregation head and a frozen video diffusion backbone, achieving state-of-the-a…

This paper proposes an uncertainty-guided synthetic context augmentation strategy for semantic segmentation models to improve performance on complex datasets with data sparsity and rare or visually di…