This paper proposes Multi-Block Diffusion Language Models (MBD-LMs) for text generation, which are obtained by post-training Block Diffusion Language Models (BD-LMs) with Multi-block Teacher Forcing (…

BlockBatch introduces a novel framework that efficiently accelerates diffusion language model (dLLM) inference by simultaneously executing multiple block-size branches for a single request, achieving…

The paper introduces BlockGen, a blockwise sequence model, to investigate the performance of uniform-state versus masked diffusion models when generating sequences block-by-block, showing that the per…

The paper systematically characterizes column-level activation sparsity across various diffusion model architectures, demonstrating that element-level sparsity metrics significantly overestimate the a…

This paper proposes KroQuant, a post-training quantization method for diffusion transformers using learned Kronecker-structured invertible transforms, which reduces parameters, improves speed, and mai…

The paper develops a quantitative framework to analyze and improve flow distillation in diffusion models, providing stability guarantees and suggesting non-uniform time scheduling to reduce approximat…

The paper introduces CaDDTree, a cost-aware method that optimizes token throughput by jointly selecting the tree structure and node budget for speculative decoding, outperforming existing methods like…

The paper introduces Geometry-Aware Tabular Diffusion (GATD), a method that enhances tabular data synthesis by explicitly incorporating pairwise geometric relationships (angles and lengths) into the d…

This paper addresses the problem of inferring a directed network from nodal measurements using graph convolutional filters and identifies the diffusion filter and network topology.

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

This paper introduces MeanFlowNFT, a method that applies reinforcement learning to MeanFlow generators to improve performance and consistency.

The paper introduces SynCity 3000, a framework for generating large, coherent 3D scenes using a convolutional generator, addressing the scarcity of 3D scene data for training.

The paper introduces Strong Stochastic Flow Maps (SSFMs), a novel framework that directly learns the strong solution map of additive-noise Stochastic Differential Equations (SDEs), enabling few-step s…

This paper shows that small forward-marginal error in score matching does not guarantee numerical stability, and constructs a smooth score field with small forward-marginal error but diverging moments…

This paper introduces DiPhon, a diffusion framework for size-scalable graph generation, using a continuous diffusion process on the graphon space and a discretized graph-level process.

A unified high-dimensional k-space reconstruction framework is proposed to enhance diffusion-based solvers for noisy MRI inverse problems through representation lifting.

This paper investigates the effects of structural and temporal inhomogeneities in decentralised federated learning and shows that they significantly slow down the convergence process.

The paper introduces MDM-VGB, a reward-guided sampler for Masked Diffusion Models, which extends the Jerrum-Sinclair backtracking Markov chain to a masked-state graph for effective high-reward generat…

This paper derives the Oracle Distance theorem for discrete diffusion models and proves that the negative ELBO is equal to the data entropy plus the path KL from the oracle reverse process to the lear…