This paper explores the effects of geometric perturbations on the stability of diffusion architectures, specifically Diffusion Transformers and Convolutional UNets, using a unified framework and contr…

The paper introduces Complexity-Balanced Splitting (CBS), a framework that efficiently allocates model capacity across the diffusion timeline by focusing computational resources on the most complex ge…

FLARE is a systematic conversion framework that enables a single checkpoint to support both autoregressive (AR) and diffusion-style parallel decoding for hybrid-attention large language models, achiev…

This paper proposes a hybrid two-stage diffusion transformer architecture for instruction-guided audio editing, balancing performance and efficiency.

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

The paper introduces a theoretically grounded evaluation framework for watermarking generative models, proposing a novel method (SSB) that allows for systematic design across all security-robustness-f…

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 demonstrates that off-the-shelf image diffusion models, like Stable Diffusion, can be repurposed to generate synthetic structured data, posing a threat of ground truth drift in closed eviden…

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.

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 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…

The paper proposes CODA, an algorithm-hardware co-designed architecture for deploying Video Diffusion Models on edge devices, achieving up to 1.80x speedup and 1.74x energy efficiency.

The paper repurposes a pre-trained speech classifier as the backbone for diffusion generation, reducing the need for two separately trained models.

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 (…

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…

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

The paper introduces Graph Cascades, a mesoscopic rewiring technique that enhances Graph Neural Networks by promoting node pairs with strong multi-hop connections to direct edges, improving performanc…

VideoMLA introduces a novel Multi-Head Latent Attention (MLA) mechanism that replaces per-head KV caches with a shared low-rank content latent, significantly reducing memory and improving throughput f…