Related papers: Exploring Magnitude Preservation and Rotation Modu…
Diffusion models have emerged as the mainstream approach for visual generation. However, these models typically suffer from sample inefficiency and high training costs. Consequently, methods for efficient finetuning, inference and…
Diffusion models have emerged as one of the most promising frameworks for deep generative modeling. In this work, we explore the potential of non-uniform diffusion models. We show that non-uniform diffusion leads to multi-scale diffusion…
Masked diffusion models (MDMs) are a promising alternative to autoregressive models (ARMs), but they suffer from inherently much higher training variance. High variance leads to noisier gradient estimates and unstable optimization, so even…
Designing model architectures requires decisions such as selecting operators (e.g., attention, convolution) and configurations (e.g., depth, width). However, evaluating the impact of these decisions on model quality requires costly…
Atmospheric Turbulence (AT) correction is a challenging restoration task as it consists of two distortions: geometric distortion and spatially variant blur. Diffusion models have shown impressive accomplishments in photo-realistic image…
Diffusion Transformers (DiT) achieve strong performance in image generation but incur substantial inference costs. While prior work has reduced this cost via quantization and distillation, semi-structured sparsity, which can nearly halve…
Recent advancements in diffusion models, particularly the architectural transformation from UNet-based models to Diffusion Transformers (DiTs), significantly improve the quality and scalability of image and video generation. However,…
In spite of their huge success, transformer models remain difficult to scale in depth. In this work, we develop a unified signal propagation theory and provide formulae that govern the moments of the forward and backward signal through the…
Diffusion models, such as Stable Diffusion, have shown incredible performance on text-to-image generation. Since text-to-image generation often requires models to generate visual concepts with fine-grained details and attributes specified…
Diffusion Transformers have emerged as the foundation for vision generative models, but their scalability is limited by the high cost of hyperparameter (HP) tuning at large scales. Recently, Maximal Update Parametrization ($\mu$P) was…
Diffusion models have achieved outstanding image generation by reversing a forward noising process to approximate true data distributions. During training, these models predict diffusion scores from noised versions of true samples in a…
Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…
Video generation using diffusion-based models is constrained by high computational costs due to the frame-wise iterative diffusion process. This work presents a Diffusion Reuse MOtion (Dr. Mo) network to accelerate latent video generation.…
Data availability remains a critical bottleneck in many deep learning applications. Large-scale datasets are often expensive to collect, curate and annotate, which can limit the scalability and applicability of supervised learning methods.…
Diffusion Transformer (DiT) has demonstrated remarkable performance in text-to-image generation; however, its large parameter size results in substantial inference overhead. Existing parameter compression methods primarily focus on pruning,…
Diffusion Transformers (DiT) have become the de-facto model for generating high-quality visual content like videos and images. A huge bottleneck is the attention mechanism where complexity scales quadratically with resolution and video…
Diffusion models have achieved remarkable success across a range of generative tasks. Recent efforts to enhance diffusion model architectures have reimagined them as a form of multi-task learning, where each task corresponds to a denoising…
Diffusion models have achieved impressive performance on multi-focus image fusion (MFIF). However, a key challenge in applying diffusion models to the ill-posed MFIF problem is that defocus blur can make common symmetric geometric…
Pre-trained Transformer models like T5 and BART have advanced the state of the art on a wide range of text generation tasks. Compressing these models into smaller ones has become critically important for practical use. Common neural network…
Diffusion transformers (DiT) have already achieved appealing synthesis and scaling properties in content recreation, e.g., image and video generation. However, scaling laws of DiT are less explored, which usually offer precise predictions…