Related papers: Runge-Kutta Approximation and Decoupled Attention …

Diffusion Transformers (DiT) excel at image and video generation but face computational challenges due to the quadratic complexity of self-attention operators. We propose DiTFastAttn, a post-training compression method to alleviate the…

Diffusion Transformers (DiTs) have exhibited robust capabilities in image generation tasks. However, accurate text-guided image editing for multimodal DiTs (MM-DiTs) still poses a significant challenge. Unlike UNet-based structures that…

This paper identifies significant redundancy in the query-key interactions within self-attention mechanisms of diffusion transformer models, particularly during the early stages of denoising diffusion steps. In response to this observation,…

Diffusion transformers (DiTs) have emerged as a dominant architecture for text-to-image generation, yet their performance drops when generating at resolutions beyond their training range. Existing training-free approaches mitigate this by…

Diffusion models excel in high-fidelity image generation but face scalability limits due to transformers' quadratic attention complexity. Plug-and-play token reduction methods like ToMeSD and ToFu reduce FLOPs by merging redundant tokens in…

Video diffusion transformers have achieved remarkable progress in high-quality video generation, but remain computationally expensive due to the quadratic complexity of attention over high-dimensional video sequences. Recent acceleration…

Diffusion models (DMs) and flow-matching models have demonstrated remarkable performance in image and video generation. However, such models require a significant number of function evaluations (NFEs) during sampling, leading to costly…

Diffusion models with large-scale pre-training have achieved significant success in the field of visual content generation, particularly exemplified by Diffusion Transformers (DiT). However, DiT models have faced challenges with quadratic…

Test-time adaptation (TTA) addresses the unforeseen distribution shifts occurring during test time. In TTA, performance, memory consumption, and time consumption are crucial considerations. A recent diffusion-based TTA approach for…

Recently, Transformer-based architecture has been introduced into single image deraining task due to its advantage in modeling non-local information. However, existing approaches tend to integrate global features based on a dense…

Outdoor images often suffer from severe degradation due to rain, haze, and noise, impairing image quality and challenging high-level tasks. Current image restoration methods struggle to handle complex degradation while maintaining…

Diffusion models have significantly improved the quality and diversity of audio generation but are hindered by slow inference speed. Rectified flow enhances inference speed by learning straight-line ordinary differential equation (ODE)…

Machine learning methods, such as diffusion models, are widely explored as a promising way to accelerate high-fidelity fluid dynamics computation via a super-resolution process from faster-to-compute low-fidelity input. However, existing…

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…

Self-attention is central to the success of Transformer architectures; however, learning the query, key, and value projections from random initialization remains challenging and computationally expensive. In this paper, we propose two…

State-of-the-art text-to-image diffusion models can produce impressive visuals but may memorize and reproduce training images, creating copyright and privacy risks. Existing prompt perturbations applied at inference time, such as random…

Vision-based perception and reasoning is essential for scene understanding in any autonomous system. RGB and depth images are commonly used to capture both the semantic and geometric features of the environment. Developing methods to…

Diffusion-based methods demonstrate significant potential for remote sensing image super-resolution at large scaling factors, particularly in reference-based super-resolution (RefSR) where high-resolution reference images provide critical…

Transformer-based large language models (LLMs) excel in natural language processing tasks by capturing long-range dependencies through self-attention mechanisms. However, long-context modeling faces significant computational inefficiencies…

Recently, image editing based on Diffusion-in-Transformer models has undergone rapid development. However, existing editing methods often lack effective control over the degree of editing, limiting their ability to achieve more customized…