Related papers: Relational Feature Caching for Accelerating Diffus…

Transfer learning has become a central paradigm in modern machine learning, yet it suffers from the long-standing problem of negative transfer, where leveraging source representations can harm rather than help performance on the target…

Diffusion models have achieved remarkable performance on a wide range of generative tasks, yet training them from scratch is notoriously resource-intensive, typically requiring millions of training images and many GPU days. Motivated by a…

Diffusion Transformers (DiTs) have emerged as a leading architecture for text-to-image synthesis, producing high-quality and photorealistic images. However, the quadratic scaling properties of the attention in DiTs hinder image generation…

Generative models, particularly Diffusion Models (DM), have shown strong potential for Computed Tomography (CT) reconstruction serving as expressive priors for solving ill-posed inverse problems. However, diffusion-based reconstruction…

Local feature matching is an essential technique in image matching and plays a critical role in a wide range of vision-based applications. However, existing Transformer-based detector-free local feature matching methods encounter challenges…

Diffusion models have emerged as state-of-the-art in image generation, but their practical deployment is hindered by the significant computational cost of their iterative denoising process. While existing caching techniques can accelerate…

Imputation methods play a critical role in enhancing the quality of practical time-series data, which often suffer from pervasive missing values. Recently, diffusion-based generative imputation methods have demonstrated remarkable success…

Text-to-Video applications receive increasing attention from the public. Among these, diffusion models have emerged as the most prominent approach, offering impressive quality in visual content generation. However, it still suffers from…

A dramatic influx of diffusion-generated images has marked recent years, posing unique challenges to current detection technologies. While the task of identifying these images falls under binary classification, a seemingly straightforward…

Diffusion Transformers (DiTs) achieve state-of-the-art generation quality but require long sequential denoising trajectories, leading to high inference latency. Recent speculative inference methods enable lossless parallel sampling in…

We introduce a diffusion-transformer (DiT) framework for single-image reflection removal that leverages the generalization strengths of foundation diffusion models in the restoration setting. Rather than relying on task-specific…

In this letter, we derive the probability density function (PDF) and cumulative distribution function (CDF) of the minimum of two non-central Chi-square random variables with two degrees of freedom in terms of power series. With the help of…

Wireless connectivity promises to unshackle virtual reality (VR) experiences, allowing users to engage from anywhere, anytime. However, delivering seamless, high-quality, real-time VR video wirelessly is challenging due to the stringent…

The predominant approach to advancing text-to-image generation has been training-time scaling, where larger models are trained on more data using greater computational resources. While effective, this approach is computationally expensive,…

Diffusion Transformers (DiT) excel in video generation but encounter significant computational challenges due to the quadratic complexity of attention. Notably, attention differences between adjacent diffusion steps follow a U-shaped…

Diffusion Transformers (DiTs) with billions of model parameters form the backbone of popular image and video generation models like DALL.E, Stable-Diffusion and SORA. Though these models are necessary in many low-latency applications like…

Diffusion transformers have demonstrated remarkable capabilities in generating videos. However, their practical deployment is severely constrained by high memory usage and computational cost. Post-Training Quantization provides a practical…

Caching is crucial for enabling high-throughput networks for data intensive applications. Traditional caching technology relies on DRAM, as it can transfer data at a high rate. However, DRAM capacity is subject to contention by most system…

While Diffusion Transformers (DiTs) have achieved notable progress in video generation, this long-sequence generation task remains constrained by the quadratic complexity inherent to self-attention mechanisms, creating significant barriers…

Dense pixel matching problems such as optical flow and disparity estimation are among the most challenging tasks in computer vision. Recently, several deep learning methods designed for these problems have been successful. A sufficiently…