Related papers: Not All Tokens Need 40 Steps: Heterogeneous Step A…
Transformer-based models have achieved state-of-the-art performance in various computer vision tasks, including image and video analysis. However, Transformer's complex architecture and black-box nature pose challenges for explainability, a…
No-reference video quality assessment (NR-VQA) estimates perceptual quality without a reference video, which is often challenging. While recent techniques leverage saliency or transformer attention, they merely address global context of the…
Video transformers have recently emerged as an effective alternative to convolutional networks for action classification. However, most prior video transformers adopt either global space-time attention or hand-defined strategies to compare…
Due to spatial redundancy in remote sensing images, sparse tokens containing rich information are usually involved in self-attention (SA) to reduce the overall token numbers within the calculation, avoiding the high computational cost issue…
Video generation using diffusion models is highly computationally intensive, with 3D attention in Diffusion Transformer (DiT) models accounting for over 80\% of the total computational resources. In this work, we introduce {\bf RainFusion},…
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…
Transformers have become the foundation of numerous state-of-the-art AI models across diverse domains, thanks to their powerful attention mechanism for modeling long-range dependencies. However, the quadratic scaling complexity of attention…
Diffusion models are widely recognized for their ability to generate high-fidelity images. Despite the excellent performance and scalability of the Diffusion Transformer (DiT) architecture, it applies fixed compression across different…
Diffusion-based generative models learn to iteratively transfer unstructured noise to a complex target distribution as opposed to Generative Adversarial Networks (GANs) or the decoder of Variational Autoencoders (VAEs) which produce samples…
We consider the allocation of Virtual Arrays (VAs) in a Heterogeneous Disk Array (HDA). Each VA holds groups of related objects and datasets such as files, relational tables, which has similar performance and availability characteristics.…
We introduce Presto, a novel video diffusion model designed to generate 15-second videos with long-range coherence and rich content. Extending video generation methods to maintain scenario diversity over long durations presents significant…
Visual geometry transformers have become powerful architectures for multi-view 3D reconstruction, enabling joint prediction of multiple 3D attributes in a feed-forward manner. However, their computational cost grows quadratically with the…
Vision transformer has achieved impressive performance for many vision tasks. However, it may suffer from high redundancy in capturing local features for shallow layers. Local self-attention or early-stage convolutions are thus utilized,…
While generative modeling on time series facilitates more capable and flexible probabilistic forecasting, existing generative time series models do not address the multi-dimensional properties of time series data well. The prevalent…
Diffusion models have achieved impressive success in high-fidelity image generation but suffer from slow sampling due to their inherently iterative denoising process. While recent one-step methods accelerate inference by learning direct…
The application of diffusion transformers is suffering from their significant inference costs. Recently, feature caching has been proposed to solve this problem by reusing features from previous timesteps, thereby skipping computation in…
Existing video tokenizers typically use the traditional Variational Autoencoder (VAE) architecture for video compression and reconstruction. However, to achieve good performance, its training process often relies on complex multi-stage…
Sounding Video Generation (SVG) remains a challenging task due to the inherent structural misalignment between audio and video, as well as the high computational cost of multimodal data processing. In this paper, we introduce ProAV-DiT, a…
Synthetic data generation in histopathology faces unique challenges: preserving tissue heterogeneity, capturing subtle morphological features, and scaling to unannotated datasets. We present a latent diffusion model that generates realistic…
Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents. However, existing diffusion-based methods are slow due to numerous denoising steps and costly…