Related papers: Forecasting When to Forecast: Accelerating Diffusi…

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…

Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT…

Diffusion Transformers (DiT) are renowned for their impressive generative performance; however, they are significantly constrained by considerable computational costs due to the quadratic complexity in self-attention and the extensive…

Diffusion models have recently revolutionized the field of image synthesis due to their ability to generate photorealistic images. However, one of the major drawbacks of diffusion models is that the image generation process is costly. A…

Layout generation is a foundation task of graphic design, which requires the integration of visual aesthetics and harmonious expression of content delivery. However, existing methods still face challenges in generating precise and visually…

Diffusion models have shown remarkable progress in various generative tasks such as image and video generation. This paper studies the problem of leveraging pretrained diffusion models for performing discriminative tasks. Specifically, we…

Diffusion Transformers (DiTs) are a powerful yet underexplored class of generative models compared to U-Net-based diffusion architectures. We propose TIDE-Temporal-aware sparse autoencoders for Interpretable Diffusion transformErs-a…

Diffusion models have achieved impressive generative quality across modalities like 2D images, videos, and 3D shapes, but their inference remains computationally expensive due to the iterative denoising process. While recent caching-based…

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…

Diffusion Transformers (DiTs) have achieved state-of-the-art (SOTA) image generation quality but suffer from high latency and memory inefficiency, making them difficult to deploy on resource-constrained devices. One major efficiency…

Long-term time-series forecasting (LTTF) has become a pressing demand in many applications, such as wind power supply planning. Transformer models have been adopted to deliver high prediction capacity because of the high computational…

Generative models, particularly diffusion models, have made significant success in data synthesis across various modalities, including images, videos, and 3D assets. However, current diffusion models are computationally intensive, often…

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

Diffusion models have been successfully adapted to text generation tasks by mapping the discrete text into the continuous space. However, there exist nonnegligible gaps between training and inference, owing to the absence of the forward…

Diffusion-based image compression has recently shown outstanding perceptual fidelity, yet its practicality is hindered by prohibitive sampling overhead and high memory usage. Most existing diffusion codecs employ U-Net architectures, where…

Video object removal and inpainting are critical tasks in the fields of computer vision and multimedia processing, aimed at restoring missing or corrupted regions in video sequences. Traditional methods predominantly rely on flow-based…

We explore the role of attention mechanism during inference in text-conditional diffusion models. Empirical observations suggest that cross-attention outputs converge to a fixed point after several inference steps. The convergence time…

With the development of Artificial Intelligence, numerous real-world tasks have been accomplished using technology integrated with deep learning. To achieve optimal performance, deep neural networks typically require large volumes of data…

Generating cognitive-aligned layered SVGs remains challenging due to existing methods' tendencies toward either oversimplified single-layer outputs or optimization-induced shape redundancies. We propose LayerTracer, a diffusion transformer…

Diffusion models (DMs) embark a new era of generative modeling and offer more opportunities for efficient generating high-quality and realistic data samples. However, their widespread use has also brought forth new challenges in model…