Related papers: DiSC: Resolution-Scalable Acceleration of Diffusio…

Removing degradation from document images not only improves their visual quality and readability, but also enhances the performance of numerous automated document analysis and recognition tasks. However, existing regression-based methods…

Diffusion Transformers (DiT) have become the dominant methods in image and video generation yet still suffer substantial computational costs. As an effective approach for DiT acceleration, feature caching methods are designed to cache the…

Long-context models are essential for many applications but face inefficiencies in loading large KV caches during decoding. Prior methods enforce fixed token budgets for sparse attention, assuming a set number of tokens can approximate full…

Diffusion Transformers are fundamental for video and image generation, but their efficiency is bottlenecked by the quadratic complexity of attention. While block sparse attention accelerates computation by attending only critical key-value…

Deep Neural Networks (DNNs) excel in learning hierarchical representations from raw data, such as images, audio, and text. To compute these DNN models with high performance and energy efficiency, these models are usually deployed onto…

Video Diffusion Transformer (DiT) models are a dominant approach for high-quality video generation but suffer from high inference cost due to iterative denoising. Existing caching approaches primarily exploit similarity within the diffusion…

Transformer-based Super-Resolution (SR) methods have demonstrated superior performance compared to convolutional neural network (CNN)-based SR approaches due to their capability to capture long-range dependencies. However, their high…

Long-context agentic workflows have emerged as a defining use case for large language models, making attention efficiency critical for both inference speed and serving cost. Sparse attention addresses this challenge effectively, and…

Recent years have witnessed the rapid development of acceleration techniques for diffusion models, especially caching-based acceleration methods. These studies seek to answer two fundamental questions: "When to cache" and "How to use…

Recent attempts to interleave autoregressive (AR) sketchers with diffusion-based refiners over continuous speech representations have shown promise, but they remain brittle under distribution shift and offer limited levers for…

An improved version of the sparse multiway kernel spectral clustering (KSC) is presented in this brief. The original algorithm is derived from weighted kernel principal component (KPCA) analysis formulated within the primal-dual…

Diffusion Transformers (DiTs) have demonstrated remarkable performance in visual generation tasks. However, their low inference speed limits their deployment in low-resource applications. Recent training-free approaches exploit the…

Diffusion speech enhancement on discrete audio codec features gain immense attention due to their improved speech component reconstruction capability. However, they usually suffer from high inference computational complexity due to multiple…

Diffusion models have achieved remarkable success in high-fidelity image generation but remain computationally demanding due to their multi-step denoising process and large model sizes. Although prior work improves efficiency either by…

Diffusion models have significantly advanced video super-resolution (VSR) by enhancing perceptual quality, largely through elaborately designed temporal modeling to ensure inter-frame consistency. However, existing methods usually suffer…

The growing adoption of generative AI in real-world applications has exposed a critical bottleneck in the computational demands of diffusion-based text-to-image models. In this work, we propose KDC-Diff, a novel and scalable generative…

This paper introduces DrDiff, a novel framework for long-text generation that overcomes the efficiency-quality trade-off through three core technologies. First, we design a dynamic expert scheduling mechanism that intelligently allocates…

Sparse-dense linear algebra is crucial in many domains, but challenging to handle efficiently on CPUs, GPUs, and accelerators alike; multiplications with sparse formats like CSR and CSF require indirect memory lookups. In this work, we…

Sparse training has received an upsurging interest in machine learning due to its tantalizing saving potential for the entire training process as well as inference. Dynamic sparse training (DST), as a leading sparse training approach, can…

Existing multimodal large model-based image compression frameworks often rely on a fragmented integration of semantic retrieval, latent compression, and generative models, resulting in suboptimal performance in both reconstruction fidelity…