Related papers: ViDiT-Q: Efficient and Accurate Quantization of Di…

How can we accurately quantize a pre-trained Vision Transformer model? Quantization algorithms compress Vision Transformers (ViTs) into low-bit formats, reducing memory and computation demands with minimal accuracy degradation. However,…

Diffusion models have achieved cutting-edge performance in image generation. However, their lengthy denoising process and computationally intensive score estimation network impede their scalability in low-latency and resource-constrained…

Previous Quantization-Aware Training (QAT) methods for vision transformers rely on expensive retraining to recover accuracy loss in non-linear layer quantization, limiting their use in resource-constrained environments. In contrast,…

The transformer extends its success from the language to the vision domain. Because of the stacked self-attention and cross-attention blocks, the acceleration deployment of vision transformer on GPU hardware is challenging and also rarely…

Reasoning models excel at complex tasks such as coding and mathematics, yet their inference is often slow and token-inefficient. To improve the inference efficiency, post-training quantization (PTQ) usually comes with the cost of large…

Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs. However, existing works either suffer from a severe performance drop in ultra-low precision of 4 or lower bit-widths,…

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 transformer-based video generation models (DiTs) have recently attracted widespread attention for their excellent generation quality. However, their computational cost remains a major bottleneck-attention alone accounts for over…

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…

Vision transformers (ViTs) have achieved remarkable performance in various computer vision tasks. However, intensive memory and computation requirements impede ViTs from running on resource-constrained edge devices. Due to the non-normally…

Diffusion transformers exhibit remarkable video generation capability, yet their prohibitive computational and memory costs hinder practical deployment. Model quantization and attention sparsification are two promising directions for…

Post-Training Quantization (PTQ) has received significant attention because it requires only a small set of calibration data to quantize a full-precision model, which is more practical in real-world applications in which full access to a…

Post-training quantization (PTQ) is a powerful technique for model compression, reducing the numerical precision in neural networks without additional training overhead. Recent works have investigated adopting 8-bit floating-point…

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 models have revolutionized video generation, becoming essential tools in creative content generation and physical simulation. Transformer-based architectures (DiTs) and classifier-free guidance (CFG) are two cornerstones of this…

Diffusion transformers (DiTs) adopt Patchify, mapping patch representations to token representations through linear projections, to adjust the number of tokens input to DiT blocks and thus the computation cost. Instead of a single patch…

Despite the revolutionary breakthroughs of large-scale text-to-image diffusion models for complex vision and downstream tasks, their extremely high computational and storage costs limit their usability. Quantization of diffusion models has…

Diffusion models (DMs) generate remarkable high quality images via the stochastic denoising process, which unfortunately incurs high sampling time. Post-quantizing the trained diffusion models in fixed bit-widths, e.g., 4 bits on weights…

While Vision Transformers (ViTs) are extremely effective at computer vision tasks and are replacing convolutional neural networks as the new state-of-the-art, they are complex and memory-intensive models. In order to effectively run these…

Diffusion-based video editing have reached impressive quality and can transform either the global style, local structure, and attributes of given video inputs, following textual edit prompts. However, such solutions typically incur heavy…