Related papers: Mixture of Efficient Diffusion Experts Through Aut…

Diffusion models demonstrate outstanding performance in image generation, but their multi-step inference mechanism requires immense computational cost. Previous works accelerate inference by leveraging layer or token cache techniques to…

Discrete diffusion models have recently shown significant progress in modeling complex data, such as natural languages and DNA sequences. However, unlike diffusion models for continuous data, which can generate high-quality samples in just…

To solve ever more complex problems, Deep Neural Networks are scaled to billions of parameters, leading to huge computational costs. An effective approach to reduce computational requirements and increase efficiency is to prune unnecessary…

This paper identifies significant redundancy in the query-key interactions within self-attention mechanisms of diffusion transformer models, particularly during the early stages of denoising diffusion steps. In response to this observation,…

Mixture-of-Experts (MoE) Large Language Models (LLMs) efficiently scale-up the model while keeping relatively low inference cost. As MoE models only activate part of the experts, related work has proposed expert prediction and caching…

Diffusion models have found widespread adoption in various areas. However, their sampling process is slow because it requires hundreds to thousands of network evaluations to emulate a continuous process defined by differential equations. In…

Diffusion models have become the dominant tool for high-fidelity image and video generation, yet are critically bottlenecked by their inference speed due to the numerous iterative passes of Diffusion Transformers. To reduce the exhaustive…

Exploring deep convolutional neural networks of high efficiency and low memory usage is very essential for a wide variety of machine learning tasks. Most of existing approaches used to accelerate deep models by manipulating parameters or…

Due to the high complexity and technical requirements of industrial production processes, surface defects will inevitably appear, which seriously affects the quality of products. Although existing lightweight detection networks are highly…

This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models. While diffusion models are renowned for their generative modeling capabilities,…

In recent years, motion generative models have undergone significant advancement, yet pose challenges in aligning with downstream objectives. Recent studies have shown that using differentiable rewards to directly align the preference of…

We propose a novel adaptive Mixture-of-Experts (MoE) framework for time series forecasting that enhances expert specialization by incorporating expert-specific loss information directly into the training process. Notably, the overall…

Diffusion models are an important tool for generative modelling, serving as effective priors in applications such as imaging and protein design. A key challenge in applying diffusion models for downstream tasks is efficiently sampling from…

Mixture-of-Experts (MoE) models offer dynamic computation, but are typically deployed as static full-capacity models, missing opportunities for deployment-specific specialization. We introduce PreMoE, a training-free framework that…

Recent efforts on Diffusion Mixture-of-Experts (MoE) models have primarily focused on developing more sophisticated routing mechanisms. However, we observe that the underlying architectural configuration space remains markedly…

Efficient deep learning-based approaches have achieved remarkable performance in single image super-resolution. However, recent studies on efficient super-resolution have mainly focused on reducing the number of parameters and…

Denoising diffusion models have emerged as a powerful tool for various image generation and editing tasks, facilitating the synthesis of visual content in an unconditional or input-conditional manner. The core idea behind them is learning…

Diffusion models are the go-to method for Text-to-Image generation, but their iterative denoising processes has high inference latency. Quantization reduces compute time by using lower bitwidths, but applies a fixed precision across all…

In this paper, we present DiT-MoE, a sparse version of the diffusion Transformer, that is scalable and competitive with dense networks while exhibiting highly optimized inference. The DiT-MoE includes two simple designs: shared expert…

We study a discrete denoising diffusion framework that integrates a sample-efficient estimator of single-site conditionals with round-robin noising and denoising dynamics for generative modeling over discrete state spaces. Rather than…