Related papers: Image-Free Timestep Distillation via Continuous-Ti…

As a highly expressive generative model, diffusion models have demonstrated exceptional success across various domains, including image generation, natural language processing, and combinatorial optimization. However, as data distributions…

Sampling from diffusion probabilistic models (DPMs) is often expensive for high-quality image generation and typically requires many steps with a large model. In this paper, we introduce sampling Trajectory Stitching T-Stitch, a simple yet…

Discrete diffusion models have emerged as powerful tools for high-quality data generation. Despite their success in discrete spaces, such as text generation tasks, the acceleration of discrete diffusion models remains under-explored. In…

Distillation addresses the slow sampling problem in diffusion models by creating models with smaller size or fewer steps that approximate the behavior of high-step teachers. In this work, we propose a reinforcement learning based…

Diffusion trajectory distillation accelerates sampling by training a student model to approximate the multi-step denoising trajectories of a pretrained teacher model using far fewer steps. Despite strong empirical results, the trade-off…

Diffusion models are powerful generative models that achieve state-of-the-art performance in image synthesis. However, training them demands substantial amounts of data and computational resources. Continual learning would allow for…

Significant advancements in image generation have been made with diffusion models. Nevertheless, when contrasted with previous generative models, diffusion models face substantial computational overhead, leading to failure in real-time…

Transformer-based architectures have become the de-facto standard models for diverse vision tasks owing to their superior performance. As the size of the models continues to scale up, model distillation becomes extremely important in…

Diffusion-based text-to-image generation models trained on extensive text-image pairs have demonstrated the ability to produce photorealistic images aligned with textual descriptions. However, a significant limitation of these models is…

Flow-based generative models achieve state-of-the-art sample quality, but require the expensive solution of a differential equation at inference time. Flow map models, commonly known as consistency models, encompass many recent efforts to…

It is currently difficult to distill discrete diffusion models. In contrast, continuous diffusion literature has many distillation approaches methods that can reduce sampling steps to a handful. Our method, Discrete Moment Matching…

Modeling physical systems in a generative manner offers several advantages, including the ability to handle partial observations, generate diverse solutions, and address both forward and inverse problems. Recently, diffusion models have…

Autoregressive (AR) models with diffusion heads have recently achieved strong text-to-audio performance, yet their iterative decoding and multi-step sampling process introduce high-latency issues. To address this bottleneck, we propose a…

Sampling from pretrained diffusion and flow-matching models typically requires many forward passes to generate diverse and high-fidelity images. Existing distillation methods often rely on multiple auxiliary networks, carefully designed…

This paper introduces DLM-One, a score-distillation-based framework for one-step sequence generation with continuous diffusion language models (DLMs). DLM-One eliminates the need for iterative refinement by aligning the scores of a student…

Score distillation sampling~(SDS) has been widely adopted to overcome the absence of unseen views in reconstructing 3D objects from a \textbf{single} image. It leverages pre-trained 2D diffusion models as teacher to guide the reconstruction…

Diffusion models have demonstrated excellent potential for generating diverse images. However, their performance often suffers from slow generation due to iterative denoising. Knowledge distillation has been recently proposed as a remedy…

Diffusion models have recently achieved remarkable performance in image super-resolution (SR), but their high computational cost limits practical deployment in remote sensing applications. To address this issue, we propose SlimDiffSR, a…

The ultimate goal of Dataset Distillation is to synthesize a small synthetic dataset such that a model trained on this synthetic set will perform equally well as a model trained on the full, real dataset. Until now, no method of Dataset…

Recent hybrid video generation models combine autoregressive temporal dynamics with diffusion-based spatial denoising, but their sequential, iterative nature leads to error accumulation and long inference times. In this work, we propose a…