Related papers: Dual-End Consistency Model
Time series generation (TSG) is widely used across domains, yet most existing methods assume regular sampling and fixed output resolutions. These assumptions are often violated in practice, where observations are irregular and sparse, while…
Recently, diffusion models (DMs) have made significant strides in high-quality image generation. However, the multi-step denoising process often results in considerable computational overhead, impeding deployment on resource-constrained…
One-step generative modeling has emerged as a leading approach to amortize the inference cost of diffusion and flow-matching models. Among distillation-free methods, MeanFlow training is notoriously unstable, with non-decreasing loss and…
Flow-based image generative models exhibit stable training and produce high quality samples when using multi-step sampling procedures. One-step generative models can produce high quality image samples but can be difficult to optimize as…
Recent advancements in Latent Diffusion Models (LDMs) have propelled them to the forefront of various generative tasks. However, their iterative sampling process poses a significant computational burden, resulting in slow generation speeds…
Video diffusion models have shown great potential in generating high-quality videos, making them an increasingly popular focus. However, their inherent iterative nature leads to substantial computational and time costs. While efforts have…
Aligning diffusion model outputs with downstream objectives is essential for improving task-specific performance. Broadly, inference-time training-free approaches for aligning diffusion models can be categorized into two main strategies:…
Monocular depth estimation within the diffusion-denoising paradigm demonstrates impressive generalization ability but suffers from low inference speed. Recent methods adopt a single-step deterministic paradigm to improve inference…
X-ray computed tomography (CT) is widely used for medical diagnosis and treatment planning; however, concerns about ionizing radiation exposure drive efforts to optimize image quality at lower doses. This study introduces Poisson Flow…
While diffusion distillation has enabled one-step generation through methods like Variational Score Distillation, adapting distilled models to emerging new controls -- such as novel structural constraints or latest user preferences --…
Recent advances in large multi-modal generative models have demonstrated impressive capabilities in multi-modal generation, including image and video generation. These models are typically built upon multi-step frameworks like diffusion and…
Masked Diffusion Models (MDMs) have emerged as a powerful generative modeling technique. Despite their remarkable results, they typically suffer from slow inference with several steps. In this paper, we propose Di$\mathtt{[M]}$O, a novel…
Classifier-free guided diffusion models have recently been shown to be highly effective at high-resolution image generation, and they have been widely used in large-scale diffusion frameworks including DALLE-2, Stable Diffusion and Imagen.…
While diffusion models can learn complex distributions, sampling requires a computationally expensive iterative process. Existing distillation methods enable efficient sampling, but have notable limitations, such as performance degradation…
Generative models, particularly Diffusion Models (DM), have shown strong potential for Computed Tomography (CT) reconstruction serving as expressive priors for solving ill-posed inverse problems. However, diffusion-based reconstruction…
Diffusion-based or flow-based models have achieved significant progress in video synthesis but require multiple iterative sampling steps, which incurs substantial computational overhead. While many distillation methods that are solely based…
Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generation. We argue that the bottleneck is not continuity itself,…
Continuous diffusion is a natural framework for non-autoregressive generation but has generally lagged behind masked discrete diffusion models (MDMs) on discrete sequence generation. We argue that the bottleneck is not continuity itself,…
Consistency models (CMs) learn a consistent mapping from multiple noise levels to the data endpoint and can therefore perform generative inference in one or a few steps. This property makes them attractive as learned priors for low-latency…
Consistency distillation is a prevalent way for accelerating diffusion models adopted in consistency (trajectory) models, in which a student model is trained to traverse backward on the probability flow (PF) ordinary differential equation…