Related papers: Stochastic Transition-Map Distillation for Fast Pr…
Fine-grained air pollution forecasting is crucial for urban management and the development of healthy buildings. Deploying portable sensors on mobile platforms such as cars and buses offers a low-cost, easy-to-maintain, and wide-coverage…
Sparse neural systems are gaining traction for efficient continual learning due to their modularity and low interference. Architectures such as Sparse Distributed Memory Multi-Layer Perceptrons (SDMLP) construct task-specific subnetworks…
Recent years have witnessed the remarkable success of deep learning in remote sensing image interpretation, driven by the availability of large-scale benchmark datasets. However, this reliance on massive training data also brings two major…
Diffusion models have seen rapid adoption in robotic imitation learning, enabling autonomous execution of complex dexterous tasks. However, action synthesis is often slow, requiring many steps of iterative denoising, limiting the extent to…
Diffusion models have emerged as a powerful tool for generating high-quality images, videos, and 3D content. While sampling guidance techniques like CFG improve quality, they reduce diversity and motion. Autoguidance mitigates these issues…
In applications of diffusion models, controllable generation is of practical significance, but is also challenging. Current methods for controllable generation primarily focus on modifying the score function of diffusion models, while Mean…
Diffusion models represent a powerful family of generative models widely used for image and video generation. However, the time-consuming deployment, long inference time, and requirements on large memory hinder their applications on…
Dataset Distillation (DD) aims to generate a compact synthetic dataset that enables models to achieve performance comparable to training on the full large dataset, significantly reducing computational costs. Drawing from optimal transport…
Diffusion distillation provides an effective approach for learning lightweight and few-steps diffusion models with efficient generation. However, evaluating their generalization remains challenging: theoretical metrics are often impractical…
We introduce Posterior Distillation Sampling (PDS), a novel optimization method for parametric image editing based on diffusion models. Existing optimization-based methods, which leverage the powerful 2D prior of diffusion models to handle…
The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive…
Diffusion models have shown strong performance in speech enhancement, but their real-time applicability has been limited by multi-step iterative sampling. Consistency distillation has recently emerged as a promising alternative by…
Speculative decoding (SD) accelerates large language model inference by employing a faster draft model for generating multiple tokens, which are then verified in parallel by the larger target model, resulting in the text generated according…
Diffusion models have recently emerged as powerful tools for missing data imputation by modeling the joint distribution of observed and unobserved variables. However, existing methods, typically based on stochastic denoising diffusion…
Diffusion models have shown tremendous results in image generation. However, due to the iterative nature of the diffusion process and its reliance on classifier-free guidance, inference times are slow. In this paper, we propose a new…
We provide new convergence guarantees in Wasserstein distance for diffusion-based generative models, covering both stochastic (DDPM-like) and deterministic (DDIM-like) sampling methods. We introduce a simple framework to analyze…
Sampling from diffusion models involves a slow iterative process that hinders their practical deployment, especially for interactive applications. To accelerate generation speed, recent approaches distill a multi-step diffusion model into a…
Accelerating the sampling speed of diffusion models remains a significant challenge. Recent score distillation methods distill a heavy teacher model into a student generator to achieve one-step generation, which is optimized by calculating…
Image enhancement finds wide-ranging applications in real-world scenarios due to complex environments and the inherent limitations of imaging devices. Recent diffusion-based methods yield promising outcomes but necessitate prolonged and…
Online HD map construction is a fundamental task in autonomous driving systems, aiming to acquire semantic information of map elements around the ego vehicle based on real-time sensor inputs. Recently, several approaches have achieved…