Related papers: Guiding a diffusion model using sliding windows

Global Navigation Satellite Systems (GNSS) are vital for reliable urban positioning. However, multipath and non-line-of-sight reception often introduce large measurement errors that degrade accuracy. Learning-based methods for predicting…

This study aims to construct an audio-video generative model with minimal computational cost by leveraging pre-trained single-modal generative models for audio and video. To achieve this, we propose a novel method that guides single-modal…

With the rapid advances in diffusion models, generating decent images from text prompts is no longer challenging. The key to text-to-image generation is how to optimize the results of a text-to-image generation model so that they can be…

Classifier-free guidance (CFG) is the de facto standard for conditional sampling in diffusion models, yet it often reduces sample diversity. Using tools from statistical physics, we analyze the emergence of generative distortions induced by…

We present Readout Guidance, a method for controlling text-to-image diffusion models with learned signals. Readout Guidance uses readout heads, lightweight networks trained to extract signals from the features of a pre-trained, frozen…

Recent diffusion distillation methods have achieved remarkable progress, enabling high-quality ${\sim}4$-step sampling for large-scale text-conditional image and video diffusion models. However, further reducing the number of sampling steps…

While diffusion models have made remarkable progress in image generation, their outputs can still appear unrealistic and lack fine details, especially when using fewer number of neural function evaluations (NFEs) or lower guidance scales.…

The use of guidance in diffusion models was originally motivated by the premise that the guidance-modified score is that of the data distribution tilted by a conditional likelihood raised to some power. In this work we clarify this…

In recent years, diffusion models have been widely adopted for image inpainting tasks due to their powerful generative capabilities, achieving impressive results. Existing multimodal inpainting methods based on diffusion models often…

Conditional generative models typically demand large annotated training sets to achieve high-quality synthesis. As a result, there has been significant interest in designing models that perform plug-and-play generation, i.e., to use a…

While Classifier-Free Guidance (CFG) has become standard for improving sample fidelity in conditional diffusion models, it can harm diversity and induce memorization by applying constant guidance regardless of whether a particular sample…

Diffusion models are primarily trained for image synthesis, yet their denoising trajectories encode rich, spatially aligned visual priors. In this paper, we demonstrate that these priors can be utilized for text-conditioned semantic and…

Score-based diffusion models have recently been extended to infinite-dimensional function spaces, with uses such as inverse problems arising from partial differential equations. In the Bayesian formulation of inverse problems, the aim is to…

Diffusion models have demonstrated strong generative performance when using guidance methods such as classifier-free guidance (CFG), which enhance output quality by modifying the sampling trajectory. These methods typically improve a target…

Guided or controlled data generation with diffusion models\blfootnote{Partial preliminary results of this work appeared in International Conference on Machine Learning 2025 \citep{li2025provable}.} has become a cornerstone of modern…

Because diffusion models have shown impressive performances in a number of tasks, such as image synthesis, there is a trend in recent works to prove (with certain assumptions) that these models have strong approximation capabilities. In…

Diffusion models have demonstrated exceptional efficacy in various generative applications. While existing models focus on minimizing a weighted sum of denoising score matching losses for data distribution modeling, their training primarily…

To synthesize high-fidelity samples, diffusion models typically require auxiliary data to guide the generation process. However, it is impractical to procure the painstaking patch-level annotation effort required in specialized domains like…

Diffusion models have recently gained prominence in offline reinforcement learning due to their ability to effectively learn high-performing, generalizable policies from static datasets. Diffusion-based planners facilitate long-horizon…

Image compression technology eliminates redundant information to enable efficient transmission and storage of images, serving both machine vision and human visual perception. For years, image coding focused on human perception has been…