Related papers: Large Scale Diffusion Distillation via Score-Regul…

Image super-resolution (SR) has attracted increasing attention due to its wide applications. However, current SR methods generally suffer from over-smoothing and artifacts, and most work only with fixed magnifications. This paper introduces…

Diffusion models can synthesize realistic co-speech video from audio for various applications, such as video creation and virtual agents. However, existing diffusion-based methods are slow due to numerous denoising steps and costly…

The Stable Diffusion Model (SDM) is a popular and efficient text-to-image (t2i) generation and image-to-image (i2i) generation model. Although there have been some attempts to reduce sampling steps, model distillation, and network…

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…

Vision-language models (VLMs) could power real-time assistants and autonomous agents, but they face a critical challenge: understanding near-infinite video streams without escalating latency and memory usage. Processing entire videos with…

Diffusion- and flow-based models have emerged as state-of-the-art generative modeling approaches, but they require many sampling steps. Consistency models can distill these models into efficient one-step generators; however, unlike flow-…

Text-to-image generation via Stable Diffusion models (SDM) have demonstrated remarkable capabilities. However, their computational intensity, particularly in the iterative denoising process, hinders real-time deployment in latency-sensitive…

With the advance of diffusion models, today's video generation has achieved impressive quality. To extend the generation length and facilitate real-world applications, a majority of video diffusion models (VDMs) generate videos in an…

Dataset distillation provides an effective approach to reduce memory and computational costs by optimizing a compact dataset that achieves performance comparable to the full original. However, for large-scale datasets and complex deep…

The recent development of deep learning large models in medicine shows remarkable performance in medical image analysis and diagnosis, but their large number of parameters causes memory and inference latency challenges. Knowledge…

Score-based diffusion models provide a powerful way to model images using the gradient of the data distribution. Leveraging the learned score function as a prior, here we introduce a way to sample data from a conditional distribution given…

Diffusion models (DMs) are a class of generative models that allow sampling from a distribution learned over a training set. When applied to solving inverse problems, the reverse sampling steps are modified to approximately sample from a…

While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains challenging, particularly in maintaining multi-view consistency. Classical approaches…

Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis…

There is a rapidly growing interest in controlling consistency across multiple generated images using diffusion models. Among various methods, recent works have found that simply manipulating attention modules by concatenating features from…

Distilling pre-trained 2D diffusion models into 3D assets has driven remarkable advances in text-to-3D synthesis. However, existing methods typically rely on Score Distillation Sampling (SDS) loss, which involves asymmetric KL divergence--a…

The intensive computational burden of Stable Diffusion (SD) for text-to-image generation poses a significant hurdle for its practical application. To tackle this challenge, recent research focuses on methods to reduce sampling steps, such…

Reinforcement learning (RL) has improved guided image generation with diffusion models by directly optimizing rewards that capture image quality, aesthetics, and instruction following capabilities. However, the resulting generative policies…

Sequential Monte Carlo (SMC) samplers for reward-guided diffusion models often suffer from rapid lineage collapse: a few high-reward particles dominate the population within a handful of resampling steps, destroying diversity and degrading…

Autoregressive models (ARMs) are hindered by slow sequential inference. While masked diffusion models (MDMs) offer a parallel alternative, they suffer from critical drawbacks: high computational overhead from precluding Key-Value (KV)…