相关论文: Rethinking Oversaturation in Classifier-Free Guida…

AIGC has shown remarkable success in CV and NLP, and has recently demonstrated promising potential in the wireless domain. However, significant data imbalance exists across RF modalities, with abundant WiFi data but scarce mmWave and RFID…

Knowledge distillation is commonly employed to compress neural networks, reducing the inference costs and memory footprint. In the scenario of homogenous architecture, feature-based methods have been widely validated for their…

Classifier guidance -- using the gradients of an image classifier to steer the generations of a diffusion model -- has the potential to dramatically expand the creative control over image generation and editing. However, currently…

This study addresses the challenge of, without training or fine-tuning, controlling the global color aspect of images generated with a diffusion model. We rewrite the guidance equations to ensure that the outputs are closer to a known color…

Flow matching has demonstrated strong generative capabilities and has become a core component in modern Text-to-Speech (TTS) systems. To ensure high-quality speech synthesis, Classifier-Free Guidance (CFG) is widely used during the…

Diffusion models are proficient at generating high-quality images. They are however effective only when operating at the resolution used during training. Inference at a scaled resolution leads to repetitive patterns and structural…

Diffusion models are a powerful class of generative models capable of producing high-quality images from pure noise using a simple text prompt. While most methods which introduce additional spatial constraints into the generated images…

Guidance is a cornerstone of modern diffusion models, playing a pivotal role in conditional generation and enhancing the quality of unconditional samples. However, current approaches to guidance scheduling--determining the appropriate…

Conditional diffusion models have shown remarkable success in visual content generation, producing high-quality samples across various domains, largely due to classifier-free guidance (CFG). Recent attempts to extend guidance to…

While diffusion-based models have shown remarkable generative capabilities in static settings, their extension to continual learning (CL) scenarios remains fundamentally constrained by Generative Catastrophic Forgetting (GCF). We observe…

We introduce the Latent Fourier Transform (LatentFT), a framework that provides novel frequency-domain controls for generative music models. LatentFT combines a diffusion autoencoder with a latent-space Fourier transform to separate musical…

The application of diffusion transformers is suffering from their significant inference costs. Recently, feature caching has been proposed to solve this problem by reusing features from previous timesteps, thereby skipping computation in…

While classifier-free guidance (CFG) is essential for conditional diffusion models, it doubles the number of neural function evaluations (NFEs) per inference step. To mitigate this inefficiency, we introduce adapter guidance distillation…

Generative models are transforming creative domains such as music generation, with inference-time strategies like Classifier-Free Guidance (CFG) playing a crucial role. However, CFG doubles inference cost while limiting originality and…

Inference-time guided sampling steers state-of-the-art diffusion and flow models without fine-tuning by interpreting the generation process as a controllable trajectory. This provides a simple and flexible way to inject external constraints…

Denoising diffusion models (DDMs) have attracted attention for their exceptional generation quality and diversity. This success is largely attributed to the use of class- or text-conditional diffusion guidance methods, such as classifier…

Load frequency control (LFC) is widely employed in power systems to stabilize frequency fluctuation and guarantee power quality. However, most existing LFC methods rely on accurate power system modeling and usually ignore the nonlinear…

Text-to-image diffusion models have achieved remarkable performance in image synthesis, while the text interface does not always provide fine-grained control over certain image factors. For instance, changing a single token in the text can…

While diffusion-based generative models have made significant strides in visual content creation, conventional approaches face computational challenges, especially for high-resolution images, as they denoise the entire image from noisy…

Stochastic reduced-order models are widely used to represent the effective dynamics of complex systems, but estimating their drift and diffusion coefficients from data remains challenging. Standard approaches often rely on short-time…