相关论文: Slight Corruption in Pre-training Data Makes Bette…

Recent advances in text-to-image diffusion models have enabled the generation of diverse and high-quality images. While impressive, the images often fall short of depicting subtle details and are susceptible to errors due to ambiguity in…

Mixup~\cite{zhang2017mixup} is a recently proposed method for training deep neural networks where additional samples are generated during training by convexly combining random pairs of images and their associated labels. While simple to…

Algorithmic robust statistics has traditionally focused on the contamination model where a small fraction of the samples are arbitrarily corrupted. We consider a recent contamination model that combines two kinds of corruptions: (i) small…

We present Diffusion Model Patching (DMP), a simple method to boost the performance of pre-trained diffusion models that have already reached convergence, with a negligible increase in parameters. DMP inserts a small, learnable set of…

Diffusion Models enable realistic image generation, raising the risk of misinformation and eroding public trust. Currently, detecting images generated by unseen diffusion models remains challenging due to the limited generalization…

There is a bias in the inference pipeline of most diffusion models. This bias arises from a signal leak whose distribution deviates from the noise distribution, creating a discrepancy between training and inference processes. We demonstrate…

Code datasets, often collected from diverse and uncontrolled sources such as GitHub, potentially suffer from quality issues, thereby affecting the performance and training efficiency of Large Language Models (LLMs) optimized for code…

As latent diffusion models (LDMs) democratize image generation capabilities, there is a growing need to detect fake images. A good detector should focus on the generative models fingerprints while ignoring image properties such as semantic…

Diffusion models recently proved to be remarkable priors for Bayesian inverse problems. However, training these models typically requires access to large amounts of clean data, which could prove difficult in some settings. In this work, we…

Diffusion Models (DMs) have disrupted the image Super-Resolution (SR) field and further closed the gap between image quality and human perceptual preferences. They are easy to train and can produce very high-quality samples that exceed the…

Conditional diffusion models have gained increasing attention since their impressive results for cross-modal synthesis, where the strong alignment between conditioning input and generated output can be achieved by training a…

A key inefficiency in diffusion training occurs when a randomly initialized network, lacking visual priors, encounters gradients from the full complexity spectrum--most of which it lacks the capacity to resolve. We propose Data Warmup, a…

Large volumes of text data have contributed significantly to the development of large language models (LLMs) in recent years. This data is typically acquired by scraping the internet, leading to pretraining datasets comprised of noisy web…

Diffusion models are a new class of generative models that have shown outstanding performance in image generation literature. As a consequence, studies have attempted to apply diffusion models to other tasks, such as speech enhancement. A…

The recently introduced Consistency models pose an efficient alternative to diffusion algorithms, enabling rapid and good quality image synthesis. These methods overcome the slowness of diffusion models by directly mapping noise to data,…

Foundation models are usually pre-trained on large-scale datasets and then adapted to downstream tasks through tuning. However, the large-scale pre-training datasets, often inaccessible or too expensive to handle, can contain label noise…

Diffusion models have achieved remarkable success in generating high quality image and video data. More recently, they have also been used for image compression with high perceptual quality. In this paper, we present a novel approach to…

Conditional diffusion models have made impressive progress in the field of image processing, but the characteristics of constructing data distribution pathways make it difficult to exploit the intrinsic correlation between tasks in…

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…

Diffusion models (DMs) excel in unconditional generation, as well as on applications such as image editing and restoration. The success of DMs lies in the iterative nature of diffusion: diffusion breaks down the complex process of mapping…