Related papers: Slight Corruption in Pre-training Data Makes Bette…

Latent diffusion models (LDMs) have made significant advancements in the field of image generation in recent years. One major advantage of LDMs is their ability to operate in a compressed latent space, allowing for more efficient training…

Visual Instruction Tuning (VIT) aims to enhance Multimodal Large Language Models (MLLMs), yet its effectiveness is often compromised by corrupted datasets with issues such as hallucinated content, incorrect responses, and poor OCR quality.…

Conventional class-guided diffusion models generally succeed in generating images with correct semantic content, but often struggle with texture details. This limitation stems from the usage of class priors, which only provide coarse and…

We argue that diffusion models' success in modeling complex distributions is, for the most part, coming from their input conditioning. This paper investigates the representation used to condition diffusion models from the perspective that…

The rapid advancement of multimodal large language models (MLLMs) has significantly enhanced performance across benchmarks. However, data contamination-unintentional memorization of benchmark data during model training-poses critical…

DNNs trained on natural clean samples have been shown to perform poorly on corrupted samples, such as noisy or blurry images. Various data augmentation methods have been recently proposed to improve DNN's robustness against common…

Diffusion models learn to denoise data and the trained denoiser is then used to generate new samples from the data distribution. In this paper, we revisit the diffusion sampling process and identify a fundamental cause of sample quality…

Diffusion Probabilistic Models (DPMs) are powerful generative models that have achieved unparalleled success in a number of generative tasks. In this work, we aim to build inductive biases into the training and sampling of diffusion models…

Image diffusion distillation achieves high-fidelity generation with very few sampling steps. However, applying these techniques directly to video diffusion often results in unsatisfactory frame quality due to the limited visual quality in…

Large-scale brain imaging datasets provide unprecedented opportunities for developing domain foundation models through pretraining. However, unlike natural image datasets in computer vision, these neuroimaging data often exhibit high…

The field of image generation has made significant progress thanks to the introduction of Diffusion Models, which learn to progressively reverse a given image corruption. Recently, a few studies introduced alternative ways of corrupting…

Diffusion models have shown remarkable capabilities in generating high quality and creative images conditioned on text. An interesting application of such models is structure preserving text guided image editing. Existing approaches rely on…

Corruptions due to data perturbations and label noise are prevalent in the datasets from unreliable sources, which poses significant threats to model training. Despite existing efforts in developing robust models, current learning methods…

Diffusion models generate high-quality images through progressive denoising but are computationally intensive due to large model sizes and repeated sampling. Knowledge distillation, which transfers knowledge from a complex teacher to a…

Conventional techniques to establish dense correspondences across visually or semantically similar images focused on designing a task-specific matching prior, which is difficult to model. To overcome this, recent learning-based methods have…

The state-of-the-art deep neural networks are vulnerable to common corruptions (e.g., input data degradations, distortions, and disturbances caused by weather changes, system error, and processing). While much progress has been made in…

Training with mixed data distributions is a common and important part of creating multi-task and instruction-following models. The diversity of the data distributions and cost of joint training makes the optimization procedure extremely…

Though the background is an important signal for image classification, over reliance on it can lead to incorrect predictions when spurious correlations between foreground and background are broken at test time. Training on a dataset where…

This paper studies the training-testing discrepancy (a.k.a. exposure bias) problem for improving the diffusion models. During training, the input of a prediction network at one training timestep is the corresponding ground-truth noisy data…

Though diffusion-based video generation has witnessed rapid progress, the inference results of existing models still exhibit unsatisfactory temporal consistency and unnatural dynamics. In this paper, we delve deep into the noise…