Related papers: LACON: Training Text-to-Image Model from Uncurated…

For many computer vision problems, the deep neural networks are trained and validated based on the assumption that the input images are pristine (i.e., artifact-free). However, digital images are subject to a wide range of distortions in…

Deep learning algorithms have a large number of trainable parameters often with sizes of hundreds of thousands or more. Training this algorithm requires a large amount of training data and generating a sufficiently large dataset for these…

Current unlearning methods for large language models usually rely on reverse optimization to reduce target token probabilities. However, this paradigm disrupts the subsequent tokens prediction, degrading model performance and linguistic…

Deep generative models are known to produce undesirable samples such as harmful content. Traditional mitigation methods include re-training from scratch, filtering, or editing; however, these are either computationally expensive or can be…

Recent advances in text-to-image generative models provide the ability to generate high-quality images from short text descriptions. These foundation models, when pre-trained on billion-scale datasets, are effective for various downstream…

Transforming unstructured text into structured data is a complex task, requiring semantic understanding, reasoning, and structural comprehension. While Large Language Models (LLMs) offer potential, they often struggle with handling…

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…

Text-to-image diffusion models allow seamless generation of personalized images from scant reference photos. Yet, these tools, in the wrong hands, can fabricate misleading or harmful content, endangering individuals. To address this…

Improving data quality in unstructured documents is a long-standing challenge. Unstructured data, especially in textual form, inherently lacks defined semantics, which poses significant challenges for effective processing and for ensuring…

Recent text-to-image diffusion models are able to learn and synthesize images containing novel, personalized concepts (e.g., their own pets or specific items) with just a few examples for training. This paper tackles two interconnected…

Text-to-video generation has demonstrated promising progress with the advent of diffusion models, yet existing approaches are limited by dataset quality and computational resources. To address these limitations, this paper presents a…

Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling what to say and in what order. In this work, we present a neural…

Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent…

Generative adversarial networks (GANs) offer an effective solution to the image-to-image translation problem, thereby allowing for new possibilities in medical imaging. They can translate images from one imaging modality to another at a low…

Likelihood training and maximization-based decoding result in dull and repetitive generated texts even when using powerful language models (Holtzman et al., 2019). Adding a loss function for regularization was shown to improve text…

The deep neural networks used in modern computer vision systems require enormous image datasets to train them. These carefully-curated datasets typically have a million or more images, across a thousand or more distinct categories. The…

Concept erasure techniques have recently gained significant attention for their potential to remove unwanted concepts from text-to-image models. While these methods often demonstrate promising results in controlled settings, their…

Recently, methods based on deep learning have dominated the field of text recognition. With a large number of training data, most of them can achieve the state-of-the-art performances. However, it is hard to harvest and label sufficient…

Subject-driven text-to-image generation still struggles to preserve high-frequency identity details such as logos, patterns, and text. Existing methods typically operate directly in RGB space, which often leads to detail degradation under…

Deep generative models are becoming a cornerstone of modern machine learning. Recent work on conditional generative adversarial networks has shown that learning complex, high-dimensional distributions over natural images is within reach.…