Related papers: Simplex Autoencoders

Data-driven reduced order modeling of chaotic dynamics can result in systems that either dissipate or diverge catastrophically. Leveraging non-linear dimensionality reduction of autoencoders and the freedom of non-linear operator inference…

By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. Additionally, their formulation allows for a…

Multimodal models have demonstrated powerful capabilities in complex tasks requiring multimodal alignment, including zero-shot classification and cross-modal retrieval. However, existing models typically rely on millions of paired…

Artificial intelligence and machine learning techniques have the promise to revolutionize the field of digital pathology. However, these models demand considerable amounts of data, while the availability of unbiased training data is…

Given the inherent class imbalance issue within student performance datasets, samples belonging to the edges of the target class distribution pose a challenge for predictive machine learning algorithms to learn. In this paper, we introduce…

We present a novel introspective variational autoencoder (IntroVAE) model for synthesizing high-resolution photographic images. IntroVAE is capable of self-evaluating the quality of its generated samples and improving itself accordingly.…

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually…

In few-shot learning, the selection of samples has a significant impact on the performance of the model. While effective sample selection strategies are well-established in supervised settings, research on large language models largely…

Multi-modal systems enhance performance in autonomous driving but face inefficiencies due to indiscriminate processing within each modality. Additionally, the independent feature learning of each modality lacks interaction, which results in…

As machine learning models continue to swiftly advance, calibrating their performance has become a major concern prior to practical and widespread implementation. Most existing calibration methods often negatively impact model accuracy due…

Image synthesis is a core problem in modern deep learning, and many recent architectures such as autoencoders and Generative Adversarial networks produce spectacular results on highly complex data, such as images of faces or landscapes.…

Class imbalance can often degrade predictive performance of supervised learning algorithms. Balanced classes can be obtained by oversampling exact copies, with noise, or interpolation between nearest neighbours (as in traditional SMOTE…

Diffusion models suffer from slow sample generation at inference time. Despite recent efforts, improving the sampling efficiency of stochastic samplers for diffusion models remains a promising direction. We propose Splitting Integrators for…

The heightened realism of AI-generated images can be attributed to the rapid development of synthetic models, including generative adversarial networks (GANs) and diffusion models (DMs). The malevolent use of synthetic images, such as the…

The interest in summarizing complex and multidimensional phenomena often related to one or more specific sectors (social, economic, environmental, political, etc.) to make them easily understandable even to non-experts is far from waning. A…

Medical image segmentation suffers from data scarcity, particularly in polyp detection where annotation requires specialized expertise. We present SynDiff, a framework combining text-guided synthetic data generation with efficient…

Although significant advances have been made in face recognition (FR), FR in unconstrained environments remains challenging due to the domain gap between the semi-constrained training datasets and unconstrained testing scenarios. To address…

Latent diffusion models (LDMs) enable high-fidelity synthesis by operating in learned latent spaces. However, training state-of-the-art LDMs requires complex staging: a tokenizer must be trained first, before the diffusion model can be…

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges…

This paper introduces SynDiffix, a mechanism for generating statistically accurate, anonymous synthetic data for structured data. Recent open source and commercial systems use Generative Adversarial Networks or Transformed Auto Encoders to…