Related papers: CTSyn: A Foundation Model for Cross Tabular Data G…

Recent advances in generative artificial intelligence have enabled the creation of high-quality synthetic data that closely mimics real-world data. This paper explores the adaptation of the Stable Diffusion 2.0 model for generating…

Generative Adversarial Networks (GANs) are typically trained to synthesize data, from images and more recently tabular data, under the assumption of directly accessible training data. Recently, federated learning (FL) is an emerging…

Traditional Differential Privacy (DP) mechanisms are typically tailored to specific analysis tasks, which limits the reusability of protected data. DP tabular data synthesis overcomes this by generating synthetic datasets that can be shared…

The social graphs synthesized by the generative models are increasingly in demand due to data scarcity and concerns over user privacy. One of the key performance criteria for generating social networks is the fidelity to specified…

Deep learning-based food image classification enables precise identification of food categories, further facilitating accurate nutritional analysis. However, real-world food images often show a skewed distribution, with some food types…

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…

Synthetic data generation is an important tool for privacy-preserving data sharing. Although diffusion models have set recent benchmarks, flow matching (FM) offers a promising alternative. This paper presents different ways to implement FM…

Despite the growing importance of dental CBCT scans for diagnosis and treatment planning, generating anatomically realistic scans with fine-grained control remains a challenge in medical image synthesis. In this work, we propose a novel…

3D Gaussian Splatting (3DGS) has shown convincing performance in rendering speed and fidelity, yet the generation of Gaussian Splatting remains a challenge due to its discreteness and unstructured nature. In this work, we propose DiffGS, a…

Most tabular-data generators match marginal statistics yet ignore causal structure, leading downstream models to learn spurious or unfair patterns. We present TabSCM, a mixed-type generator that preserves those causal dependencies. Starting…

Diffusion models are instrumental in text-to-audio (TTA) generation. Unfortunately, they suffer from slow inference due to an excessive number of queries to the underlying denoising network per generation. To address this bottleneck, we…

Imbalanced datasets pose a difficulty in fraud detection, as classifiers are often biased toward the majority class and perform poorly on rare fraudulent transactions. Synthetic data generation is therefore commonly used to mitigate this…

The generation of high-quality, long-sequenced time-series data is essential due to its wide range of applications. In the past, standalone Recurrent and Convolutional Neural Network-based Generative Adversarial Networks (GAN) were used to…

Recent advances in generative modeling, namely Diffusion models, have revolutionized generative modeling, enabling high-quality image generation tailored to user needs. This paper proposes a framework for the generative design of structural…

In the era of big data, access to abundant data is crucial for driving research forward. However, such data is often inaccessible due to privacy concerns or high costs, particularly in healthcare domain. Generating synthetic (tabular) data…

Although remarkable progress has been made in image style transfer, style is just one of the components of artistic paintings. Directly transferring extracted style features to natural images often results in outputs with obvious synthetic…

Transformer-based deep neural networks have achieved remarkable success across various computer vision tasks, largely attributed to their long-range self-attention mechanism and scalability. However, most transformer architectures embed…

Tree ensembles such as XGBoost are often preferred for discriminative tasks in mixed-type tabular data, due to their inductive biases, minimal hyperparameter tuning, and training efficiency. We argue that these qualities, when leveraged…

Synthesizing consistent and photorealistic 3D scenes is an open problem in computer vision. Video diffusion models generate impressive videos but cannot directly synthesize 3D representations, i.e., lack 3D consistency in the generated…

The synthesis of crystalline materials, such as zeolites, remains a significant challenge due to a high-dimensional synthesis space, intricate structure-synthesis relationships and time-consuming experiments. Considering the one-to-many…