Related papers: White-Box Diffusion Transformer for single-cell RN…

In this study, we develop a Diffusion Transformer (referred as to DiT1D) for synthesizing realistic earthquake time histories. The DiT1D generates realistic broadband accelerograms (0-30 Hz resolution), constrained at low frequency by…

Time-series single-cell RNA-sequencing (scRNA-seq) datasets offer unprecedented insights into the dynamics and heterogeneity of cellular systems. These systems exhibit multiscale collective behaviors driven by intricate intracellular gene…

Deep neural networks (DNNs) are susceptible to adversarial examples, which introduce imperceptible perturbations to benign samples, deceiving DNN predictions. While some attack methods excel in the white-box setting, they often struggle in…

Single-nucleus RNA sequencing (snRNA-seq) has significantly advanced our understanding of the disease etiology of neurodegenerative disorders. However, the low quality of specimens derived from postmortem brain tissues, combined with the…

Diffusion Transformers (DiTs) have emerged as a highly scalable and effective backbone for image generation, outperforming U-Net architectures in both scalability and performance. However, their real-world deployment remains challenging due…

Class imbalance is a persistent challenge in visual recognition, particularly in safety-critical domains where collecting positive examples is expensive and rare events are inherently underrepresented. We propose a lightweight synthetic…

Data augmentation (DA) can significantly strengthen the electroencephalogram (EEG)-based seizure prediction methods. However, existing DA approaches are just the linear transformations of original data and cannot explore the feature space…

While many unsupervised learning models focus on one family of tasks, either generative or discriminative, we explore the possibility of a unified representation learner: a model which uses a single pre-training stage to address both…

Recently, the application of deep learning to change detection (CD) has significantly progressed in remote sensing images. In recent years, CD tasks have mostly used architectures such as CNN and Transformer to identify these changes.…

This paper introduces a methodology for generating synthetic annotated data to address data scarcity in semantic segmentation tasks within the precision agriculture domain. Utilizing Denoising Diffusion Probabilistic Models (DDPMs) and…

Image fusion aims to blend complementary information from multiple sensing modalities, yet existing approaches remain limited in robustness, adaptability, and controllability. Most current fusion networks are tailored to specific tasks and…

Synthetic tabular data is crucial for sharing and augmenting data across silos, especially for enterprises with proprietary data. However, existing synthesizers are designed for centrally stored data. Hence, they struggle with real-world…

Many real-world datasets, such as citation networks, social networks, and molecular structures, are naturally represented as heterogeneous graphs, where nodes belong to different types and have additional features. For example, in a…

Discrete diffusion models enable parallel token sampling for faster inference than autoregressive approaches. However, prior diffusion models use a decoder-only architecture, which requires sampling algorithms that invoke the full network…

Multimodal medical images play a crucial role in the precise and comprehensive clinical diagnosis. Diffusion model is a powerful strategy to synthesize the required medical images. However, existing approaches still suffer from the problem…

With the rapid development of various sensing devices, spatiotemporal data is becoming increasingly important nowadays. However, due to sensing costs and privacy concerns, the collected data is often incomplete and coarse-grained, limiting…

Diffusion models have significantly advanced the field of generative modeling. However, training a diffusion model is computationally expensive, creating a pressing need to adapt off-the-shelf diffusion models for downstream generation…

Recently, ultra high-throughput sequencing of RNA (RNA-Seq) has been developed as an approach for analysis of gene expression. By obtaining tens or even hundreds of millions of reads of transcribed sequences, an RNA-Seq experiment can offer…

In recent years, diffusion models have emerged as a superior alternative to generative adversarial networks (GANs) for high-fidelity image generation, with wide applications in text-to-image generation, image-to-image translation, and…

Unsupervised representation learning, particularly sequential disentanglement, aims to separate static and dynamic factors of variation in data without relying on labels. This remains a challenging problem, as existing approaches based on…