GitHub

A novel generative model with simple principles and unique properties

We introduce a novel generative model: Discrete Distribution Networks (DDN). DDN employs a simple yet unique approach to model the target distribution, distinctly different from mainstream generative ...
GitHub

Semantically Consistent Discrete Diffusion for 3D Biological Graph Generation

This repository contains the official code for our MICCAI 2025 paper, “Semantically Consistent Discrete Diffusion for 3D Biological Graph Generation.” We introduce a discrete diffusion framework that ...
IEEE

Gen-GraphEx: Generative In-Distribution Graph Explanations for Time-Efficient Model-Level ...

Abstract: Graph neural networks (GNNs) have become the prevailing methodology for addressing graph data-related tasks, permeating critical domains like recommendation systems and drug development. The ...
IEEE

Posture-Movement-Frequency-Enhanced Graph Convolutional Network for Gait Emotion Recognition

Abstract: Recent progress in recognizing emotions through gait analysis has attracted substantial interest. Spatial temporal graph convolutional networks (ST-GCN) have been applied to extract gait ...
Frontiers

Frequency-aligned loss and spectral filtering improve long-range influenza forecasting

1 Department of Rehabilitation, West China Hospital Sichuan University Jintang Hospital, Jintang First People's Hospital, Chengdu, China 2 Jilin Institute of Physical ...
Nature

Genetics and the understanding of selection

Genetics is important to our understanding of selection for at least three reasons: first, although the concept of selection seems obvious, it was not until selection was linked to Mendelian genetics ...