GitHub

Data Mining Lab 2020: The Variational Fair Autoencoder

This repository contains a pytorch (+ pytorch_lightning) implementation of the Variational Fair Autoencoder (VFAE) as proposed in "The Variational Fair Autoencoder". The code was written in order to ...
IEEE

VG-Net: Sensor Time Series Anomaly Detection with Joint Variational Autoencoder and Graph ...

Abstract: Intelligent Cyber-Physical Systems typically utilize sensors to gather a significant amount of raw data which often possesses temporal and high-dimensional characteristics. Ensuring the data ...
IEEE

Complex-Valued Variational Autoencoders for Radar Detection in Joint Compound Gaussian ...

Abstract: This paper introduces a novel Complex Variational AutoEncoder architecture leveraging complex-valued representations with a single latent channel for radar target detection. Unlike ...
Tech Xplore

Ferroelectric memory enables one chip to sample randomness and compute for generative AI

For the first time, a research team has demonstrated an artificial intelligence semiconductor technology that integrates the ...
Electronics For You

Ferroelectric Memory Powers AI Chips

Researchers have demonstrated a ferroelectric memory chip that performs both random sampling and AI computation, paving the ...

CVPR 2026 最佳学生论文奖！微软&清华等提出TRELLIS.2：原生3D大模型新 ...

这篇CVPR 2026 最佳学生论文，来自清华大学、微软研究院、中国科学技术大学和微软 AI 的研究团队。他们推出了新一代原生 3D 生成大模型——TRELLIS.2。该研究直接从原生 3D 数据中学习一种结构化隐式表征，不仅能还原极其精细的几何与物理材质细节，重要的是将 3D 资产的生成效率也提升到了新的高度。
生物通

将独特数字图像作为临床试验激励物：面向有意义参与的数字转型

临床试验中的受试者在参与过程中的激励（Incentivization）一直具有挑战性，尽管采用传统补偿策略，许多研究仍无法达到招募或留存目标。随着数字健康（Digital Health）的发展，新的方法可望更有意义地吸引受试者参与。研究人员提出将独特数字图像（ 临床试验中的受试者在参与过程中的激励（Incentivization）一直具有挑战性，尽管采用传统补偿策略，许多研究仍无法达到招募或留存目 ...
生物通

AI增强计算机辅助设计：建模操作的预测建模

该研究提出一种基于图的CAD辅助方法，可在参数化设计序列中预测下一个建模操作。研究人员将来自汽车领域的真实CATIA V5模型转换为有向无环图（Directed Acyclic Graph，DAG）以捕获特征依赖关系，从而实现直接从结构设计数据中学习。所采用的 该研究提出一种基于图的CAD辅助方法，可在参数化设计序列中预测下一个建模操作。研究人员将来自汽车领域的真实CATIA V5模型转换为有向无 ...