IEEE

MSTG-Transformer: Multivariate Spatial-Temporal Gated Transformer Model for 3D Skeleton Data-based Fall Risk Prediction

Abstract: As the aging population continues to grow, falls among older adults have become a significant public health concern worldwide. Data-driven approaches for effective fall risk prediction, ...
GitHub

VGGT: Visual Geometry Grounded Transformer

[July 6, 2025] Training code is now available in the training folder, including an example to finetune VGGT on a custom dataset. [June 13, 2025] Honored to receive the Best Paper Award at CVPR 2025!
IEEE

TAFF-YOLO: An Enhanced YOLO Model With Transformer and Attention Feature Fusion for Chip Internal Defect Detection

Abstract: Accurate and efficient detection of internal defects in chips is crucial for ensuring the reliability and yield of electronic products. However, conventional object detection models often ...
TweakTown

DLSS 4 research paper offers a detailed look at the new transformer model and Multi Frame Gen

TL;DR: NVIDIA's DLSS 4, launched with the GeForce RTX 50 Series, enhances image quality and performance with its new transformer-based models. It also introduces Multi Frame Generation, generating up ...
New Atlas

Paper-Kit transforms 2D portraits into a 3D model

Papercraft projects tend to be based on 3D models from video games or custom-made art projects. The basic idea is to take a 3D model and flatten it out in software such as Dunreeb Cutout or Pepakura ...