GitHub

SVG-T2I: Scaling up Text-to-Image Latent Diffusion Model

Important Note: This repository implements SVG-T2I, a text-to-image diffusion framework that performs visual generation directly in Visual Foundation Model (VFM) representation space, rather than ...
GitHub

Quantized Visual Geometry Grounded Transformer

First, clone this repository to your local machine, and install the dependencies (torch, torchvision, numpy, Pillow, and huggingface_hub). git clone [email protected] ...
IEEE

Data Generation for State-of-Health Estimation of Retired Batteries: Exploration of Conditional Vector Quantized Variational Autoencoder

Abstract: Accurate and rapid state-of-health (SOH) estimation of retired lithium-ion batteries is critical for sustainable recycling and second-life applications. However, data-driven methods face ...
IEEE

Spatially-Aware Vision Transformer with Learnable Axial Attention

Abstract: Long-range dependencies can be modelled by the current Vision Transformer (ViT) models for picture reconstruction, but they are computationally costly and have poor spatial interpretability.