GitHub

ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

ARDY is an autoregressive diffusion model designed for interactive motion generation, supporting online text prompting and flexible long-horizon kinematic constraints (root paths/waypoints, full-body ...
GitHub

UniVidX Intrinsic & Alpha Decomposition for ComfyUI

This is a 14-billion-parameter video diffusion model running locally. It is not lightweight. Verify your system can handle it before installing. Validated configuration (all benchmarks in this README) ...
Cancer Research

AAnet Resolves a Continuum of Spatially Localized Cell States to Unveil Intratumoral Heterogeneity

1Computational Biology and Bioinformatics Program, Yale University, New Haven, Connecticut. 6Department of Computer Science, Yale University, New Haven, Connecticut. 12Department of Internal Medicine, ...
Scientific Research Publishing

From U-Net to Swin-Unet Transformers: The Next-Generation Advances in Brain Tumor Segmentation with Deep Learning ()

Brain tumor segmentation is a vital step in diagnosis, treatment planning, and prognosis in neuro-oncology. In recent years, deep learning approaches have revolutionized this field, evolving from the ...
IEEE

Reconstruction of Image using Swin Transformer Encoder and Convolutional Neural Network Decoder

Abstract: In recent years, reconstruction of image has crucially advanced because of Deep Learning (DL) and AI-driven techniques. Traditional methods such as Fourier transform is replaced by Neural ...
C&EN

AI Approaches to Homogeneous Catalysis with Transition Metal Complexes

Hylleraas Centre for Quantum Molecular Sciences, Department of Chemistry, University of Oslo, P.O. Box 1033, Blindern, 0315 Oslo, Norway Centre for Materials Science and Nanotechnology, Department of ...