About
Research & Development
Advanced AI Model Achieves Over 99% Accuracy in Deepfake Image Detection
TLDR: This research introduces a robust Deepfake detection model based on a modified Vision Transformer (ViT). Trained on the OpenForensics Dataset with extensive data...
Research & Development
Enhancing LLM Accuracy with ReFactX: A Scalable Approach to Fact-Grounded Generation
TLDR: ReFactX is a new method that allows Large Language Models (LLMs) to access external knowledge from massive databases (up to 800 million facts)...
Research & Development
EDLDNet: Achieving High Accuracy and Efficiency in Multi-Organ Medical Image Segmentation
TLDR: EDLDNet is a new deep learning model for medical image segmentation that uses an efficient dual-line decoder network with multi-scale convolutional attention. It...
Research & Development
Unlocking Deeper Insights: TabResFlow for Flexible Tabular Regression
TLDR: TabResFlow is a new machine learning model designed for probabilistic univariate tabular regression. It moves beyond single-value predictions by modeling full probability distributions,...
Research & Development
FPGA Acceleration Unlocks Energy Efficiency for Adaptive Neural Networks
TLDR: Kolmogorov-Arnold Networks (KANs) offer high accuracy and interpretability but pose significant computational challenges for energy-constrained edge AI devices. This research introduces an innovative...
Research & Development
GraphFNP: A Unified Approach for Trustworthy and Explainable Graph Neural Networks
TLDR: GraphFNP is a novel model that significantly enhances Graph Neural Networks (GNNs) by simultaneously improving uncertainty quantification and interpretability. It achieves this by...