About
Research & Development
SPICEAssistant: Empowering LLMs for Switched-Mode Power Supply Design
TLDR: SPICEAssistant is a new framework that enhances large language models (LLMs) like GPT-4o for designing switched-mode power supplies (SMPS). It addresses LLM limitations...
Research & Development
AI-Powered Speech Recognition Boosts SENĆOŦEN Language Revitalization
TLDR: A new research paper introduces an AI-driven pipeline to support the documentation of SENĆOŦEN, an endangered Indigenous language. Facing challenges like limited data...
Research & Development
New Offline Reinforcement Learning Method Uses Optimal Transport Maps for Stable Policy Learning
TLDR: A new research paper introduces Q-DOT, an offline reinforcement learning method that uses Wasserstein distance for regularization without adversarial training. By employing Input-Convex...
Research & Development
Winsor-CAM: Enhancing AI Transparency with Tunable Visual Explanations
TLDR: Winsor-CAM is a novel method that improves visual explanations for deep learning models by aggregating saliency information from all convolutional layers of a...
Research & Development
Boosting Phishing Detection: Introducing the PhreshPhish Dataset and Benchmarks
TLDR: PhreshPhish is a new, large, high-quality dataset of phishing and benign websites designed to improve machine learning-based phishing detection. It addresses common issues...
Research & Development
Boosting Accuracy in Colorectal Polyp Detection with LOF-YOLOv11n
TLDR: A new AI framework, LOF-YOLOv11n, significantly improves real-time colorectal polyp detection. It combines the Local Outlier Factor (LOF) algorithm to clean noisy training...