About
Research & Development
A Control Theory Approach to Ensuring Safe Language Model Outputs
TLDR: The paper introduces CBF-LLM, a novel control-based framework for aligning large language models (LLMs) to generate user-desirable text. It utilizes a Control Barrier...
Research & Development
AI System Enhances Post-Disaster Building Damage Assessment Using Drone Imagery
TLDR: This paper introduces the first AI/ML system for automatically assessing building damage from drone (sUAS) imagery that has been deployed in real-world federally...
Research & Development
GraphCliff: A New Approach to Unraveling Molecular Activity Cliffs with Graph Neural Networks
TLDR: GraphCliff is a novel graph neural network architecture designed to address the limitations of existing GNNs in predicting molecular activity cliffs. It integrates...
Research & Development
A Hybrid AI Approach for More Reliable and Interpretable Fact-Checking
TLDR: This research introduces a hybrid fact-checking system that integrates Knowledge Graphs (KGs), Large Language Models (LLMs), and web search agents. The system first...
Research & Development
AI-Powered Imaging Predicts Brain Glioma Mutations Non-Invasively
TLDR: Researchers developed a framework combining Large Language Models (LLMs) with computational image analysis to non-invasively predict IDH mutation status in brain gliomas from...
Research & Development
Navigating Trust in the Agentic Web: A Deep Dive into AI Agent Protocols
TLDR: This research paper compares six trust models (Brief, Claim, Proof, Stake, Reputation, Constraint) crucial for designing secure interactions between AI agents in the...