3 papers
cs.CY2026
Trustworthy AI Posture (TAIP): A Framework for Continuous AI Assurance of Agentic Systems at Horizontal and Vertical scale
Guy Lupo, Bao Quoc Vo, Natania Locke
The emergence of autonomous, high-velocity Agentic AI systems is creating an internal assurance scalability crisis. Point-in-time, document-based audits cannot keep pace with non d…
cs.RO2025
Intelligent Control of Spacecraft Reaction Wheel Attitude Using Deep Reinforcement Learning
Ghaith El-Dalahmeh, Mohammad Reza Jabbarpour, Bao Quoc Vo +1
Reliable satellite attitude control is essential for the success of space missions, particularly as satellites increasingly operate autonomously in dynamic and uncertain environmen…
cs.AI2025
Toward Better Generalisation in Uncertainty Estimators: Leveraging Data-Agnostic Features
Thuy An Ha, Bao Quoc Vo
Large Language Models (LLMs) often generate responses that are factually incorrect yet expressed with high confidence, which can pose serious risks for end users. To address this,…