About
Research & Development
Adaptive Adversarial Scenarios for Autonomous Driving Safety
TLDR: SAGE (Steerable Adversarial scenario GEnerator) is a new framework for creating challenging yet realistic scenarios to test autonomous driving systems. Unlike previous methods...
Research & Development
Verifying Game Tree Search: A Deep Dive into Minimax Algorithms and Transposition Tables
TLDR: This research paper formally verifies minimax search algorithms, including those with alpha-beta pruning and transposition tables, using the Dafny verification system. It introduces...
Research & Development
AI Agents Streamline CT Scan Protocol Management
TLDR: A new framework uses Large Language Model (LLM) agents to automate the complex and time-consuming process of managing CT scan protocols. This system...
Research & Development
Enhancing Trust and Performance in Healthcare Federated Learning
TLDR: FedFiTS is a novel federated learning framework designed to improve accuracy, convergence speed, and security in healthcare AI. It achieves this by implementing...
Research & Development
Unveiling Large Language Model Signatures: A Deep Dive into Weight Distribution and Clustering
TLDR: This research introduces two novel "fingerprints" for Large Language Models (LLMs): the Standard-Deviation Vector and the Clustering Vector. The Standard-Deviation Vector captures how...
Research & Development
Advancing GUI Testing with LLM Agents: Addressing Soundness and Consistency
TLDR: This research paper explores the use of LLM agents for executing natural language (NL) test cases in GUI applications. It addresses key challenges...