WindowsWorld: Benchmarking Autonomous GUI Agents in Multi-App Workflows
Discover WindowsWorld, a benchmark evaluating autonomous GUI agents in complex, multi-application professional environments for improved AI efficiency.
Intent2Tx: Benchmarking LLMs for Ethereum Intent Translation
Discover Intent2Tx, a benchmark evaluating LLMs' ability to translate natural language intents into Ethereum blockchain transactions with real-world data.
AI-Driven Digital Twin Traffic Signal Optimization
Optimize urban traffic flow with AI-powered digital twin systems for real-time traffic signal control and reduced congestion.
Australian Consumer Attitudes Toward AI in Digital Health
Explore Australian consumer views on AI in digital health, highlighting trust, usefulness, and safety concerns from a mixed-methods survey.
MED-VRAG: Multimodal AI Boosts Medical QA Accuracy
Discover MED-VRAG, a multimodal AI framework that enhances medical question answering by integrating text and visual data for 78.6% accuracy.