Trustworthy Medical VQA: Auditing Vision-Language Models
Explore the reliability of top vision-language models in medical VQA, focusing on grounding failures, format issues, and domain adaptation strategies.
Enhancing AI Policy Compliance with Knowledge Graphs
Discover how knowledge graphs improve LLM-based AI policy compliance reasoning for better risk management and regulatory adherence.
WaferSAGE: AI-Driven Wafer Defect Analysis with Synthetic Data
Discover WaferSAGE, an AI-powered framework using synthetic data and reinforcement learning for precise wafer defect analysis in semiconductor manufacturin...
Enhancing Math Learning with LLMs: Anxiety, Confidence & Performance
Explore how MEDS dataset improves math education by analyzing LLMs' performance, anxiety, and confidence in simulated students and AI tutors.
Trace Analysis of Information Contamination in Multi-Agent AI
Explore how trace-level analysis reveals info contamination impacts in multi-agent AI systems, enhancing workflow reliability and decision accuracy.