PhD Candidate

The petitioner proposes to continue research in developing trustworthy and human-centered artificial intelligence systems, specifically focusing on Large Language Model (LLM) safety. The work involves creating advanced LLM-based systems that enhance productivity while implementing safeguards against bias and unfair outcomes. The intended impact is to ensure AI-driven applications operate responsibly and equitably within the United States.

The petitioner proposes to continue her research on developing human-centered and responsible artificial intelligence frameworks. Her work focuses on illuminating how individuals utilize and understand AI to mitigate its harms and promote effective integration in public domains such as education, management, and creativity.

The petitioner proposes to continue her research in the field of artificial intelligence, specifically focusing on developing algorithms for effective collaboration between humans and AI. Her work aims to improve the safety, interpretability, and usability of autonomous systems through innovations in explainable planning and secure AI action synthesis. The endeavor seeks to bridge technical innovation with practical, socially responsible deployment of AI systems.

The petitioner endeavors to develop new artificial intelligence methods for clear decision-making, transparent model monitoring, and bias identification to enhance industrial machine learning. His work focuses on making AI systems more explainable and trustworthy to facilitate their integration across critical domains and foster trust in decision-making processes.