About Me
Hi! I'm Reza Shahriari, a PhD candidate in Computer Science at the University of Florida, advised by Dr. Eric Ragan. I am an HCI + AI researcher passionate about designing and developing interactive software that leverages AI to address human needs.
My research focuses on Human-AI collaboration, natural language interaction, and multimodal interfaces for knowledge exploration and feedback. I design systems that reduce cognitive effort, improve interpretability, and enhance user efficiency in AI-driven tasks.
I have led multiple research projects, including:
- KnowledgeCapture: Built an LLM-assisted interface for efficient knowledge graph editing, showing improved accuracy over GUI methods.
- MuCHEx (DARPA ECOLE): Designed a multimodal conversational tool for debugging object learning models and led user studies on interpretability.
- FeedMeBetter: Conducted a large-scale study (n=149) evaluating trade-offs in human-in-the-loop AI, fine-tuning vision-language models with human feedback.
- GraphExploration: Created a multimodal interface for large-scale graph exploration with ambiguity resolution and adaptive visual feedback.
My technical expertise spans UI/UX design, data visualization (D3.js, Cytoscape.js), Python, JavaScript, React, and Neo4j. I combine quantitative and qualitative methods in user studies to evaluate usability, interpretability, and engagement.