Postdoctoral Associate
College of AI, Cyber and Computing
UT San Antonio
Mentor: Dr. Jinjun Xiong
I develop AI, particularly multimodal large language models, to support teaching, learning, and human connection. My work translates educational goals into computational tasks and builds algorithms, datasets, and systems for assessment and feedback, instructional material evaluation, storybook generation, and student behavior analysis. Through interdisciplinary collaboration, I aim to automate parts of task formulation and evaluation design and study risks such as emotional overreliance on AI and reduced independent reasoning. My goal is reliable, responsible AI that supports equitable, high-quality education.
I received my Ph.D. in Computer Science from The Pennsylvania State University in 2024, advised by Dr. Rebecca J. Passonneau in the Natural Language Processing Lab. My dissertation on automated assessment of STEM reasoning received the Best Doctoral Dissertation Award. Before joining UT San Antonio, I was a postdoctoral associate at the University at Buffalo’s Institute for Artificial Intelligence and Data Science (IAD), mentored by Dr. Jinjun Xiong.
I continue to work with the following centers at the University at Buffalo:
2026 · Journal of Autism and Developmental Disorders
PaiCoach combines AI-generated feedback with human review to support parent-led communication interventions. A four-family single-case study found improvements in parent implementation and child responsiveness, while showing the continued need for expert oversight.
AIED 2026 · Companion proceedings, pp. 498–504
An LLM-powered humanoid robot combines speech, vision, and gesture during shared reading about AI. Comparing three dialogue policies on real hardware identifies how structured interaction and bounded language-model support can improve pedagogical coherence.
AIED 2026, pp. 539–554
SciEval benchmarks how well language models evaluate K-12 science instructional materials against an educator-designed rubric. It contains 273 lessons annotated across 13 criteria, with scores and supporting rationales, and tests whether domain-specific fine-tuning improves evaluation.
LAK 2026 Companion Proceedings, pp. 246–248
LLM4Art uses expert-informed prompts and rubrics to examine visual analysis, historical context, and cultural significance. A 50-artwork benchmark compares five language models, and a web application makes the interpretation workflow available to users.
Computing Conference 2026 · Intelligent Computing, pp. 481–496
Two science education experts review evaluations from GPT, Claude, and Gemini across 12 curriculum units. The study distinguishes agreement on numerical scores from agreement on reasoning and suggestions, revealing where model judgments depart from educational expertise.
AIED 2025, pp. 285–292
StoryLab helps K-2 teachers create personalized stories with illustrations, narration, and vocabulary support. Teachers specify learning goals and review generated materials, connecting children's interests with classroom literacy objectives.
Projects by research area · More paper highlights · Full publication list · Fields & venues