Institution profile

Vanderbilt University

Academic institutionnorthamerica · us
Official website
Research library506linked papers
Opportunities0open roles
Selected work

Representative Papers

Towards Resilience and Autonomy-Based Approaches for Adolescents Online Safety

Apr 22, 2025Social Science Research Network

Current parental digital interventions overly emphasize restrictive monitoring, undermining adolescents’ privacy and impeding the development of their digital competence. Method: This study integrates empirical literature review with conceptual modeling, synthesizing theories of digital resilience, Privacy-Enhancing Design (PED), participatory design, and adolescent digital literacy assessment frameworks. Contribution/Results: It introduces— for the first time—a systematic, teen-centered online safety model grounded in resilience and autonomy, shifting the paradigm from “safety as control” to one that positions adolescents as agentic participants rather than passive risk subjects. The study yields scalable pathways for cultivating digital resilience and empirically informed design principles. These findings provide theoretical grounding and evidence-based guidance for EdTech product development, platform governance policies, and family-oriented digital co-parenting practices.

4 citationsRead paper

Reasoning-Based Personalized Generation for Users with Sparse Data

Jan 31, 2026arXiv.org

This study addresses the limited personalization performance of large language models under sparse interaction histories by proposing GraSPer, a novel framework that pioneers a graph reasoning-based paradigm for sparse personalized generation. By predicting future interactions and generating aligned synthetic text through reasoning, GraSPer effectively enriches user context to achieve better style and preference alignment. As the first approach integrating graph neural networks with synthetic data augmentation, it significantly enhances personalized generation in sparse scenarios across three benchmark datasets. These results validate the effectiveness of leveraging synthetic history to mitigate data insufficiency, demonstrating that structured reasoning over augmented interactions can substantially improve model adaptability even when historical user data is limited.

2 citationsRead paper

Online Decision-Making Under Uncertainty for Vehicle-to-Building Systems

May 06, 2025International Conference on Cyber-Physical Systems

This study addresses the challenge of optimizing electricity costs in vehicle-to-building (V2B) systems under multiple uncertainties, including dynamic electricity pricing, long-horizon scheduling, heterogeneous charging infrastructure, and stochastic user demands. To overcome the limitations of conventional single-stage combinatorial optimization approaches, this work is the first to formally model the problem as a stochastic Markov decision process. The authors propose a novel policy that integrates online search with domain-informed action pruning to effectively manage the high-dimensional state and action spaces inherent in real-world V2B operations. Evaluated on real-world electric vehicle data from the Nissan Silicon Valley Advanced Technology Center, the proposed method demonstrates significant performance improvements over current state-of-the-art solutions.

2 citationsRead paper

Agentic AI -- Physicist Collaboration in Experimental Particle Physics: A Proof-of-Concept Measurement with LEP Open Data

Mar 05, 2026

This work investigates the feasibility of employing artificial intelligence agents to carry out complex measurement tasks in high-energy physics experiments, with a focus on end-to-end analysis of the thrust distribution in e⁺e⁻ collisions. The study presents the first complete AI-driven measurement pipeline: leveraging open data from LEP, an AI agent—guided by expert supervision and powered by OpenAI Codex and Anthropic Claude—automatically executes data processing, performs shape corrections via iterative Bayesian unfolding combined with Monte Carlo-based corrections, and generates a full analysis report. The resulting fully corrected thrust distribution demonstrates the effectiveness of AI agents in precision physics measurements and establishes a novel paradigm for closed-loop collaboration between theoretical modeling and experimental analysis.

1 citationsRead paper

Real-World Design and Deployment of an Embedded GenAI-powered 9-1-1 Calltaking Training System: Experiences and Lessons Learned

Jan 30, 2026arXiv.org

This study addresses a critical training crisis in 9-1-1 emergency call centers, where staffing shortages exceed 25% and conventional training demands up to 720 hours per operator while lacking scalability. In collaboration with Nashville’s Emergency Communications Department, the authors deployed—within an active operational environment—the first large-scale, generative AI–driven interactive training system for emergency dispatchers. Over six months, the system engaged 190 operators across 1,120 training sessions and 98,429 user interactions. The research identifies four human-centered AI design and governance practices tailored to real-world constraints, uncovers systemic challenges invisible in simulated settings, and demonstrates the feasibility of generative AI for high-stakes public safety training. The findings yield actionable design principles and implementation guidelines that are readily transferable to comparable domains.

1 citationsRead paper
Recent publications

Latest Papers