Institution profile

College of William & Mary

Academic institutionnorthamerica · us
Official website
Research library269linked papers
Opportunities0open roles
Selected work

Representative Papers

Conceptual Modeling: Topics, Themes, and Technology Trends

Mar 30, 2023ACM Computing Surveys

Despite rapid technological advances, the enduring value and evolutionary trajectory of conceptual modeling in digital-era information systems development remain inadequately understood. Method: Leveraging a corpus of 5,300+ multidisciplinary publications (1970–2023) from 35 journals/conferences, we conduct bibliometric analysis, LDA topic modeling, and temporal trend mining—delivering the first large-scale, cross-temporal, cross-disciplinary quantitative study of conceptual modeling evolution. Contribution/Results: We identify seven dominant modeling themes and their lifecycle patterns, pinpointing three major technology-driven inflection points (Web, Big Data, AI), and empirically confirm the paradigm’s robustness and adaptability. Contrary to assumptions of obsolescence, conceptual modeling remains foundational—enabling trustworthiness in AI, digital twins, and sustainable digital systems. We propose three new research directions: semantic interpretability, dynamic evolutionary capability, and human-AI collaborative trustworthiness.

16 citations1 influentialRead paper

Jailbreaking and Mitigation of Vulnerabilities in Large Language Models

Oct 20, 2024arXiv.org

Existing research on large language models (LLMs) lacks a unified taxonomy for prompt injection and jailbreaking attacks, and insufficiently evaluates defenses under dynamic, interactive scenarios. Method: We propose the first four-dimensional attack taxonomy—spanning prompt-level, model-level, multimodal, and multilingual pathways—and develop a robust alignment framework tailored to interactive settings, alongside a novel automated jailbreaking detection method. We further conduct systematic defense benchmarking, bias diagnosis of existing evaluation benchmarks, and multi-dimensional security measurement. Contribution/Results: Our analysis reveals critical failure modes of current defenses in dynamic interactions, identifies key research gaps—including ethical implications and data bias—and delivers the first comprehensive technical roadmap for LLM safety alignment.

7 citationsRead paper

Machine Learning-Guided Memory Optimization for DLRM Inference on Tiered Memory

Mar 01, 2025International Symposium on High-Performance Computer Architecture

Deep learning recommendation models (DLRMs) require terabyte-scale embedding memory, and while hierarchical memory offers cost efficiency, its irregular access patterns severely degrade embedding placement and cache efficiency. To address this, we propose RecMG—a novel system that decouples cache admission decisions from prefetching prediction into two independently trainable models for the first time. We introduce a differentiable loss function explicitly modeling long reuse distances and infrequent embedding accesses, significantly improving prefetching accuracy. RecMG integrates vectorized access pattern learning, hierarchical-memory-aware scheduling, and dynamic prefetching policies. Experimental results show that RecMG reduces on-demand embedding loads by 1.5–2.8× over state-of-the-art baselines and achieves up to a 43% reduction in end-to-end inference latency in industrial-scale deployments.

4 citationsRead paper

Designing AI Peers for Collaborative Mathematical Problem Solving with Middle School Students: A Participatory Design Study

Jan 25, 2026

This study addresses the challenge that middle school students often struggle in collaborative mathematical problem solving due to insufficient teacher support, while existing AI systems predominantly focus on one-on-one tutoring and offer limited assistance in collaborative learning contexts. Through a participatory design approach, 24 middle school students engaged with an interactive generative AI probe to complete mathematics tasks and co-design their ideal AI peer. Findings reveal that students prefer an AI that assumes a “humble yet competent” role, providing progressive scaffolding—such as hints and verification—under student direction, and exhibiting a friendly, professional persona rather than exaggerated anthropomorphism. The study distills design principles for AI peers tailored to collaborative mathematics learning in middle school, offering theoretical and practical insights into the role configuration and interaction mechanisms of educational AI.

1 citationsRead paper

Relink: Constructing Query-Driven Evidence Graph On-the-Fly for GraphRAG

Jan 12, 2026arXiv.org

Existing GraphRAG approaches are constrained by static knowledge graphs, which often suffer from incomplete structures that disrupt reasoning paths and are further compromised by low signal-to-noise ratios in factual evidence. To address these limitations, this work proposes Relink, a novel framework that introduces a “reason-and-construct” paradigm to dynamically build query-oriented evidence graphs. Relink instantiates missing relations on-the-fly from raw text, synergistically integrating structured knowledge graphs with a latent relation pool, and employs a query-aware unified scoring mechanism to jointly select high-quality candidate facts. This approach adaptively repairs broken reasoning chains and proactively filters noise, substantially enhancing the faithfulness and precision of the resulting evidence graph. Evaluated on five open-domain question answering benchmarks, Relink achieves consistent improvements, averaging +5.4% in Exact Match and +5.2% in F1 score over state-of-the-art GraphRAG baselines.

1 citationsRead paper
Recent publications

Latest Papers