Institution profile

University of Connecticut

Academic institutionnorthamerica · us
Official website
Research library341linked papers
Opportunities0open roles
Selected work

Representative Papers

Simulation of Crowd Egress with Environmental Stressors

Jun 03, 2022arXiv.org

This study addresses the challenge of modeling human responses to stressors during emergency evacuations in multi-compartment buildings. Methodologically, it introduces a novel social-force model framework integrating psychological stress theory—specifically embedding stress-response mechanisms systematically into macroscopic pedestrian dynamics for the first time—coupled with opinion dynamics to capture collective decision-making during pre-movement phases, and synergistically combining FDS+EVAC with the custom crowdEgress platform for multi-scale co-simulation. Its key contribution lies in establishing an interpretable, causal chain from environmental stress → individual stress response → emergent collective behavior, unifying bottleneck passage, herding decisions, and dynamic pathfinding within a single formalism. Experimental validation demonstrates high-fidelity reproduction and prediction of stress-induced phenomena—including evacuation delays, localized congestion amplification, and irrational clustering—as well as accurate reconstruction of real-world flow-rate distributions and route-choice preferences across benchmark scenarios.

2 citationsRead paper

Graph is a Substrate Across Data Modalities

Jan 29, 2026

This work addresses the limitation of existing graph learning approaches, which typically operate in isolation within a single modality and task, thereby hindering the cross-task and cross-modal reuse of structural knowledge. To overcome this, the authors propose G-Substrate, a novel framework that models graph structures as persistent, shareable substrates. By unifying structural patterns and employing a role-interleaved training strategy, G-Substrate enables collaborative learning across multiple tasks and modalities. This approach facilitates the continuous accumulation and transfer of graph-structured knowledge, consistently outperforming both isolated training and conventional multi-task learning methods across diverse domains, modalities, and tasks.

1 citationsRead paper

GLEN-Bench: A Graph-Language based Benchmark for Nutritional Health

Jan 26, 2026

This work addresses critical limitations in existing personalized dietary guidance approaches—namely, their frequent neglect of real-world constraints, insufficient interpretability, and lack of a unified evaluation benchmark. To bridge this gap, the authors introduce the first graph–language integrated benchmark for nutritional health, which synthesizes multimodal real-world data including health records, food composition, and accessibility. They construct a knowledge graph linking demographics, medical conditions, dietary behaviors, and resource constraints, and propose a unified evaluation framework centered on three core tasks: risk identification, personalized recommendation, and natural language question answering. Leveraging a hybrid architecture combining graph neural networks and large language models, the approach enables resource-aware, interpretable nutritional interventions. Experiments not only uncover dietary patterns significantly associated with health risks but also yield actionable insights for practical deployment and establish a robust baseline for future research.

1 citationsRead paper

LongDA: Benchmarking LLM Agents for Long-Document Data Analysis

Jan 05, 2026arXiv.org

This work addresses the limitations of current large language model (LLM) agents in handling real-world data analysis tasks that require reasoning over long, heterogeneous documents, a challenge exacerbated by the absence of suitable evaluation benchmarks. To bridge this gap, we introduce LongDA, a benchmark constructed from 17 U.S. national surveys, comprising 505 complex analytical queries that demand cross-document retrieval, information synthesis, and generation of executable code. We also develop LongTA, a tool-augmented agent framework to enable systematic evaluation. Experimental results reveal substantial performance gaps between state-of-the-art open- and closed-source LLMs on this benchmark, underscoring the difficulty of such tasks and highlighting the current limitations of LLM agents in supporting high-stakes decision-making scenarios.

1 citationsRead paper

Robust Training with Data Augmentation for Medical Imaging Classification

Jun 20, 2025

Medical imaging classification models are vulnerable to adversarial attacks and distributional shifts, compromising clinical reliability. To address this, we propose the Robust Training and Data Augmentation (RTDA) framework—a synergistic approach that unifies adaptive robust training with anatomical-structure-aware multimodal image augmentation for the first time. RTDA integrates gradient-regularized adversarial training, geometric and intensity-based augmentations, and cross-modal consistency constraints. Evaluated on benchmark datasets of mammography, X-ray, and ultrasound imaging, RTDA preserves clean accuracy above 94% while improving adversarial robustness by 18.7% on average and out-of-distribution generalization by 9.3%. Its core contribution lies in establishing a unified training paradigm that jointly optimizes clean accuracy, adversarial robustness, and out-of-distribution generalization—thereby advancing the clinical deployability of medical AI systems.

1 citationsRead paper
Recent publications

Latest Papers