Huili Huang 黄慧丽

Disaster Resilience × AI

Hello! I'm Huili Huang, a postdoctoral fellow in the School of Civil and Environmental Engineering at Georgia Tech, working with Dr. David Frost. I completed my Ph.D. in Computational Science and Engineering at Georgia Tech under the supervision of Dr. David Frost and Dr. Max Mahdi Roozbahani.

As a computer scientist working on real-world engineering problems, my research focuses on AI for disaster resilience, particularly damage assessment using deep learning, computer vision, and generative AI, with an emphasis on ground-level imagery. I develop large-scale disaster image datasets, including EID and EIDSeg, and design domain-adaptive models built upon state-of-the-art foundation models to address practical challenges in disaster response and infrastructure resilience.

Computer Vision Generative AI Disaster Resilience Remote Sensing
Email CV (PDF) Scholar LinkedIn GitHub
Portrait of Huili Huang

Updates

News

2026.9 Excited to share that our paper “SeismoMind: A Zero-shot Decision-Tree Based Multimodal Large Language Model Framework for Post-Earthquake Infrastructure Damage Understanding” was published in Advanced Engineering Informatics!
2026.8 Thrilled to share that our paper “Rockfill Compaction Control and Decision Support Framework Using Transformers with Diffusion-Assisted Data Synthesis” was published in Computer-Aided Civil and Infrastructure Engineering.
2026.5 Successfully defended my Ph.D. dissertation, “Post-disaster Damage Assessment Based on Deep Learning with Surrogate Data.” An unforgettable milestone in my Ph.D. journey!
2026.4 Honored to receive the 2026 Outstanding Graduate Research Assistant Award from the College of Computing at Georgia Tech!
2026.1 Excited to share that EIDSeg was accepted at AAAI 2026 in the AI for Social Impact track!
2025.10 Happy to share that our paper on machine-vision particle-breakage analysis was accepted for publication in Automation in Construction. Congrats Chengeng!
2025.8 Excited to share that DASeg was published in Remote Sensing!
2025.3 Happy to share that our work on the Earthquake Image Database (EID) , a social-media imagery dataset for earthquake infrastructure damage assessment, was published in Earthquake Spectra!

Selected work

Recent publications

A few highlights. See the full list →

EIDSeg: A Pixel-Level Semantic Segmentation Dataset for Post-Earthquake Damage Assessment from Social Media Images

Huili Huang, Chengeng Liu, Danrong Zhang, et al.

AAAI, AI for Social Impact (AISI), 2026
AAAI '26

DASeg: A Domain-Adaptive Segmentation Pipeline Using Vision Foundation Models — Earthquake Damage Detection Use Case

Huili Huang, Andrew Zhang, Danrong Zhang, M. Mahdi Roozbahani, J. David Frost

Remote Sensing, 2025
Remote Sensing

Towards Enhancing the Utility of Social Media Images in Earthquake Disaster Assessment

Huili Huang, Danrong Zhang, Anastasiya Masalava, M. Mahdi Roozbahani, Nimisha Roy, J. David Frost

Earthquake Spectra, 2025
Eq. Spectra