knowledge/profile.md

Prof. Liang Zhao — Profile

Brief description (at a glance)

Dr. Liang Zhao is an award-winning AI researcher at Emory University who builds scalable and trustworthy machine learning for structured, spatial, and scientific problems. Over more than a decade his work has spanned a remarkable arc — from the deployed EMBERS civil-unrest forecasting system, through foundational work on graph neural networks and deep graph generation, to today's frontier of retrieval-augmented and agentic large language models, AI for science (molecules, epidemiology, power grids), and LLM efficiency. He is among Stanford's "Top 2%" most-cited scientists, with ~12,200 citations, an h-index of 52, and an i10-index of 213, and his research is funded by NSF (including a CAREER Award), NIH, and industry partners such as Amazon, Meta, and NVIDIA. His guiding philosophy: "Whatever science domain I work with, I abstract the core problem into mathematical language."

Who he is

Dr. Liang Zhao is a Winship Distinguished Research Professor and Associate Professor in the Department of Computer Science at Emory University, with a joint appointment in the Cell & Molecular Biology Division of the Winship Cancer Institute. He earned his Ph.D. from Virginia Tech in 2017. He has authored 200+ peer-reviewed papers, with roughly 12,000 citations, an h-index of 52, and an i10-index of 212 (Google Scholar). His work is supported by NSF, NIH, and industry partners including Amazon, Meta, and NVIDIA.

Homepage: https://cs.emory.edu/~lzhao41/ Google Scholar: https://scholar.google.com/citations?user=qnvyqtwAAAAJ&hl=en

Research mission

He builds scalable and trustworthy machine learning for structured, spatial, and scientific domains. A recurring theme in his own words: "Whatever science domain I work with, I abstract the core problem into mathematical language."

Core research areas

• Graph neural networks & graph learning — foundations, deep graph generation, graph transformation, text-attributed graphs, distributed/efficient GNN training, spectral–spatial unification, GNN explainability.
• Geospatial & spatio-temporal reasoning — spatial event forecasting, trajectory generation, polyhedra/3D geometry representation learning, spatial RAG and spatial agents.
• AI for science / scientific ML — AI-guided molecule and disinfectant design, neurobiology simulation, wildfire-smoke modeling, tumor detection, MRI-based brain health, healthcare knowledge graphs.
• Large language models — retrieval-augmented generation (RAG), graph & citation RAG, agentic systems, domain specialization, uncertainty quantification, federated pruning, resource-efficient LLMs.
• Trustworthy & efficient AI — explainability, robustness, optimization for infrastructure and energy efficiency, LLM cost reduction.

Research impact & reach

• Metrics (Google Scholar): ~12,200 total citations, h-index 52, i10-index 213; most citations are recent (since 2021), reflecting an accelerating research program.
• Highly cited works include the Graph Neural Networks: Foundations, Frontiers, and Applications book (1400+ citations), the Domain Specialization of LLMs survey, the EMBERS civil-unrest forecasting system, and GRAG: Graph Retrieval-Augmented Generation.
• Frequent collaborators span top institutions and labs: Chang-Tien Lu and Naren Ramakrishnan (Virginia Tech), Lingfei Wu, Feng Chen (UT Dallas), Jian Pei (Duke), Jieping Ye (Alibaba), Charu Aggarwal (IBM), Hui Xiong, and Lise Getoor (UC Santa Cruz), among others.
• Newest directions (2026): "world models" for science and decision-making — e.g. Toward World Models for Epidemiology, MolWorld for molecular optimization, and LUMINA, a grid foundation model for power-system optimization — plus self-maintaining LLM-agent skill libraries (SkillOps).

Selected awards & recognition

• 2025: KDD Test of Time Award; CIKM Best Paper Runner-up.
• 2024: Stanford "Top 2% Scientists" ranking.
• 2023: IEEE Middle-Career Award.
• 2022: ICDM Best Paper Award; Meta Research Award.
• 2020: NSF CAREER Award; Amazon Research Award.

Current Ph.D. students and their topics

• Dazhou Yu (2021–): 3D geometry, spatial reasoning, polyhedra representation learning (PolyhedronNet; Spatial-RAG).
• Yifei Zhang (2022–): visual explanations, saliency analysis, active learning (Saliency-Bench).
• Bo Pan (2022–): graph neural networks, text-attributed graphs, GNN explanations (GraphNarrator).
• Mengdan Zhu (2023–): latent representation explanation, generative models (LatentExplainer).
• Yuntong Hu (2023–): RAG systems, citation networks, memory-augmented LLMs (GRAG, CG-RAG, RAG-without-Forgetting).
• Zeeshan Memon (2024–): information propagation, diffusion networks (propagation-tree identification).
• Yang Qiao (2024–).
• Ziyuan Qin (2024–, co-advised): biomedical informatics applications.
• Xinyuan Song (2024–).
• Riyang Bao (2025–): spatial reasoning, agentic systems (Spatial-Agent).
• Yuzhu Mao (2025–).
• Ziyang Yu (2025–).
• Yuxiang Lai (2026–, co-advised): biomedical applications.
• Ken Su (2026–).