About Me

Hello! I’m an applied researcher at Capital One, specializing in foundation models. Previously, I was a machine learning scientist at JPMorganChase, where I applied natural language processing to challenges in cybersecurity and technology infrastructure. I hold a PhD in Nuclear Engineering and an MS in Computational Science and Engineering from Georgia Tech. My research focuses on developing and applying machine learning models in cybersecurity, economics, and physics.

I’m looking to collaborate on research involving large language models, especially in cybersecurity and economics. If you’re working on related topics, feel free to email me!

Work Experience

Applied Researcher, Capital One, Apr 2025 – Present
Applied AI ML Associate Sr, JPMorganChase, Feb 2022 – Apr 2025
Applied AI & Machine Learning Summer Associate, JPMorganChase, Jun 2021 – Aug 2021

Education

Ph.D. in Nuclear Engineering, Georgia Institute of Technology, May 2018 – Aug 2022
M.S. in Computational Science and Engineering, Georgia Institute of Technology, May 2018 – Dec 2021
M.S. in Aerospace Engineering, Georgia Institute of Technology, Aug 2016 – May 2018
B.E. in Energy and Power Engineering, Shandong University, Sep 2012 – Jun 2016

Academic Service

Reviewer: NeurIPS’24 Workshop (ML4PS, FM4Science), AAAI’25 Workshop (MARW), ICLR’25 & Workshop, IJCNN’25.

Zefang Liu

About Me

Work Experience

Education

Publications

EconWebArena: Benchmarking Autonomous Agents on Economic Tasks in Realistic Web Environments

AutoBnB: Multi-Agent Incident Response with Large Language Models

Multi-Agent Collaboration in Incident Response with Large Language Models

Retrieval of Temporal Event Sequences from Textual Descriptions

TPP-LLM: Modeling Temporal Point Processes by Efficiently Fine-Tuning Large Language Models

Application of Neural Ordinary Differential Equations for ITER Burning Plasma Dynamics

InvAgent: A Large Language Model based Multi-Agent System for Inventory Management in Supply Chains

EconLogicQA: A Question-Answering Benchmark for Evaluating Large Language Models in Economic Sequential Reasoning

AdaMoLE: Fine-Tuning Large Language Models with Adaptive Mixture of Low-Rank Adaptation Experts

Application of Neural Ordinary Differential Equations for Tokamak Plasma Dynamics Analysis

A Review of Advancements and Applications of Pre-trained Language Models in Cybersecurity

CyberBench: A Multi-Task Benchmark for Evaluating Large Language Models in Cybersecurity

SecQA: A Concise Question-Answering Dataset for Evaluating Large Language Models in Computer Security

Anomaly Detection of Command Shell Sessions based on DistilBERT: Unsupervised and Supervised Approaches

A Multi-Region Multi-Timescale Burning Plasma Dynamics Model for Tokamaks

Deep Reinforcement Learning based Group Recommender System

Yelp Review Rating Prediction: Machine Learning and Deep Learning Models

Academic Service