Open to opportunities

Hao Zhang

@haozhang

Message

PhD student specializing in large language models and graph learning.

United States

Message

What I'm looking for

I seek a collaborative environment that fosters innovation and growth in AI research.

I am currently a PhD student at UW-Madison, where I am supervised by Prof. Suman Banerjee. My research focuses on deploying large language models (LLMs) on power-constrained devices, and I have been actively involved in benchmarking platforms for evaluating LLMs on mobile devices. My academic journey has been marked by significant contributions to various research projects, including a comprehensive benchmark of compressed LLMs on mobile platforms, which was presented at ICLR 2025.

Throughout my research career, I have gained valuable experience as a research assistant at prestigious institutions such as ETH Zurich and the National University of Singapore. My work has included using deep learning algorithms for IoT device security and developing AR applications for wearable devices. I have also contributed to open-source projects like GluonCV and the Deep Graph Library, which are widely recognized in the field of computer vision and deep learning.

Experience

Work history, roles, and key accomplishments

Current

Research Assistant

Current

UW-Madison

Sep 2022 - Present (2 years 10 months)

Worked on deploying Large Language Models (LLM) on power-constrained devices. Focused on quantization and benchmarking platforms for evaluating LLM performance on mobile devices.

Model Quantization Benchmarking Mobile Deep Learning

Research Assistant

Network Security Group at ETH Zurich

Aug 2021 - Nov 2021 (3 months)

Utilized deep learning algorithms to simulate defense and attack processes for IoT devices and detect data exfiltration. Developed and deployed a flow size predictor using TCP packet datasets to optimize networking system performance.

Deep Learning Data Exfiltration TCP

Remote Visiting Student

UW Networks and Mobile Systems Lab

Jul 2020 - Aug 2021 (1 year 1 month)

Developed and deployed AR applications on wearable devices, including face detection on VR headsets with eye-tracking integration. Explored and replicated state-of-the-art real-time speech separation baselines, including simulating synthetic audio datasets for Beamforming validation.

VR Speech Separation Beamforming Python

Research Assistant

Learning and Vision Lab at National University of Singapore

Jun 2019 - Aug 2019 (2 months)

Participated in the NeurIPS 2019 MineRL Competition, achieving 4th place. Focused on distributed reinforcement learning, combining PPO with Vtrace to enhance performance in MineCraft and Impala reproduction.

Reinforcement Learning Distributed Systems PPO Minecraft Impala

Visiting Guest

AWS AI Lab Shanghai

Mar 2019 - Jun 2019 (3 months)

Contributed to building a deep learning system for graph-based models and worked on graph-based model benchmarks. Proposed algorithms for sparsifying molecule datasets based on edge attention.

Deep Learning Algorithm Development Benchmarking

Education

Degrees, certifications, and relevant coursework

University of Wisconsin-Madison

PhD, Computer Science

Activities and societies: Engaged in research on deploying LLM on power-constrained devices, including quantization and benchmarking platforms for evaluating LLM on mobile devices. Contributed to various research papers presented at conferences like ICLR and AAAI.

Currently pursuing a PhD in Computer Science, supervised by Prof. Suman Banerjee. Research interests include Large Language Models (LLM), Graph Representation Learning, and Wireless Sensing.