Zihao Ding
I am a PhD student in Electrical and Computer Engineering at Rutgers University, working on AR/VR systems and edge ML under the supervision of Prof. Yao Liu. My research focuses on running computation-intensive vision and AI models on resource-constrained personal devices through model partitioning and systems optimization.
I also previously integrated real-world sensing and infrastructure systems, including the WIM (Weigh-in-Motion) deployment on the BQE. Broadly, I work at the intersection of systems, multimedia, and hardware-aware machine learning.
Research Themes
Privacy on the Edge
Partitioning Vision Transformers to ensure data privacy on constrained edge devices.
AR/VR Systems
Navigation datasets, 6-DoF tracking systems, and performance optimization for AR/VR workloads.
LLM System Performance
Characterizing latency, cost, and multi-agent system overheads in tool-augmented LLM systems.
Publications
We propose a distributed ViT framework that partitions attention layers across multiple servers, preventing full-scene reconstruction on any single server while preserving near-baseline accuracy.
A real-world 6-DoF VR navigation dataset for 3DGS scenes, with a record-and-replay toolkit for evaluating rendering and VR system performance.
Recent Updates
- Dec 2025 Presented at ACM/IEEE SEC’25 (Session 1C: Privacy & Security).
- Oct 27, 2025 EyeNavGS published at ACM Multimedia 2025.
- Oct 20, 2025 Released preprint on MCP-enabled LLM agent performance.