Contact: swjz@uchicago.edu
Office: Crerar 381
I am currently a fifth-year PhD student in computer science at the University of Chicago, advised by Sanjay Krishnan. My research interests include streaming systems for real-time multimodal serving.
EdgeServe is a real-time model serving system that optimizes the movements of multimodal streaming data. [Website] [GitHub]
EdgeServe: A Streaming System for Decentralized Model Serving [Paper]
Ted Shaowang and Sanjay Krishnan.
In submission.
Sensor Fusion on the Edge: Initial Experiments in the EdgeServe System [Paper]
Ted Shaowang, Xi Liang and Sanjay Krishnan.
BiDEDE 2022: The International Workshop on Big Data in Emergent Distributed Environments
Declarative Data Serving: The Future of Machine Learning Inference on the Edge [Paper]
Ted Shaowang, Nilesh Jain, Dennis D. Matthews and Sanjay Krishnan.
VLDB 2021: The 47th International Conference on Very Large Data Bases
AMIR (Active Multimodal Interaction Recognition) is a framework for activity recognition that trains independent models for video and network data respectively, and subsequently combines the predictions from both models using a meta-learning method. [Link]
VizEx is an ongoing project that explores how to effectively debug long-tail errors in video analytics pipelines.