I am an Assistant Professor in the Computer Science Department at Worcester Polytechnic Institute (WPI) and a proud member of the Cake Lab! Broadly, I am interested in designing systems mechanisms and policies to handle trade-offs in cost, performance, and efficiency for emerging applications. Specifically, I have worked on projects related to cloud/edge resource management, big data frameworks, deep learning inference, distributed training, neural architecture search, and AR/VR. My recent work has a strong focus on improving system support for deep learning and on the practical applications of deep learning in AR/VR.
I completed my Ph.D. at the University of Massachusetts Amherst advised by Prof. Prashant Shenoy. Before that, I received my B.E. from Nanjing University and was an exchange student at National Cheng Kung University.
- Jean-Baptiste Truong (co-advised with Robert Walls) - Master in 2021. Thesis: Protecting Model Confidentiality for Machine Learning as a Service.
- 09/22/2021: [Talk] I gave an invited talk on speeding up cloud-based distributed training in the Xia Peisu Forum. I was glad to see a good attendance and enjoyed great talks by other researchers on various topics! Maybe all-things-graphs are the future?
- 08/27/2021: [Paper] Our vision paper on decarbonizing the cloud has been accepted to SoCC 2021! This is a collaboration between UMass Amherst and Caltech.
- 08/25/2021: [Teach] Our academic year officially starts and I am both excited and nervous about going back in-person; well, it has been a while since mid March 2019. I hope I don't disappoint!
- 08/07/2021: [Paper] The shepherding process of DELI was successful and DELI has been officially accepted to IC2E 2021. Meanwhile, the organizing committee of IC2E is finalizing our position paper on the future of cloud engineering! Oh and FishNet, our first attempt to toward resource-efficient multi-task learning, has been accepted to CIKM 2021! We think that FishNet has the potential of modernizing mobile AR.
- 06/29/2021: [Paper] Fidelius has been accepted to IC2E 2021 and DELI has been conditionally accepted! These two projects are both related to speeding up deep learning, the former is for inference while the later is for training.
- 05/23/2021: 🔥 [Paper] I am happy to announce that our paper Xihe has been accepted to MobiSys 2021! Xihe is a 3D Vision-based Lighting Estimation Framework for Mobile Augmented Reality; it provides fast (~20ms per estimation) and accurate lighting estimation compared to ARKit and GLEAM.
FiShNet: Fine-Grained Filter Sharing for Resource-Efficient Multi-Task Learning
ACM International Conference on Information and Knowledge Management (CIKM'21)
Having multiple deep learning tasks that you want to run on mobile devices? Our FiShNet circumvents the need to manage multiple DL models and provides flexible and fine-grained sharing among different tasks.
Many Models at the Edge:Scaling Deep Inference via Model-Level Caching
2nd IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS'21)
Want to know how to effectively manage a large number of deep learning models, some are popular and some are less requested, at a resource-constrained edge? Check out our model-specific caching work CremeBrulee!
Enabling Sustainable Clouds: The Case for Virtualizing the Energy System
ACM Symposium on Cloud Computing 2021 (SoCC'21)
It is time to treat carbon as the first-class citizen when designining and managing data centers and clouds! Our vision paper outlines a roadmap with energy virtualization that leads us toward near zero carbon future.
On the Future of Cloud Engineering
9th IEEE International Conference on Cloud Engineering (IC2E'21)