郭甜

Tian Guo

Office: Fuller Labs 138
100 Institute Road
Worcester, MA 01609

Phone: (508)831-6860

👩🏻‍💻 About Me

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.

🚸 Current Students
🎓 Former Students
📝 News
More News >>>
📰 Publications

FusedAR: Adaptive Environment Lighting Reconstruction for Visually Coherent Mobile AR Rendering

Yiqin Zhao, Tian Guo

IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW) (IEEEVRW'22)

paper , project

A followup work to Xihe, FusedAR now provides lighting information that can be used for high-quality reflection rendering for Mobile AR.

Multi-objective Optimization by Learning Space Partitions

Yiyang Zhao, Linnan Wang, Kevin Yang, Tianjun Zhang, Tian Guo, Yuandong Tian

International Conference on Learning Representations (ICLR'22)

paper

A novel multi-objective optimizer that learns a model from observed samples to partition the search space and then focus on promising regions that are likely to contain a subset of the Pareto frontier.

FiShNet: Fine-Grained Filter Sharing for Resource-Efficient Multi-Task Learning

Xin Dai, Xiangnan Kong, Tian Guo, Xinlu He

ACM International Conference on Information and Knowledge Management (CIKM'21)

paper

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

Samuel S. Ogden, Guin R. Gilman, Robert J. Walls, Tian Guo

2nd IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS'21)

code , paper

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!

More Publications >>>
🤝 Recent Collaborators
Prashant Shenoy
Robert Walls
Xiangnan Kong
Lijie Xu
Sheng Wei
Prateek Sharma
❤️ Sponsors