Projects

Visualize the Invisible
This work explores the use of generative models to create visualizations based on one or more sensor inputs. We address the challenge of inconsistent or abrupt changes in visual output, such as current SOTA models tend to generate cooler/blueish scenes despite increasing temperature readings. (Left: Stable Diffusion; Right: Ours)

Fully Autonomous System with a Reconfigurable Drone and Foundation Models
This work enables language models to interact with a drone by dynamically swapping its payload and surveying the surroundings. It integrates LLM and VLM agents for task understanding, planning, and scene comprehension using a god-view camera. Open-vocabulary detection models and distillation techniques are employed to perform actuations. (Left: drone swapping platform; Right: system pipeline)

A Low-Cost In-situ System for Continuous Multi-Person Fever Screening
Kaiyuan Hou, Yanchen Liu, Peter Wei, Chenye Yang, Hengjiu Kang, Stephen Xia, Teresa Spada, Andrew Rundle, Xiaofan Jiang
2022 21st ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN 2022) [PDF]

LegoSENSE: An Open and Modular Sensing Platform for Rapidly-Deployable IoT Applications
Minghui Zhao, Stephen Xia, Jingping Nie, Kaiyuan Hou, Avik Dhupar, Xiaofan Jiang
Proceedings of the 8th ACM/IEEE Conference on Internet of Things Design and Implementation (IoTDI 2023) [PDF]

ARSteth: Enabling Home Self-Screening with AR-Assisted Intelligent Stethoscopes
Kaiyuan Hou, Stephen Xia, Emily Bejerano, Junyi Wu, Xiaofan Jiang
Proceedings of the 22nd International Conference on Information Processing in Sensor Networks (IPSN 2023) [PDF]

Anemoi: A Low-cost Sensorless Indoor Drone System for Autonomous Mapping of 3D Airflow Fields
Stephen Xia, Minghui Zhao, Charuvahan Adhivarahan, Kaiyuan Hou, Yuyang Chen, Jingping Nie, Eugene Wu, Karthik Dantu, Xiaofan Jiang
Proceedings of the 29th Annual International Conference On Mobile Computing And Networking (MobiCom 2023) [PDF]