Tong Wu

Deep Learning, Human-computer Interaction

Ph.D. in Computer Engineering

Jersey City, NJ, 07302

Tong Wu is a Research Scientist @Meta in NYC office. He works on developing next generation of AI systems and infrastructures.

Tong attained Ph.D. degree in Computer Engineering at Rutgers University in 2023, supervised by Dr. Jorge Ortiz. His research interest is deep learning models for timing and attention predictions during human-computer interaction. His work focuses on improving system objectives and user experience by learning human behaviors. Much of his work have been applied to a broad range of sensing systems including smart vehicles, smart robots and smart buildings by machine learning, multi-modal learning, human-computer interaction.

Tong attained M.S. degree in Computer Engineering at Rutgers University in 2019, and B.S. in Electronic and Information Engineering at University of Electronic Science and Technology of China (UESTC) in 2018.

Tong worked as a Senior Data Scientist @Anthem in 2023. He also interned as a Research Scientist @Meta in 2022, Research Scientist @Honda Research Institute in 2021, Software Engineer @Amazon Web Services in 2019, Software Engineer @Alibaba Group in 2018.

Publications

Learning When Agents Can Talk to Drivers using the inagt Dataset and Multisensor Fusion (IMWUT 2021, UbiComp 2021)

Tong Wu*, Nik Martelaro*, Simon Stent, Jorge Ortiz, Wendy Ju

Human-Robot Commensality: Bite Timing Prediction for Robot-Assisted Feeding in Groups (CoRL 2022)

Janko Andras*, Tong Wu*, Frank Bu, Jorge Ortiz, Tapomayukh Bhattacharjee.

RLAD: Time Series Anomaly Detection through Reinforcement Learning and Active Learning (KDD MiLeTS 2021)

Tong Wu and Jorge Ortiz

Toward an Adaptive Situational Awareness Support System for Urban Driving (IV 2021)

Tong Wu, Enna Sachdeva, Kumar Akash, Xingwei Wu, Teruhisa Misu and Jorge Ortiz

Towards Adaptive Anomaly Detection in Buildings with Deep Reinforcement Learning (BuildSys 2019)

Tong Wu and Jorge Ortiz.

The Smart Building Privacy Challenge (BuildSys 2021)

Tong Wu*, Murtadha Aldeer* and Jorge Ortiz

Multi-sensor Fusion for In-cabin Vehicular Sensing Applications (IPSN 2023)

Tong Wu*, Navid Salami Pargoo* and Jorge Ortiz

(Social) Trouble on the Road: Understanding and Addressing Social Discomfort in Shared Car Trips (arXiv)

Alexandra Bremers, Natalie Friedman, Sam Lee, Tong Wu, Eric Laurier, Malte Jung, Jorge Ortiz, Wendy Ju

System and method for providing a situational awareness based adaptive driver vehicle interface (US Patent)

Tong Wu, Enna Sachdeva, Kumar Akash, Teruhisa Misu

Research

Learning When Agents Can Talk to Drivers using the inagt Dataset and Multisensor Fusion

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT). Volume 5Issue 3Article No.: 133pp 1–28
UbiComp 2021

Dataset

Code

Toward an Adaptive Situational Awareness Support System for Urban Driving

2022 IEEE Intelligent Vehicles Symposium (IV 2022)

Demo

Human-Robot Commensality: Bite Timing Prediction for Robot-Assisted Feeding in Groups

6th Annual Conference on Robot Learning (CoRL 22)

Dataset

Code

Home page

MiLets KDD 2021 Paper 2

RLAD: Time Series Anomaly Detection through Reinforcement Learning and Active Learning

2021 The 7th SIGKDD Workshop on Mining and Learning from Time Series

Code

madness_buildsys

Towards Adaptive Anomaly Detection in Buildings with Deep Reinforcement Learning

Proceedings of the 6th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys '19), November 2019 Pages 380–382

The Smart Building Privacy Challenge

Proceedings of the 8th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys '21), November 2021 Pages 238–239