Xi (Alex) Chen, PhD

Senior Principal Researcher@ Huawei Noah's Ark Lab, Montreal

Adjunct Professor @ School of CS, McGill Univ.,

Montreal, QC, Canada

Email: xi.chen11 at mcgill dot ca

Short Bio 

Xi Chen is currently a Senior Principle Researcher at Huawei Noah's Ark Lab, Montreal, leading the Decision Making and Reasoning (DMnR) Team in Canada. He also serves as an adjunct professor at School of Computer Science, McGill University. His experience and passion lie in a wide range of AI domains, including LLM superalignment, decision making foundation models, 5G/6G foundation models, AI for communications, Integrated Sensing and Communications (ISAC), autonomous driving, smart IoT, smart homes, smart systems, vehicle-to-everything, etc. He achieved his PhD degree at School of Computer Science, McGill University.  He received both M.Eng. and B.S. degrees from Department of Electronic Engineering, Shanghai Jiao Tong University.  

News

[2024.01] Two of our papers "Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time", and "Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation" accepted by ICLR 2024!

[2023.12] Our paper "Calibrated One Round Federated Learning with Bayesian Inference in the Predictive Space " accepted by AAAI 2024!

[2023.09] Our paper "FedSwarm: An Adaptive Federated Learning Framework for Scalable AIoT" accepted by Internet of Things Journal!

[2023.07] Our paper "Understanding Hessian Alignment for Domain Generalization" accepted by ICCV 2023!

[2023.03] Our paper "Eliminating Space Scanning: Fast mmWave Beam Alignment With UWB Radios" accepted by ACM Transactions on Sensor Networks!

[2023.01] Our Paper "Proportional Fairness in Federated Learning" accepted by TMLR.

[2022.10] Our paper on "Dynamic Consolidation for Continual Learning" accepted by Neural Computation Journal!

[2022.08] Two papers on 5G and aerial networks accepted by Globecom 2022!

[2022.08] Our survey "Gradient-based Bi-level Optimization for Deep Learning: A Survey" is available online!

[2022.08] Our survey "Encoder-Decoder Architecture for Supervised Dynamic Graph Learning: A Survey" is available online!

[2022.06] Our paper "Learning from FM Communications: Toward Accurate, Efficient, All-Terrain Vehicle Localization" was accepted by IEEE/ACM Trans. Networking!

[2022.03] Our paper "Fidora: Robust WiFi-based Indoor Localization via Unsupervised Domain Adaptation" was accepted by Internet of Thing Journal!

[2022.01] Two papers on transfer/continual learning for 5G traffic prediction accepted by ICC 2022!

Publications


Community Services

Projects involved

Testbeds and demos

VSmart is a DSRC-enabled smart vehicle testbed established at CPS Lab, McGill University, and is partially supported by General Motors Company. (Testbed website, YouTube videos and slides)

Aerial can tell who you are, where you are and what you are doing, even if you don't carry any wearable devices, smartphones, nor cameras. As long as there are standard Wi-Fi signals in the air, aerial is good to go. (Check our Project website and YouTube video to see the magic!)