Zihan Wang
Logo Ph.D. Student
Logo Board Member

I am a first-year Ph.D. student at McGill University and Mila – Quebec AI Institute, co-advised by Prof. Doina Precup and Prof. Xiao-Wen Chang. My research focuses on continual reinforcement learning, aiming to develop AI systems that can learn and adapt in non-stationary environments. I am also a Board Member of ContinualAI, a nonprofit organization advancing research in continual learning.

Previously, I completed my M.Sc. in Electrical and Computer Engineering at McGill and Mila, under the supervision of Prof. Narges Armanfard and Prof. Samira Ebrahimi Kahou, where I worked on anomaly detection. I also hold a B.Sc. in Electrical and Computer Engineering, with a Minor in Mathematics, from the University of Alberta.

Curriculum Vitae

Education
  • McGill University && Mila-Quebec AI Institute
    McGill University && Mila-Quebec AI Institute
    School of Computer Science
    Ph.D. Student
    Supervisors: Doina Precup, Xiao-Wen Chang
    Sep. 2025 - present
  • McGill University && Mila-Quebec AI Institute
    McGill University && Mila-Quebec AI Institute
    M.Sc. in Electrical and Computer Engineering
    Supervisors: Narges Armanfard, Samira Ebrahimi Kahou
    Sep. 2023 - Aug. 2025
  • University of Alberta
    University of Alberta
    B.Sc. in Electrical and Computer Engineering
    Minor in Mathematics
    Sep. 2018 - Jun. 2023
Experience
  • ContinualAI
    ContinualAI
    Board Member
    May 2024 - Present
Honors & Awards
  • Flight PS752 Commemorative Scholarship Program
    2025–2026
  • FRQNT Doctoral Research Scholarship
    2025–2029
  • FRQNT Master’s Research Scholarship
    2024–2025
  • McGill University Graduate Excellence Fellowship
    2023–2025
  • University of Alberta Academic Scholarship (×3)
    2019–2023
  • University of Alberta Dean’s Research Award (×2)
    2021, 2022
News
2025
Started as a Ph.D. student in the School of Computer Science at McGill University and Mila in Fall 2025.
Sep 01
Our paper 'Zero-Shot Anomaly Detection with Dual-Branch Prompt Learning' selected as Oral at BMVC 2025! See you in Sheffield!
Jul 25
Submitted my M.Sc. thesis—ending a wonderful two years at iSMART Lab.
Jun 30
Awarded FRQNT Doctoral Research Scholarship
Apr 30
2024
Joined ContinualAI as Board Member
May 02
Awarded FRQNT Master's Research Scholarship
Apr 30
2023
Started M.Sc. thesis program in Electrical and Computer Engineering at McGill University and Mila in Fall 2023.
Sep 01
Graduated with a B.Sc. from the University of Alberta after five wonderful years. Capstone project: Guess a Sketch
Apr 30
Selected Publications (view all )
Zero-shot Anomaly Detection with Dual-Branch Prompt Learning
Zero-shot Anomaly Detection with Dual-Branch Prompt Learning

Zihan Wang, Samira Ebrahimi Kahou, Narges Armanfard

Proceedings of the British Machine Vision Conference (BMVC) 2025 Oral

Zero-shot anomaly detection (ZSAD) aims to identify and localize unseen defects without requiring any labeled anomalies, but existing methods struggle to generalize under domain shifts. We propose PILOT, a framework combining a dual-branch prompt learning mechanism with label-free test-time adaptation, enabling dynamic adaptation to new distributions using only unlabeled data. PILOT achieves state-of-the-art performance on 13 industrial and medical benchmarks for both anomaly detection and localization under domain shift.

Zero-shot Anomaly Detection with Dual-Branch Prompt Learning

Zihan Wang, Samira Ebrahimi Kahou, Narges Armanfard

Proceedings of the British Machine Vision Conference (BMVC) 2025 Oral

Zero-shot anomaly detection (ZSAD) aims to identify and localize unseen defects without requiring any labeled anomalies, but existing methods struggle to generalize under domain shifts. We propose PILOT, a framework combining a dual-branch prompt learning mechanism with label-free test-time adaptation, enabling dynamic adaptation to new distributions using only unlabeled data. PILOT achieves state-of-the-art performance on 13 industrial and medical benchmarks for both anomaly detection and localization under domain shift.

Improving ECG-based COVID-19 Diagnosis and Mortality Predictions Using Pre-pandemic Medical Records at Population-Scale
Improving ECG-based COVID-19 Diagnosis and Mortality Predictions Using Pre-pandemic Medical Records at Population-Scale

Weijie Sun, Sunil Vasu Kalmady, Nariman Sepehrvand, Luan Manh Chu, Zihan Wang, Amir Salimi, Abram Hindle, Russell Greiner, Padma Kaul

NeurIPS 2022 Workshop on Learning from Time Series for Health 2022

We show that pre-training deep learning models on pre-pandemic health records and fine-tuning them with limited pandemic data can substantially improve ECG-based COVID-19 diagnosis and prognosis. This transfer learning approach demonstrates notable gains across three prediction tasks, highlighting its potential for rapid AI deployment in future outbreaks.

Improving ECG-based COVID-19 Diagnosis and Mortality Predictions Using Pre-pandemic Medical Records at Population-Scale

Weijie Sun, Sunil Vasu Kalmady, Nariman Sepehrvand, Luan Manh Chu, Zihan Wang, Amir Salimi, Abram Hindle, Russell Greiner, Padma Kaul

NeurIPS 2022 Workshop on Learning from Time Series for Health 2022

We show that pre-training deep learning models on pre-pandemic health records and fine-tuning them with limited pandemic data can substantially improve ECG-based COVID-19 diagnosis and prognosis. This transfer learning approach demonstrates notable gains across three prediction tasks, highlighting its potential for rapid AI deployment in future outbreaks.

SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space
SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space

Zihan Wang, Ruimin Chen, Mengxuan Liu, Guanfang Dong, Anup Basu

International Conference on Smart Multimedia 2022

We propose SPGNet, a method for 3D human pose estimation that integrates multi-dimensional re-projection into supervised learning. Our approach enforces kinematic constraints and jointly optimizes both 2D and 3D pose consistency, leading to improved accuracy. Experiments on the Human3.6M dataset show that SPGNet outperforms many state-of-the-art methods.

SPGNet: Spatial Projection Guided 3D Human Pose Estimation in Low Dimensional Space

Zihan Wang, Ruimin Chen, Mengxuan Liu, Guanfang Dong, Anup Basu

International Conference on Smart Multimedia 2022

We propose SPGNet, a method for 3D human pose estimation that integrates multi-dimensional re-projection into supervised learning. Our approach enforces kinematic constraints and jointly optimizes both 2D and 3D pose consistency, leading to improved accuracy. Experiments on the Human3.6M dataset show that SPGNet outperforms many state-of-the-art methods.

All publications