Qiuhao Zeng
PhD Candidate, Machine Learning Group · University of Western Ontario
About
I am a fourth-year PhD candidate advised by Prof. Charles Ling (Fellow, Canadian Academy of Engineering) and Prof. Boyu Wang. My research spans efficient Transformer architectures and transfer learning under temporal distribution shifts. I’m currently open to post-doctoral and research scientist opportunities.
Research Interests
- Efficient attention and Transformer acceleration (e.g., Triton-based kernels, top-k attention).
- Transfer learning across evolving temporal domains; sequence modeling under distribution shift.
- Graph learning and domain adaptation.
Publications
-
ZETA: Leveraging Z-order Curves for Efficient Top-k AttentionInternational Conference on Learning Representations (ICLR), 2025.
-
Calibrated Language Models and How to Find Them with Label SmoothingInternational Conference on Machine Learning (ICML), 2025.
-
On the Benefits of Attribute-Driven Graph Domain AdaptationInternational Conference on Learning Representations (ICLR), 2025.
-
Homophily Enhanced Graph Domain AdaptationInternational Conference on Machine Learning (ICML), 2025.
-
Towards Understanding Evolving Patterns in Sequential DataConference on Neural Information Processing Systems (NeurIPS), 2024 (Spotlight; Top 2.1%).
-
Latent Trajectory Learning for Limited Timestamps under Distribution Shift over TimeInternational Conference on Learning Representations (ICLR), 2024 (Oral; Top 1.2%).
-
Generalizing Across Temporal Domains with Koopman OperatorsAAAI Conference on Artificial Intelligence (AAAI), 2024.
-
Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-Stationary EnvironmentsAAAI Conference on Artificial Intelligence (AAAI), 2023.
-
Episodic Task-Agnostic Contrastive Training for Multi-Task LearningNeural Networks, 2023.
-
LGGNet: Learning from Local-Global-Graph Representations for Brain-Computer InterfaceIEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023.
Academic Service
- Conference Reviewer: ICLR, NeurIPS (Top Reviewer), ICML, AISTATS.
- Journal Reviewer: TNNLS, TMLR.
- Teaching Assistant: CS3346 (AI), CS2210 (Data Structures), CS3357 (Networks).
Patent
Mental Arousal Level Regulation System and Method, PCT Patent no. PCT/SG2022/050243 (2022).
Contact
Email: zengqhyy@gmail.com · qzeng53@uwo.ca
Also on LinkedIn and Google Scholar.