Qiuhao Zeng
Scholar

Qiuhao Zeng

Google Scholar ID: MJdcPlgAAAAJ
Western University
Machine LearningTransfer LearningLLM
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
697
 
H-index
7
 
i10-index
7
 
Publications
16
 
Co-authors
0
 
Contact
Emailzengqhyy@gmail.comCVOpen ↗GitHubOpen ↗LinkedInOpen ↗
Publications
12 items
ARM: Attention with Routed-Memory for Learnable Sparse Control
2026
Cited
0
Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix
2026
Cited
0
Graph Domain Adaptation via Homophily-Agnostic Reconstructing Structure
2026
Cited
0
A Study of Adaptive Modeling Towards Robust Generalization
2026
Cited
0
Entropy-Guided Dynamic Tokens for Graph-LLM Alignment in Molecular Understanding
2026
Cited
0
Investigating the Multilingual Calibration Effects of Language Model Instruction-Tuning
arXiv.org · 2026
Cited
0
Toward Better Generalization in Few-Shot Learning through the Meta-Component Combination
2025
Cited
0
Mamba Modulation: On the Length Generalization of Mamba
2025
Cited
0
Resume
Academic Achievements
  • - Publications:
  • - ZETA: Leveraging Z-order Curves for Efficient Top-k Attention (ICLR, 2025)
  • - Mamba Modulation: On the Length Generalization of Mamba Models (NeurIPS, 2025)
  • - Calibrated Language Models and How to Find Them with Label Smoothing (ICML, 2025)
  • - On the Benefits of Attribute-Driven Graph Domain Adaptation (ICLR, 2025)
  • - Homophily Enhanced Graph Domain Adaptation (ICML, 2025)
  • - Towards Understanding Evolving Patterns in Sequential Data (NeurIPS, 2024, Spotlight; Top 2.1%)
  • - Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time (ICLR, 2024, Oral; Top 1.2%)
  • - Generalizing Across Temporal Domains with Koopman Operators (AAAI, 2024)
  • - Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-Stationary Environments (AAAI, 2023)
  • - Episodic Task-Agnostic Contrastive Training for Multi-Task Learning (Neural Networks, 2023)
  • - LGGNet: Learning from Local-Global-Graph Representations for Brain-Computer Interface (TNNLS, 2023)
  • - Academic Service:
  • - Conference Reviewer: ICLR, NeurIPS (Top Reviewer), ICML, AAAI, AISTATS
  • - Journal Reviewer: TNNLS, TMLR
  • - Teaching Assistant: CS3346 (AI), CS2210 (Data Structures), CS3357 (Networks)
Research Experience
  • - Fourth-year PhD candidate
  • - Research areas include efficient attention and Transformer acceleration, transfer learning across evolving temporal domains, graph learning, and domain adaptation
Education
  • - PhD Candidate, Machine Learning Group, University of Western Ontario
  • - Advisors: Prof. Charles Ling and Prof. Boyu Wang
Background
  • - Research Interests: efficient Transformer architectures, transfer learning under temporal distribution shifts
  • - Advisors: Prof. Charles Ling (Fellow, Canadian Academy of Engineering) and Prof. Boyu Wang
Miscellany
  • - Open to post-doctoral and research scientist opportunities