Hi! I am Xiaohuan Pei (Terry) 😊, a PhD student at the University of Sydney, supervised by Professor Chang Xu. I major in deep learning at the school of computer science.
Specialized Field: Efficiency AI, Vision-Language Models.
Recent Work: Future-aware Attention, EfficientVMamba, Cross-Self Pruning.
🔥 Updates
- 2025.05: Release Light Future-aware Attention.
- 2024.12: Release a VLM inference project: CSP.
- 2024.12: One paper accepted to AAAI 2025.
- 2024.01: One paper accepted to ICLR 2024.
📝 Artificial Intelligence Projects
Cross-Self KV Cache Pruning for Efficient Vision-Language Inference
Xiaohuan Pei, Tao Huang, Chang Xu
EfficientVMamba: Atrous Selective Scan for Light Weight Visual Mamba
Xiaohuan Pei, Tao Huang, Chang Xu
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2025
Xiaohuan Pei, Yanxi Li, Minjing Dong, Chang Xu
The International Conference on Learning Representations (ICLR), 2024
GPT Self-Supervision for a Better Data Annotator
Xiaohuan Pei, Yanxi Li, Minjing Dong, Chang Xu
Contrastive Code-Comment Pre-training
Xiaohuan Pei, Daochang Liu, Qian Luo, Chang Xu
International Conference on Data Mining (ICDM), 2022
Self-Attention Gated Model for Cognitive Diagnosis
Xiaohuan Pei, Shuo Yang, Jiajun Huang, Chang Xu
International Conference on Data Mining (ICDM), 2022
📖 Teaching
-
2024, Guest Lecture, Artifical Intelligence, The University of Sydney
-
2023, 2025, Tutor for COMP5329 Deep Learning, The University of Sydney
🎖 Awards
- ICDM Best Student Paper Award
- Two Full Scholarship Awards
- Outstanding Graduate
- National Second Prize in Mathematics Competition in China
- Provincial Prize in C++ Programming Competition in China
🌟 Grants
- The National Computational Infrastructure (NCI) Adapter Scheme, Australia
Services
- Reviewer of ICML, NeurIPS, ICLR, CVPR.
Contact: xiaohuan.pei at sydney.edu.au, terrypei123 at gmail.com