Hi! I am Xiaohuan Pei (Terry) 😊, a second year PhD student at the University of Sydney, honorably supervised by Professor Chang Xu. I major in deep learning at the school of computer science.

Specialized Field: Efficiency, Vision Language Models, Vision Language Actions.

Recent Projects:

Future-aware Masking for Vision Language Inference,

Cross-Self Pruning with $nSoftmax$ (equivalent to GPT-OSS sink implementation released one year earlier).


📝 Recent Work

sym

Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation

Xiaohuan Pei*, Yuxing Chen*, Siyu Xu, Yunke Wang, Yuheng Shi, Chang Xu

[Paper] [Code]

sym

Self-Distilled RoI Predictors for Fine-Grained MLLM Perception

Yuheng Shi, Xiaohuan Pei, Minjing Dong, Chang Xu

[Paper] [Code]

sym

Light Future-aware Masking for Vision-Language Inference

Xiaohuan Pei, Tao Huang, Yanxiang Ma, Chang Xu

[Paper]

AAAI 2025
sym

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

[Paper] [Code] [Tutorial] GitHub stars

ECCV W 2024
sym

LocalMamba: Visual State Space Model with Windowed Selective Scan

Tao Huang, Xiaohuan Pei, Chang Xu

The European Conference on Computer Vision (ECCV), Workshop, 2024

[Paper] [Code] GitHub stars

ICLR 2024
sym

Neural Architecture Retrieval

Xiaohuan Pei, Yanxi Li, Minjing Dong, Chang Xu

The International Conference on Learning Representations (ICLR), 2024

[Paper] [Code]

sym

GPT Self-Supervision for an Efficient Data Annotator

Xiaohuan Pei, Yanxi Li, Minjing Dong, Chang Xu

[Paper] [Code] [News]

🧑🏻‍💻 Preprints

Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation.
Xiaohuan Pei*, Yuxing Chen*, Siyu Xu, Yunke Wang, Yuheng Shi, Chang Xu
arXiv preprint [arXiv:2505.18605] (2025).

Rethinking Causal Mask Attention for Vision-Language Inference.
Xiaohuan Pei, Tao Huang, Yanxiang Ma, Chang Xu.
arXiv preprint [arXiv:2505.18605] (2025).

Cross-Self KV Cache Pruning for Efficient Vision-Language Inference.
Xiaohuan Pei, Tao Huang, Chang Xu.
arXiv preprint [arXiv:2412.04652] (2024).

GPT self-supervision for a better data annotator.
Xiaohuan Pei, Yanxi Li, Chang Xu.
arXiv preprint [arXiv:2306.04349] (2023).

Catching the details: self-distilled ROI predictors for fine-grained Vision-Language-Model perception.
arXiv preprint [arXiv:2509.16944] (2025).
Yuheng Shi, Xiaohuan Pei, Minjing Dong, Chang Xu.

Text-driven Neural Architecture Embeddings and Retrieval.
Xiaohuan Pei, Yanxi Li, Minjing Dong, Chang Xu.

🧑🏻‍💻 Academic Publications

Efficientvmamba: Atrous selective scan for light weight visual mamba.
Xiaohuan Pei, Tao Huang, and Chang Xu.
Proceedings of the AAAI Conference on Artificial Intelligence (AAAI 2024). (Core Rank A*)

Localmamba: Visual state space model with windowed selective scan.
Tao Huang, Xiaohuan Pei, Chang Xu.
European Conference on Computer Vision (ECCV 2024), Workshop. (Core Rank A*)

Neural Architecture Retrieval.
Xiaohuan Pei, Yanxi Li, Minjing Dong, Chang Xu.
The Twelfth International Conference on Learning Representations (ICLR 2024). (Core Rank A*)

Contrastive code-comment pre-training.
Xiaohuan Pei, Daochang Liu, Qian Luo, Chang Xu.
IEEE International Conference on Data Mining (ICDM 2022). (Core Rank A*)

Self-attention gated cognitive diagnosis for faster adaptive educational assessments.
Xiaohuan Pei, Shuo Yang, Jiajun Huang, Chang Xu.
IEEE International Conference on Data Mining (ICDM 2022). (Core Rank A*)

TCNAS: Transformer Architecture Evolving in Clone Detection.
Hongyan Xu*, Xiaohuan Pei*, Shan You, Chang Xu.
IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2024).

📖 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
  • Provincial Prize in C++ Programming Competition

🌟 Grants

  • The National Computational Infrastructure (NCI) Adapter Scheme, Australia

Services

  • Reviewer of TPAMI, ICML, NeurIPS, ICLR, CVPR, ICCV, KDD, ICDM.

Contact: xiaohuan.pei at sydney.edu.au, terrypei123 at gmail.com