Haolei Bai

👋 Hi! I’m Haolei Bai, a first-year Ph.D. student at Rochester Institute of Technology, advised by Prof. Zhiqiang Tao. Previously, I was a visiting student at the ENCODE Lab, Westlake University, where I was fortunate to be advised by Prof. Huan Wang. Before that, I earned my M.S. in Signal Processing from Nanyang Technological University, under the supervision of Prof. Alex Kot.

My research interests include efficient AI, particularly large language models (LLMs), vision-language models (VLMs), and diffusion language models (dLLMs). I am currently exploring topics related to autonomous driving.

News

Aug 24, 2026	I am excited to begin my Ph.D. journey under the supervision of Prof. Zhiqiang Tao. A challenging yet fascinating new chapter begins!
Jan 22, 2026	ERC-SVD has been accepted to CPAL 2026! This is my first research paper. I am sincerely grateful to all our collaborators, with special thanks to Prof. Huan Wang for his invaluable guidance and support!
Feb 28, 2025	Graduated from Nanyang Technological University.
Jan 06, 2025	Joined ENCODE Lab at Westlake University as a visiting student.

Publications & Preprints

^* Equal contribution ^† Corresponding author

arXiv’26

MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?

Xingze Zou^*, Jing Wang^*, Yuhua Zheng, Xueyi Chen, Haolei Bai, Lingcheng Kong, Syed AR Abu-Bakar, Zhaode Wang, Chengfei Lv, Haoji Hu^†, and Huan Wang^†

arXiv preprint arXiv:2602.11715, 2026

arXiv Bib Website

@article{zou2026mobilekernelbench,
  title = {MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?},
  author = {Zou, Xingze and Wang, Jing and Zheng, Yuhua and Chen, Xueyi and Bai, Haolei and Kong, Lingcheng and Abu-Bakar, Syed AR and Wang, Zhaode and Lv, Chengfei and Hu, Haoji and Wang, Huan},
  journal = {arXiv preprint arXiv:2602.11715},
  year = {2026},
}

arXiv’26

DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels

Haolei Bai, Lingcheng Kong, Xueyi Chen, Jianmian Wang, Zhiqiang Tao, and Huan Wang^†

arXiv preprint arXiv:2602.11715, 2026

arXiv Bib Website

@article{bai2026dice,
  title = {DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels},
  author = {Bai, Haolei and Kong, Lingcheng and Chen, Xueyi and Wang, Jianmian and Tao, Zhiqiang and Wang, Huan},
  journal = {arXiv preprint arXiv:2602.11715},
  year = {2026},
}

CPAL’26

ERC-SVD: Error-Controlled SVD for Large Language Model Compression

Haolei Bai, Siyong Jian, Tuo Liang, Yu Yin, and Huan Wang^†

In Third Conference on Parsimony and Learning, 2026

arXiv Bib Website

@inproceedings{bai2026ercsvd,
  title = {ERC-SVD: Error-Controlled SVD for Large Language Model Compression},
  author = {Bai, Haolei and Jian, Siyong and Liang, Tuo and Yin, Yu and Wang, Huan},
  booktitle = {Third Conference on Parsimony and Learning},
  year = {2026},
}