About me
I’m now a Senior Research Engineer at Agency for Science, Technology and Research (A*STAR), Singapore. I’m also currently a part-time PhD candidate at Nanyang Technological University(NTU), Singapore(南洋理工大学), under the supervision of Prof. Weisi Lin(林维斯) in Media and Interactive Computing Lab (MICL). Prior to that, I received my master’s degree in National University of Singapore (NUS)(新加坡国立大学) and bachelor’s degree in Sun-yat-sen University,(SYSU), China(中山大学).
My current research focus lies on Neural Network Compression (Pruning, quantizaiton, etc.) Efficient deep learning, computer vision, etc. I have published many papers 
📢 Openings
We are hiring! Our team at I2R, A*STAR is looking for multiple master internship students. We work on cutting-edge technologies for truly efficient, secure and practical large AI systems, including LLMs/VLMs and more.
- Requirements: solid project or research experience in deep learning, a strong problem-solving mindset and good development skills. Candidates should be currently matriculated in Singapore.
- We offer: internship compensation, a state-of-the-art R&D platform, and opportunities for referral. Team members come from Stanford, PKU, BJTU, NUS and NTU, with publications in top venues (CVPR, ICCV, ECCV, NeurIPS, ACL, TPAMI, TIP, TNNLS, etc.).
Interested candidates are welcome to send their CVs to Xu_Kaixin@a-star.edu.sg.
🔥 News
- 10/26, I was selected as a Top Reviewer of NeurIPS 2026 !
- 07/26, 1 paper accepted by ECCV 2026 !
- 07/25, 1 journal paper accepted by TPAMI (IF: 20.8) !
- 03/25, I was awarded with A*STAR Sponsorship Awards!
- 12/2024, I gave a talk in the 2024 International Research Forum of AI+ at Peng Cheng Laboratory (PCL), Shenzhen.
- 09/2024, Codes for our ECCV 2024 paper released!
- 07/2024, 1 paper accepted by ECCV 2024!
- 10/2023, Codes for our ICCV’23 paper is finally released on GitHub!!
- 10/2023, We ranked 26 in “AI+ visual feature coding (AI+视觉特征编码)” Competition in Datafountain.
- 10/2023, 1 paper accepted by ICCV 2023!
- 07/2023, 1 paper accepted by ICIP 2023!
📝 Publications
BLOB-Q: Boosting Low Bit ViT Quantization via Global Optimization on Model Distortion
[Paper]
[Code]
Wang Zhe Mark*, Kaixin Xu, Xue Geng, Fen Fang, Mohamed M. Sabry Aly, Xulei Yang, Min Wu, Weisi Lin
Efficient Distortion-minimized Layerwise Pruning
[Paper]
Kaixin Xu, Zhe Wang, Runtao Huang, Xue Geng, Jie Lin, Xulei Yang, Min Wu, Xiaoli Li, Weisi Lin
📜 Invited Talks
- 12/2024, “Towards Accurate and Efficient Visual Model Pruning”, 2024 International Research Forum of AI+, invited talk by Dr. Chen Zhuo.
🏫 Educations
- 01/2023, started first-year part-time Ph.D. at NTU
- 07/2020, obtained Master of Technology (M.Tech) degree from ISS, NUS, Singapore
- 07/2019, obtained Bachelor of Engineering degree from SYSU, China
🏆 Honors and Awards
- 2025
- 2017, 2018
- Scholarship Awards for 2 years at SEIT School, Sun-yat-sen University (SYSU), Guangzhou, China.
👔 Work Experiences
- 04/2023, promoted as Senior Research Engineer
- 08/2020, joined I2R, A*STAR as a full-time Research Engineer
- 02/2020, started student attachment in I2R, A*STAR