Your Photo

Dr Yanxi Li

Research Assistant Professorship (RAP) @ NTU Sg,
PhD, Google PhD Fellow

Research Interests: Trustworthiness & Efficiency

Google Scholar LinkedIn

Employment

9/2025 - Present
Research Assistant Professorship (RAP)
AUMOVIO-NTU Corporate Lab (ANCL)
Nanyang Technological University (NTU), Singapore

Education

10/2021 - 2/2025
Doctor of Philosophy (Computer Science)
School of Computer Science, Faculty of Engineering
University of Sydney, NSW, Australia

Publications

Journal

[1]
Adversarially Robust Neural Architectures [Link] [arXiv] NEW
Minjing Dong, Yanxi Li, Yunhe Wang & Chang Xu
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025.
[2]
Neural Architecture Search via Proxy Validation [Link]
Yanxi Li, Minjing Dong, Yunhe Wang & Chang Xu
In IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2022.
[3]
Neural Architecture Tuning with Policy Adaptation [Link]
Yanxi Li, Minjing Dong, Yixing Xu, Yunhe Wang & Chang Xu
In Neurocomputing, 2022.

Conference

[1]
Optimizing Quantized Diffusion Models via Distillation with Cross-Timestep Error Correction [Link] NEW
Yanxi Li* & Chengbin Du*
In The AAAI Conference on Artificial Intelligence (AAAI), 2025.
[2]
Position: AI Scaling: From Up to Down and Out [arXiv] NEW
Yunke Wang*, Yanxi Li* & Chang Xu
In International Conference on Machine Learning (ICML), Position Track, 2025.
[3]
State Space Models: A Naturally Robust Alternative to Transformers in Computer Vision [Link] NEW
Chengbin Du, Yanxi Li & Chang Xu
In International Conference on Machine Learning (ICML) R2-FM Workshop, 2025.
[4]
Harnessing Edge Information for Improved Robustness in Vision Transformers [Link]
Yanxi Li, Chengbin Du & Chang Xu
In The AAAI Conference on Artificial Intelligence (AAAI), 2024.
[5]
Neural Architecture Retrieval [Link] [arXiv]
Xiaohuan Pei, Yanxi Li, Minjing Dong, Chang Xu
In International Conference on Learning Representations (ICLR), 2024.
[6]
Trade-off between Robustness and Accuracy of Vision Transformers [Link]
Yanxi Li & Chang Xu
In The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.
[7]
Stable Diffusion is Unstable [Link] 🚩 Spotlight
Chengbin Du, Yanxi Li, Zhongwei Qiu & Chang Xu
In Advances in Neural Information Processing Systems (NeurIPS), 2023.
[8]
Neural Architecture Search for Wide Spectrum Adversarial Robustness [Link] 🚩 Distinguished Paper Award
Zhi Cheng, Yanxi Li, Minjing Dong, Xiu Su, Shan You & Chang Xu
In The AAAI Conference on Artificial Intelligence (AAAI), 2023.
[9]
Spatial-channel Token Distillation for Vision MLPs [Link]
Yanxi Li, Xinghao Chen, Minjing Dong, Yehui Tang, Yunhe Wang & Chang Xu
In International Conference on Machine Learning (ICML), 2022.
[10]
An Image Patch Is a Wave: Phase-Aware Vision MLP [Link]
Yehui Tang, Kai Han, Jianyuan Guo, Chang Xu, Yanxi Li, Chao Xu & Yunhe Wang
In The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
[11]
One-shot Graph Neural Architecture Search with Dynamic Search Space [Link]
Yanxi Li, Zean Wen, Yunhe Wang & Chang Xu
In The AAAI Conference on Artificial Intelligence (AAAI), 2021.
[12]
Neural Architecture Dilation for Adversarial Robustness [Link]
Yanxi Li, Zhaohui Yang, Yunhe Wang & Chang Xu
In Advances in Neural Information Processing Systems (NeurIPS), 2021.
[13]
Prioritized Architecture Sampling with Monto-Carlo Tree Search [Link]
Xiu Su, Tao Huang, Yanxi Li, Shan You, Fei Wang, Chen Qian, Changshui Zhang & Chang Xu
In The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021.
[14]
Neural Architecture Search in A Proxy Validation Loss Landscape [Link]
Yanxi Li, Minjing Dong, Yunhe Wang & Chang Xu
In International Conference on Machine Learning (ICML), 2020.
[15]
Adapting Neural Architectures Between Domains [Link]
Yanxi Li, Zhaohui Yang, Yunhe Wang & Chang Xu
In Advances in Neural Information Processing Systems (NeurIPS), 2020.

Pre-printing

[1]
GPT Self-Supervision for a Better Data Annotator [arXiv]
Xiaohuan Pei, Yanxi Li, Zijian Wang & Chang Xu
In arXiv preprint. arXiv:2306.04349, 2023.

* = Equal contribution.

Awards and Honors

2025
Research Assistant Professorship (RAP)
Nanyang Technological University (NTU), Singapore.
2023
Google PhD Fellowship
In the field of Machine Perception, Speech Technology and Computer Vision. One of the 81 recipients globally.
2023
Distinguished Paper Award
"Neural Architecture Search for Wide Spectrum Adversarial Robustness". In The AAAI Conference on Artificial Intelligence (AAAI), 2023.
2021
Faculty of Engineering Research Scholarship
Faculty of Engineering, University of Sydney

Professional Service

Journal Reviewer

IEEE TPAMI, IEEE TNNLS (was TNN), IEEE TMM, TMLR, Neurocomputing.

Conference Reviewer

NeurIPS, ICML, CVPR, ICLR, ICCV, ECCV, AAAI, ICDM, ACM SIGKDD, ACM MM, IJCAI.