Hi, I’m an undergrad senior at the University of Minnesota (UMN), and I have been lucky to be advised by Prof. Ju Sun in GLOVEX and Prof. Shashi Shekhar. Among many exciting areas, I work in the fields of federated learning, foundational machine learning and AI for healthcare. I have also long been interested in disentangled representation learning, computer vision, optimization, and causal AI.
I have been the recipient of Google CS research mentorship with Dr. Feng Yang, UMN undergrad research scholarships and the CS&E departmental scholarships. I serve as a Math and CS reviewer for the Minnesota Undergraduate Research & Academic Journal (MURAJ), and as a volunteer in ICLR, ICML and NeurIPS 2021.
I have been fortunate to collaborate with Cisco Research in Dr. Myungjin Lee’s team to develop scalable next-generation federated learning system Flame, and I’m currently working at Cisco as a research intern.
I will be joining University of Pennsylvania in pursuing a Ph.D. in the Computer and Information Science Department with Prof. Mingmin Zhao.
You can also find an article about me on https://cse.umn.edu/cs/news/cspotlight-experiencing-research-undergrad.
Check my most recent CV here.
2018-2022 - Bachelor of Science in Computer Science with a Math minor, University of Minnesota, Twin Cities.
2022-X Ph.D. in Computer and Information Science, University of Pennsylvania.
Advisors: Prof. Mingmin Zhao
Preprint / Submitted
 Le Peng, Gaoxiang Luo, Andrew Walker, Ju Sun, Christopher J Tignanelli, et al. Evaluation of Federated Learning Variations for COVID-19 Diagnosis Using Chest Radiographs from 42 US and European Hospitals. Under review of JAMIA.
 Majid Farhadloo, Carl Molnar, Gaoxiang Luo, Yan Li, Shashi Shekhar, et al. SAMCNet for Spatial-configuration-based Classification: A Summary of Results. Accepted to ACM SIGKDD 2022.
 John Burns, Zachary Zaiman, Gaoxiang Luo, Le Peng, et al. Pixel Color Averages by Race in Chest X-Ray. Under review of MICCAI 2022.
 Jayant Gupta, Carl Molnar, Gaoxiang Luo, Joe Knight, Shashi Shekhar. Towards Comparative Physical Interpretation of Spatial Variability Aware Neural Networks: A Summary of Results.
I’m interning at Cisco Research in Dr. Myungjin Lee’s team, to develop new technologies for machine learning systems: working on building the next generation open-source scalable federated learning (FL) system Flame, and dealing with common issues such as data distribution discrepancy. https://research.cisco.com/
Improved AUPRC of chest x-ray COVID-19 classification by 9% compared to local training, by implementing real-data federated learning with several partner institutes. The case study is featured in the white paper – Federated Learning for Healthcare Using NVIDIA Clara. (Advisor: Prof. Ju Sun})
Rib Fracture Detection (Cisco Research Fellow)
Co-leading an initiative to develop an accurate and reliable automated fracture detection method combining multi-modal and semi-supervised approaches on chest CT scans and X-rays, to reduce the delays and errors that come along with the current practice of manually identifying fractures. This project is funded by Cisco Research. This work is accepted to two undergraduate research conferences NCRC 2022 and NCUR 2022. (Advisor: Prof. Christopher Tignanelli & Prof. Ju Sun)
Truncated Transfer Learning
Proposed a novel truncated transfer learning (TL) method in medical imaging classification under data-poor regimes, that consistently leads to comparable or superior performance than its non-truncated counterpart as well as other TL strategies. Our method can be applied to different deep neural networks and generalized to other tasks (e.g., segmentation). See Publication . (Advisor: Prof. Ju Sun)
Outperformed current state-of-the-art point set classifiers in terms of accuracy and F1-score on our tumor cell datasets by designing a novel Spatial-interaction Aware Multi-Category deep neural Network (SAMCNet), contributing location representation and point pair attention layers for multi-categorical point set classification. See Publication . (Advisor: Prof. Shashi Shekhar)
Added to the transparency of Spatial Variability Aware Neural Networks (SVANNs) by exploring the physical interpretation based on geographically heterogeneous features (e.g., remote sensing indices), using a case study of wetland mapping. See Publication . (Advisor: Prof. Shashi Shekhar)
Selected Course Projects
CSCI 8980 Think Deep Learning (Fall 2020)
- A Survey of Deep Semantic Segmentation on Computerized Tomography
- 3D Rib Fracture Segmentation on Computed Tomography
CSCI 5525 Machine Learning: Analysis and Methods (Spring 2021)
CSCI 8980 Modern Machine Learning (Fall 2021)
- 2021 – Google CSRMP Scholar (Mentor: Dr. Feng Yang)
- 2021 – Undergraduate Research Scholarship (UMN) x2
- 2021 – Maximillian Lando Scholarship (CS&E Merit Department)
- 2018-2021 – CSE Dean’s List
- 2021 – CSpotlight
- 2021 – Tau Beta Pi
 G Luo. Wetland Mapping Using Spatial Variability Aware Neural Networks (SVANN), In 2021 Spring UMN Undergrad Research Symposium. https://ugresearch.umn.edu/symposium/presenters2021/Gaoxiang-Luo
 G Luo. Application of Artificial Intelligence to Help Fight COVID-19, In Minnesota Undergraduate Research & Academic Journal (MURAJ), Vol.4 No.3, 2021. https://pubs.lib.umn.edu/index.php/muraj/article/view/3876
 CSpotlight: Experiencing research as an undergrad, In Departmental News. May 12, 2021. https://cse.umn.edu/cs/news/cspotlight-experiencing-research-undergrad
 Three students present at spring Undergraduate Research Symposium, In Departmental News. May 12, 2021. https://cse.umn.edu/cs/news/three-students-present-spring-undergraduate-research-symposium
 First gen student chosen for Google mentorship program, In Departmental News. Nov. 19, 2021. https://cse.umn.edu/cs/news/first-gen-student-chosen-google-mentorship-program
- CSCI 2011 Discrete Math (Fall 2020 & Spring 2021)
- CSCI 2033 Computational Linear Algebra (Fall 2021)
- Minnesota Undergraduate Research & Academic Journal, Math and Computer Science Reviewer, Oct. 2020 - May 2022
- ICLR 2021, May 2nd - 8th, 2021
- ICML 2021, July 18th - 24th, 2021
- NeurIPS 2021, December 6th - 14th, 2021
Foundations of Machine Learning by by Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar
Understanding Machine Learning: From Theory to Algorithms by Shai Shalev-Shwartz and Shai Ben-David