I am a final-year Ph.D. candidate in CS at UT-Arlington, with a Master's degree from Shanghai Jiao Tong University and a Bachelor's degree from Northwestern Polytechnical University. My research focuses on the intersection of artificial intelligence and brain science, with an emphasis on brain-inspired AI and AI for Biomedical and Health Sciences. My study covers brain network analysis, image classification, domain adaptation/generalization, semi-supervised learning, and LLMs.

I am on the job market now, seeking full-time positions.

Publications

[1] Yu, X., Huang, Z., and Zhang, Z., 2025. Feature Fusion Transferability Aware Transformer for Unsupervised Domain Adaptation. IEEE/CVF Winter Conference on Applications of Computer Vision.

[2] Yu, X., Zhang, L., Wu, Z. and Zhu, D., 2024. Core-Periphery Multi-Modality Feature Alignment for Zero-Shot Medical Image Analysis. IEEE Transactions on Medical Imaging.

[3] Huang, Z.^*, Yu, X.^*, and Zhu, D., and Hughes, M.C, 2024. InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning. ICML.

[4] Shu, Z.^*, Yu, X.^*, Wu, Z., et al, 2024. Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile Devices. NeurIPS.

[5] Ma, C., Jiang, H., Chen, W., Wu, Z., Yu, X., et al, 2024. Eye-gaze Guided Multi-modal Alignment Framework for Radiology. NeurIPS.

[6] Yu, X., Zhang, L., Wu, Z., et al, 2024. CP-CLIP: Core-Periphery Feature Alignment CLIP for Zero-Shot Medical Image Analysis. MICCAI.

[7] Yu, X., Zhang, L., Zhang, J., et al, 2024. Gyri vs. Sulci: Core-Periphery Organization in Functional Brain Networks. MICCAI.

[8] Yu, X., Huang, Z., Wang, L., Liu, T., and Zhu, D., 2023. NoisyNN: Exploring the Impact of Information Entropy Change in Learning Systems. arXiv preprint arXiv:2309.10625.

[9] Yu, X., Zhu, D. and Liu, T., 2023. Robust Core-Periphery Constrained Transformer for Domain Adaptation. arXiv preprint arXiv:2308.13515.

[10] Yu, X., Zhang, L., Lyu, Y., Liu, T. and Zhu, D., 2023. Supervised Deep Tree in Alzheimer’s Disease. ISBI.

[11] Yu, X., Zhang, L., Zhao, L., Lyu, Y., Liu, T. and Zhu, D., 2022. Disentangling Spatial-Temporal Functional Brain Networks via Twin-Transformers. arXiv preprint arXiv:2204.09225.

[12] Yu, X., Hu, D., Zhang, L., Huang, Y., Wu, Z., Liu, T., Wang L., Lin W., Zhu D., and Li G., 2022, Longitudinal Infant Functional Connectivity Prediction via Conditional Intensive Triplet Network. MICCAI. (Early Acceptance)

[13] Yu, X., Scheel, N., Zhang, L., Zhu, D. C., Zhang, R. and Zhu, D., 2021, Free water in T2 FLAIR white matter hyperintensity lesions. Alzheimer's & Dementia, 17, p.e057398.

[14] Lyu, Y., Yu, X., Zhu, D. and Zhang L., 2022, Classification of Alzheimer's Disease via Vision Transformer. In The 15th PErvasive Technologies Related to Assistive Environments Conference.

Projects

NoisyNN: Exploring the Impact of Information Entropy Change in Learning Systems (Individual Project)

Triggered by the impressive performance improvement achieved through the addition of noise, I delve deep into the mechanism explaining why adding noise would work by proposing a new learning theory. In this context, I consider additional information beyond the image itself as noise, with the application of this theory being NoisyNN.

Free Water in White Matter Hyperintensity (Collaborate with MSU and UT Southwestern)

We proposed a data processing framework to assess FW distributions in WMH and normal-appearing WM as well as in different WM fiber tracts.

Longitudinal Functional Connectivity Prediction (Collaborate with UNC)

We proposed a conditional intensive triplet network (CITN) for longitudinal prediction of the dynamic development of infant FC, which can traverse FCs within a long duration and predict the target FC at any specific age during infancy.

Disentangling Brain Networks using Twin-Transformer (Collaborate with UGA)

We proposed a Twin-Transformers framework to simultaneously infer common and individual functional networks in both spatial and temporal space, in a self-supervised manner.

Exploring core-periphery relationship between Gyri and Sulci (Collaborate with UGA)

We designed a novel Twin-Transformer framework to explore and unveil the unique functional roles of gyri and sulci as well as their relationship and interaction in the whole brain function.

Instill Core-Periphery Principle into Transformers (Work with UGA)

This work provides novel insights for brain-inspired AI: we can instill the efficient information communication mechanism of BNNs into ANNs by infusing similar organizational principles of BNNs into ANNs.

Professional Activity

Reviewer

-IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS)
-IEEE International Symposium on Biomedical Imaging 2025
-IEEE/CVF Winter Conference on Applications of Computer Vision 2025
-Medical Image Computing and Computer Assisted Interventions 2021, 2023, 2024
-Cerebral Cortex
-Medical Image Analysis
-Frontiers in Neuroimaging
-Frontiers in Neuroscience

Internship

-Research Intern, The University of North Carolina at Chapel Hill, Chapel Hill, NC, June-August 2021
-Data Science Intern, Epsilon, Remote, May-August 2023
-Data Science Intern, Epsilon, Remote, May-August 2024

Hobbies

Roadtrip, Hiking, Tennis.

Step into nature is one of my favorite activities during my leisure time. I enjoy going hiking in randomly selected national parks with Pet friends.