The Hong Kong University of Science and Technology (Guangzhou)
I'm Hua XU (εΎη»), a Year 3 undergraduate student at HKUST(GZ) majoring in Data Science, with a hybrid background in AI and Biology.
I'm eagerly looking for research internships (26Summer) and Ph.D. opportunities (27Fall) in North America, Europe and Asia. Reach out to me if you think we have a shared research interest!
My research is driven by a quest to understand the fundamental principles of intelligence. I aim to leverage these insights to build more robust AI systems while deciphering the computational mechanisms of the brain. Specifically, my interests lie at the intersection of Neuroscience, Cognitive Science, and AI (NeuroAI). Currently, I am focusing on discrete diffusion models with Gwen Yidou Weng and Prof. Anji Liu in StarAI Lab at UCLA, aiming to ensure controllable generation and investigate their probabilistic underpinnings.
I was working with Prof. Yutao Yue on irregular multivariate time series prediction. During my internship at HKU Institute of Data Science, I was fortunate to get guidance from Prof. Andrew Luo. Prior to that, I worked actively with Prof. Julie Qiaojin LIN on synthetic biology.
I'm also contributing to GrowAI, a thriving open-source research community exploring the intersections of AI and Cognitive Science, and we are currently working on evaluating the reasoning abilities of video generative models from a cognitive perspective. Join our slack if you are interested!
Warning
Problem: The current name of your GitHub Pages repository ("Solution: Please consider renaming the repository to "
http://".
However, if the current repository name is intended, you can ignore this message by removing "{% include widgets/debug_repo_name.html %}" in index.html.
Action required
Problem: The current root path of this site is "baseurl ("_config.yml.
Solution: Please set the
baseurl in _config.yml to "Education
-
The Hong Kong University of Science and Technology (Guangzhou)Data Science and Analytics Thrust UndergraduateSep. 2023 - present -
University of California, Los AngelesExchangeSep. 2025 - Jan. 2026
Honors & Awards
-
National Scholarship (sole awardee of the year)2024
-
Gold Medal and Nomination for Best Basic Parts in iGEM2024
News
Selected Publications (view all )
Building Interpretable, Trustworthy Systems for Neural Signal Decoding
Hua XU
40th Annual AAAI Conference on Artificial Intelligence (AAAI) 2026 Accepted
Undergraduate Consortium Section. This is a research proposal focusing on developing interpretable and trustworthy neural signal decoding systems.
Building Interpretable, Trustworthy Systems for Neural Signal Decoding
Hua XU
40th Annual AAAI Conference on Artificial Intelligence (AAAI) 2026 Accepted
Undergraduate Consortium Section. This is a research proposal focusing on developing interpretable and trustworthy neural signal decoding systems.
IMTS is Worth Time Γ Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction
Zhangyi Hu*, Jiemin Wu*, Hua XU*, Mingqian Liao, Ninghui Feng, Bo Gao, Songning Lai, Yutao Yue (* equal contribution)
42nd International Conference on Machine Learning (ICML) 2025 Accepted
Leveraging visual pretrained masked autoencoders to address irregular multivariate time series prediction challenges by converting sparse data into time Γ channel image-like patches, capturing cross-channel interactions with superior accuracy and strong few-shot performance.
IMTS is Worth Time Γ Channel Patches: Visual Masked Autoencoders for Irregular Multivariate Time Series Prediction
Zhangyi Hu*, Jiemin Wu*, Hua XU*, Mingqian Liao, Ninghui Feng, Bo Gao, Songning Lai, Yutao Yue (* equal contribution)
42nd International Conference on Machine Learning (ICML) 2025 Accepted
Leveraging visual pretrained masked autoencoders to address irregular multivariate time series prediction challenges by converting sparse data into time Γ channel image-like patches, capturing cross-channel interactions with superior accuracy and strong few-shot performance.