Scholar
Shangqing Xu
Google Scholar ID: LxyfYAUAAAAJ
Georgia Institute of Technology
Citations & Impact
Citations
138
H-index
5
i10-index
5
Publications
7
Co-authors
10
list available
Contact
No contact links provided.
Publications
Resume (English only)
Academic Achievements
- 1. Time-MMD: A New Multi-Domain Multimodal Dataset for Time Series Analysis. Annual Conference on Neural Information Processing Systems (NeurIPS), 2024. 2. Misconfidence-based Demonstration Selection for LLM In-Context Learning. arXiv:2401.06301 (2024). 3. TransEHR: Self-Supervised Transformer for Clinical Time Series Data, Machine Learning for Health (ML4H, Proceedings Track), 2023. 4. Unsupervised Clustering through Gaussian Mixture Variational AutoEncoder with Non-Reparameterized Variational Inference and Std Annealing. 2020 International Joint Conference on Neural Networks (IJCNN).
Research Experience
- Conducting research in Computational Science and Engineering at Georgia Tech, focusing on data-efficient ML, large language models (LLMs) with external guidance, multi-modality, and ML theory.
Education
- 1. Ph.D. in Computational Science and Engineering at Georgia Tech, advised by Prof. B. Aditya Prakash; 2. Master's degree in Computational Science and Engineering at Georgia Tech; 3. Bachelor's degree in Computer Science and Technology at Tsinghua University, worked with Prof. Wentao Han, Prof. Jie Tang, and Prof. Dan Pei.
Background
- Research Interests: self-evolving AI, machine learning, real-world NLP tasks. Field of Study: Computational Science and Engineering.
Miscellany
- If you are interested in how my name is pronounced in Chinese, it sounds like 'Shawn-Chin Shoo'. I'm especially interested in reading novels. My favorites are Le Comte de Monte-Cristo and the Foundation series (which contributes to my research interest fairly a lot). Visual novel games are also of my preferences, among which I enjoy Steins; Gate and 13 Sentinels: Aegis Rim the most.
