🔥 News
- Dec, 2025
Upcoming NeurIPS workshop Non-Euclidean Foundation Models and Geometric Learning Workshop @NeurIPS 2025 | Home
- Aug, 2025
Our paper RephQA received the Blue Sky Best Paper Award at ACM KDD 2025.
- Jul, 2025
Talk at DeepLearn 2025 on Graph foundation models and Non-Euclidean foundation models.
- Aug, 2025
Tutorial on Non-Euclidean Foundation Models. International Conference on Knowledge Discovery and Data Mining (KDD).
- May, 2025
Keynote on AI agent for science. WebConf 2025.
- May, 2025
Organized Workshop on Graph Signal Processing (GSP 2025).
- May, 2025
Organized Workshop on Non-Euclidean Foundation Models. WebConf 2025.
- April, 2025
Invited Talk on Hyperbolic Foundation Models. University of Illinois Urbana Champaign.
- April, 2025
Invited Talk on Hyperbolic Large Language Models. Queen's University.
- Dec, 2024
Invited Talk on Time Series Representation Learning. Amazon.
- Nov, 2024
Organized Workshop on Time Series Foundation Models. International Conference on AI in Finance (ICAIF 2024)
- Oct, 2024
Invited Talk on Hyperbolic Representation Learning. University of Rochester.
- Sep, 2024
Keynote speech on Hyperbolic Representation Learning and Foundation Models. IMS-NTU Joint Workshop on Applied Geometry for Data Sciences.
- Aug, 2024
Invited Talk on LLM for Telecom.Ericsson, Sweden.
- Aug, 2024
The lab has received an NSF core program award on building foundation models for scientific discovery.
- Jun, 2024
Rex gave a tutorial on Machine Learning in Network Science at NetSci 2024.
Vision
We are a group of data-driven machine learning enthusiasts who are primarily interested in building unified approaches to integrate and learn from complex real-world data. Beyond just text and images, we also build novel deep learning models that consider graphs, time series, geometry and tabular data, and use them to solve a wide array of applications in domains such as biology, medicine, chemistry, physics, neuroscience, social networks, science of science and supply chain.
Motivated by real-world use cases, we focus on efficient and scalable techniques that combine relational reasoning, multimodal learning, geometric deep learning and foundation models. Furthermore, we are actively doing research in trustworthy deep learning to allow safe, transparent and reliable deployment of such models.
