Date and Time (China standard time): Tuesday, Sep 1, 10:00 AM – 11:00 AM

Location: WDR 1005

Zoom: 949 3625 2193, Passcode: dkumath

Title: In-Context Operator Networks (ICON): A Research Program for Numerical Intelligence.

Speaker: Liu Yang, National University of Singapore

Abstract: Intelligence is commonly understood as the ability to acquire knowledge, adapt to unfamiliar situations, and solve new problems. Large language models exhibit this capacity by inferring task-relevant knowledge from textual context and applying it to new tasks. Yet intelligence need not be confined to language. Scientific and social systems often reveal themselves numerically before we can fully describe them in words. We call the ability to acquire and apply knowledge from numerical context “numerical intelligence” and view it as a foundational pillar of artificial intelligence alongside linguistic intelligence.

We proposed “In-Context Operator Learning” paradigm and the corresponding model “In-Context Operator Networks” (ICON) for numerical intelligence. We will show how a single ICON model (without fine-tuning) manages multiple families of PDE problems. In our latest work, we trained Unified ICON (UNICON) on real-world datasets across different disciplines, including weather, hydrology, power, and traffic. And it generalizes to completely novel disciplines, e.g. web activity. Apart from the model itself, we can also design “harness” for ICON due to the flexibility of the context. We will introduce building blocks, including “chain of operators” and “contextual ensemble learning”. With such techniques, we outperformed state-of-the-art (SOTA) expert models in disciplines unseen in training.

To accelerate our research, we built Evolving Ensemble of Agents (EvE), a decentralized agent system that co-evolves with downstream task solutions. We will show how EvE helps ourselves design ICON architectures and harness systems, and beyond. See more details on the website: https://scaling-group.github.io/

Bio: Dr. Yang is currently an Assistant Professor in the Department of Mathematics at National University of Singapore (NUS), awarded the NUS Presidential Young Professorship and National Science Foundation Fellowship. Before joining NUS, he was an Assistant Adjunct Professor in the Department of Mathematics at UCLA. He obtained his Ph.D. in Applied Mathematics from Brown University in 2021, and B.E. in Engineering Mechanics from Tsinghua University in 2016.

He is interested in building AI foundation models and agents for scientific challenges, including multi-physics prediction, control design, inverse problems, etc. See more details on the website: https://scaling-group.github.io/