Scientific Computing and Intelligence Group (Scaling Group) is in the Department of Mathematics at National University of Singapore, led by Dr. Liu Yang (杨柳).
Intelligence is commonly understood as the ability to acquire and apply knowledge, adapt to unfamiliar situations, and solve new problems. Yet intelligence need not be confined to language.
Our work centers on numerical intelligence: the ability to acquire and apply knowledge from numerical context. We develop In-Context Operator Networks (ICON) as a framework that enables frozen models to infer and apply relations from numerical context across scientific and social systems. We also explore the synergy between linguistic and numerical intelligence. To accelerate this research, we develop self-evolving agents (try our EvE) for automated discovery of algorithms and beyond.
We are looking for passionate new students, postdocs, and visiting scholars to join the team!
Funding. We gratefully acknowledge support from the National Research Foundation, Singapore under the NRF Fellowship (2025–2030; Project No. NRF-NRFF17-2025-0006).
Sep 07 2026
Congratulations to Jun Zhai for leading team S17 to a 3rd-place finish out of 256 participants in IGP24! Read Jun’s retrospective blog post: Producing Mathematics, Understanding Mathematics.
Jul 30 2026
Our paper A Foundation Model of Numerical Intelligence with Cross-Disciplinary Generalization is now available on arXiv. UNICON is a single frozen model that infers system-specific predictive relations from graph-based numerical examples and approaches specialist performance across disciplines absent from training.
Jun 18 2026
Our paper Agentic Symbolic Search: Characterizing PDEs Beyond Hand-crafted Expressions, Meshes, and Neural Networks is now available on arXiv.
Jun 17 2026
Our paper Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization is accepted as a poster at the 3rd ICML Workshop on AI for Math: Toward Self-Evolving Scientific Agents. It was first made available on arXiv on Apr 25, 2026.
Jun 10 2026
Our paper Chain of Operators: An Inference-Time Harness for In-Context Operator Learning is now available on arXiv.
Jun 10 2026
Our paper VICX: Generalizable Robot Manipulation via Video Generation and In-Context Operator Network (Project) is now available on arXiv.
Jun 07 2026
Our paper Self-Evolving Scientific Agent Designs Physically-Reasoned Whitebox Fluid Control is now available on arXiv.
May 26 2026
Our paper Graph In-Context Operator Networks for Generalizable Spatiotemporal Prediction is accepted by the 2nd ICML Workshop on Foundation Models for Structured Data. It was first made available on arXiv on Mar 13, 2026.
May 09 2026
Our paper Evolving Ensemble of Agents (GitHub) is now available on arXiv. We introduce EvE: a decentralized, co-evolving system of coding agents and code repositories.
... see all news