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).
Our work centers on In-Context Operator Networks (ICON), a foundation-model framework for scientific problems. Through this lens, we study directions including multi-physics prediction, physical modeling, and embodied AI. To accelerate our research, we also develop agents (EvE) for automated discovery of algorithms and beyond.
We are looking for passionate new students, postdocs, and visiting scholars to join the team!
May 09 2026
Our paper Evolutionary Ensemble of Agents (GitHub) is now available on arXiv. We introduce EvE: a decentralized evolutionary ensemble of coding agents co-evolving with code repositories.
Apr 28 2026
Our paper In-context modeling as a retrain-free paradigm for foundation models in computational science is now available on arXiv.
Apr 25 2026
Our paper Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization is now available on arXiv.
Mar 14 2026
We released icon-core, an open-source research infrastructure package for In-Context Operator Network (ICON) development. It provides standard models and algorithms, benchmark datasets, training pipelines, and development utilities, featuring built-in support for AI coding assistants like Claude Code.
Mar 13 2026
Our paper Graph In-Context Operator Networks for Generalizable Spatiotemporal Prediction is now available on arXiv.
Nov 25 2025
Our paper VICON: Vision In-Context Operator Networks for Multi-Physics Fluid Dynamics Prediction is accepted by Transactions on Machine Learning Research. This work was done in collaboration with researchers from UCLA and UCSD.
August 2025
🏆 Liu Yang has been awarded the prestigious Singapore National Research Foundation Fellowship (class of 2025), receiving over SGD 3 million in research funding. This highly competitive honor is granted to only about 10 researchers in Singapore each year.
Jun 15-18 2025
Liu Yang will participate UNCECOMP2025 in Rhodes, Greece. Let me know if you are around and interested in meeting up!
Apr 21 2025
Our paper Fine-tune language models as multi-modal differential equation solvers is published on Neural Networks.
... see all news