PINNACLE: PINN Adaptive ColLocation and Experimental Points Selection
📖 What it is
A methods research entry in the AI Singapore research portfolio, PINNACLE proposes an adaptive point-selection method for improving the training efficiency of Physics-Informed Neural Networks (PINNs).
🤖 Relation to AI
Built on empirical Neural Tangent Kernel (NTK) theory, the method jointly and automatically optimizes the selection of all training-point types (experimental and collocation points), significantly outperforming existing benchmarks on forward, inverse, and transfer-learning tasks—an advance at the methods layer where scientific computing meets AI.
🇸🇬 Relation to Singapore
Surfaced through the AI Singapore research portal, PINNACLE reflects Singapore’s investment in fundamental methods research for AI applied to scientific computing (AI4Science).
Sources
- AI Singapore — accessed 2026-07-06
Within 🔬 Foundational Research
A*STAR
Singapore Agency for Science, Technology and Research; primary engine for foundational and applied AI research
NUS
National University of Singapore; among Asia's top AI research universities. Launched the NUS AI Institute in March 2024, bringing together foundational AI, applied AI and societal impact research
NTU
Nanyang Technological University; major hub for AI and data science research
SMU
Singapore Management University; AI applications in business and society
SUTD
Singapore University of Technology and Design; innovation at the intersection of AI and design
AISG Research Collaborative Project with US-NSF Researchers
This collaborative project, led by Professor Jie Zhang (NTU) in partnership with MIT researchers including Associate Professor Jacob Andreas, focuses on developing trustworthy and interpretable human-AI collaborative systems for combinatorial optimization. The research establishes natural language as a robust interface for human-AI interaction, enabling systems to formulate complex optimization problems from imprecise input, perform robust AI-assisted solving, and provide explainable feedback. The outcomes aim to serve industries like logistics, manufacturing, and finance with intelligent decision-making tools, while advancing the theoretical foundations of trustworthy AI collaboration.
BadEdit: Backdooring Large Language Models By Model Editing
AI Singapore researchers present BadEdit, a novel framework for backdoor injection into pre-trained large language models through direct parameter manipulation. The method requires only 15 poisoned samples and 120 seconds to successfully inject backdoors with near 100% attack success rate while minimizing side effects on clean data. BadEdit addresses limitations of traditional weight poisoning methods by significantly reducing data requirements and computational overhead, while demonstrating versatility across diverse task domains including text classification, fact-checking, and conversational sentiment generation.
Utilizing Symbolic Regression to discover a larger class of splits for Decision Trees
This research introduces Symbolic Regression Enhanced Decision Tree (SREDT), which leverages symbolic regression to discover non-linear and multivariate splitting rules for decision trees. Compared to conventional decision trees, SREDT demonstrates superior prediction performance, more compact tree structures, faster inference time, and robustness to noise. The method uses genetic programming to search for closed-form analytical expressions, significantly outperforming standard decision trees on classification tasks.