mlsanityData to 7 Oct 2026

A foundation model of numerical intelligence with cross-disciplinary generalization

arXiv 2607.28432 ↗First posted 30 Jul 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Intelligence is commonly understood as the ability to acquire and apply 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. For scientific and social systems, we need models that acquire and apply knowledge from numerical context-an ability we call numerical intelligence. Here we introduce UNified In-Context Operator Networks (UNICON), a foundation model that exhibits numerical intelligence across disciplines. Using graph-based examples from a system as context, UNICON infers the predictive relation shared across them and applies it to queries from the same system. Across scientific and social systems, including those from disciplines absent from training, the same model approaches specialist performance without retraining. Combining UNICON with language-model agents to perform contextual ensemble learning (CEL) yields further gains, enabling it to surpass state-of-the-art specialists in a discipline unseen during training. We further show that training-corpus diversity improves generalization to unseen disciplines. Together, these results establish UNICON as a foundation model of numerical intelligence and position it as a building block for a broader ecosystem of artificial intelligence.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 29 of its 79 references that are in the map. First posted on arXiv 30 Jul 2026.

Builds on

29 of 79 references.

References · 29

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  3. 2020Fourier Neural Operator for Parametric Partial Differential Equationscited by 2,806
  4. 2019DeepONet: Learning nonlinear operators for identifying differential equations based on the universal approximation theorem of operatorscited by 1,965
  5. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  6. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  7. 2020Learning to Simulate Complex Physics with Graph Networkscited by 867
  8. 2020Learning Mesh-Based Simulation with Graph Networkscited by 840
  9. 2019Graph WaveNet for Deep Spatial-Temporal Graph Modelingcited by 820
  10. 2017DGM: A deep learning algorithm for solving partial differential equationscited by 674
  11. 2017The Deep Ritz method: A deep learning-based numerical algorithm for solving variational problemscited by 581
  12. 2019Machine Learning for Fluid Mechanicscited by 380
17 more
  1. 2022Message Passing Neural PDE Solverscited by 368
  2. 2017PDE-Net: Learning PDEs from Datacited by 304
  3. 2023WeatherBench 2: A benchmark for the next generation of data-driven global weather modelscited by 227
  4. 2022Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecastingcited by 122
  5. 2021PyTorch Geometric Temporal: Spatiotemporal Signal Processing with Neural Machine Learning Modelscited by 118
  6. 2023In-Context Operator Learning with Data Prompts for Differential Equation Problemscited by 98
  7. 2022Learned Turbulence Modelling with Differentiable Fluid Solvers: Physics-based Loss-functions and Optimisation Horizonscited by 39
  8. 2024Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learningcited by 32
  9. 2024PDE Generalization of In-Context Operator Networks: A Study on 1D Scalar Nonlinear Conservation Lawscited by 30
  10. 2021Conditional Neural Relational Inference for Interacting Systemscited by 28
  11. 2020Machine Learning and Computational Mathematicscited by 22
  12. 2024VICON: Vision In-Context Operator Networks for Multi-Physics Fluid Dynamics Predictioncited by 22
  13. 2024Zebra: In-Context Generative Pretraining for Solving Parametric PDEscited by 14
  14. 2025Probabilistic operator learning: generative modeling and uncertainty quantification for foundation models of differential equationscited by 9
  15. 2026Graph In-Context Operator Networks for Generalizable Spatiotemporal Predictioncited by 3
  16. 2026Chain of Operators: An Inference-Time Harness for In-Context Operator Learningcited by 2
  17. 2026AirQualityBench: A Realistic Evaluation Benchmark for Global Air Quality Forecastingcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Emergent Abilities in Large Language Models: A Survey
  2. 2023Brain in a Vat: On Missing Pieces Towards Artificial General Intelligence in Large Language Models
  3. 2026Operationalising the Superficial Alignment Hypothesis via Task Complexity
  4. 2025From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Models
  5. 2026FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks
  6. 2025General Intelligence Requires Reward-based Pretraining
  7. 2025The Avengers: A Simple Recipe for Uniting Smaller Language Models to Challenge Proprietary Giants
  8. 2026Computer Environments Elicit General Agentic Intelligence in LLMs