mlsanityData to 14 Oct 2026

Explainable AI: Learning from the Learners

arXiv 2601.05525 ↗First posted 9 Jan 2026cs.AI cs.LG physics.comp-phcited by 4

Not on the map. Why?

Abstract (arXiv)

Artificial intelligence now outperforms humans in several scientific and engineering tasks, yet its internal representations often remain opaque. In this Perspective, we argue that explainable artificial intelligence (XAI), combined with causal reasoning, enables it learning from the learners. Focusing on discovery, optimization and certification, we show how the combination of foundation models and explainability methods allows the extraction of causal mechanisms, guides robust design and control, and supports trust and accountability in high-stakes applications. We discuss challenges in faithfulness, generalization and usability of explanations, and propose XAI as a unifying framework for human-AI collaboration in science and engineering.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 55 of its 131 references that are in the map. First posted on arXiv 9 Jan 2026.

Builds on

55 of 131 references.

References · 55

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2021On the Opportunities and Risks of Foundation Modelscited by 4,033
  3. 2015Continuous control with deep reinforcement learningcited by 3,407
  4. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  5. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  6. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  7. 2018Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representationscited by 941
  8. 2019Hamiltonian Neural Networkscited by 712
  9. 2021E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentialscited by 708
  10. 2019AI Feynman: a Physics-Inspired Method for Symbolic Regressioncited by 548
  11. 2015Causal inference using invariant prediction: identification and confidence intervalscited by 536
  12. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 494
38 more
  1. 2025Accelerating scientific discovery with Co-Scientistcited by 401
  2. 2020Lagrangian Neural Networkscited by 398
  3. 2019Causality for Machine Learningcited by 243
  4. 2018PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Networkcited by 210
  5. 2017Learning Koopman Invariant Subspaces for Dynamic Mode Decompositioncited by 158
  6. 2020Weak SINDy For Partial Differential Equationscited by 155
  7. 2017Linearly-Recurrent Autoencoder Networks for Learning Dynamicscited by 145
  8. 2021Ensemble-SINDy: Robust sparse model discovery in the low-data, high-noise limit, with active learning and controlcited by 137
  9. 2017VAMPnets: Deep learning of molecular kineticscited by 136
  10. 2017Learning Deep Neural Network Representations for Koopman Operators of Nonlinear Dynamical Systemscited by 127
  11. 2018Invariance, Causality and Robustnesscited by 123
  12. 2019Machine learning for molecular simulationcited by 110
  13. 2022AUC Maximization in the Era of Big Data and AI: A Surveycited by 100
  14. 2022Clifford Neural Layers for PDE Modelingcited by 92
  15. 2022Lie Point Symmetry Data Augmentation for Neural PDE Solverscited by 77
  16. 2023β-Variational autoencoders and transformers for reduced-order modelling of fluid flowscited by 77
  17. 2018Efficient collective swimming by harnessing vortices through deep reinforcement learningcited by 73
  18. 2022On scientific understanding with artificial intelligencecited by 70
  19. 2017Time-lagged autoencoders: Deep learning of slow collective variables for molecular kineticscited by 65
  20. 2022Discovering Governing Equations from Partial Measurements with Deep Delay Autoencoderscited by 58
  21. 2022Evaluation of post-hoc interpretability methods in time-series classificationcited by 53
  22. 2020Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Propertiescited by 51
  23. 2024Nonparametric Partial Disentanglement via Mechanism Sparsity: Sparse Actions, Interventions and Sparse Temporal Dependenciescited by 41
  24. 2023Discovering Causal Relations and Equations from Datacited by 36
  25. 2022Reduced order modeling of parametrized systems through autoencoders and SINDy approach: continuation of periodic solutionscited by 29
  26. 2023Finding the right XAI method -- A Guide for the Evaluation and Ranking of Explainable AI Methods in Climate Sciencecited by 27
  27. 2024SINDy-RL: Interpretable and Efficient Model-Based Reinforcement Learningcited by 26
  28. 2023A Unified Framework to Enforce, Discover, and Promote Symmetry in Machine Learningcited by 22
  29. 2021Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Datasetcited by 18
  30. 2021Interpretable deep-learning models to help achieve the Sustainable Development Goalscited by 18
  31. 2023The role of causality in explainable artificial intelligencecited by 17
  32. 2023Identifying regions of importance in wall-bounded turbulence through explainable deep learningcited by 15
  33. 2022Explainable AI via Learning to Optimizecited by 14
  34. 2025Diff-SPORT: Diffusion-based Sensor Placement Optimization and Reconstruction of Turbulent flows in urban environmentscited by 8
  35. 2021Interpretable Data-driven Methods for Subgrid-scale Closure in LES for Transcritical LOX/GCH4 Combustioncited by 6
  36. 2025CondensNet: Enabling stable long-term climate simulations via hybrid deep learning models with adaptive physical constraintscited by 6
  37. 2025Foundation Models for Discovery and Exploration in Chemical Spacecited by 6
  38. 2024Revisiting the robustness of post-hoc interpretability methodscited by 5

50 most cited of 55 All 55 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026AeroJEPA: Learning Semantic Latent Representations for Scalable 3D Aerodynamic Field Modelingcited by 4
  2. 2026Surrogates for Physics-based and Data-driven Modelling of Parametric Systems: Review and New Perspectivescited by 2
  3. 2026Agentic Exploration of PDE Spaces using Latent Foundation Models for Parameterized Simulationscited by 1
  4. 2026Weak Dominant Balance for Robust Identification of Dynamically Consistent Fluid Flow Structurecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Position: Explainability Research Must Prioritize Foundations over Ad-hoc Methods
  2. 2026xWhyL: Causal Interactive Learning
  3. 2025Explainable artificial intelligence (XAI): from inherent explainability to large language models
  4. 2026Addressing the Selection Problem in Explainable AI
  5. 2022Towards Benchmarking Explainable Artificial Intelligence Methods
  6. 2025A Survey of Explainable Reinforcement Learning: Targets, Methods and Needs
  7. 2023Multimodal Explainable Artificial Intelligence: A Comprehensive Review of Methodological Advances and Future Research Directions
  8. 2025Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii