Physics-Informed ML papers, 2023–2026

Key findings

• Physics-Informed ML went from 50 papers in 2023 to 199 in 2026, roughly 4.0x in three years.
• NeurIPS publishes the most Physics-Informed ML work: 167 papers from 2023 to 2026, 35% of the four-venue total.
• The fastest-growing overlap is with Multimodal LLMs: papers tagged with both rose from 0 in 2023 to 11 in 2026.
• Among the 5 topics under Climate and Physical Sciences, it ranks #1 by 2026 paper count; the fastest grower in the group, Weather Forecasting, is up 6.1x versus 4.0x here.

Representative papers

Spread across years and venues so every edition shows up

• NeurIPS 2026Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency
• ICML 2026Bias-Spectrum Neural Processes for Parametric PDEs: Architecture Priors Meet PDE Constraints
• ICLR 2026CONSIGN: Conformal Segmentation Informed by Spatial Groupings via Decomposition
• CVPR 2026Domain Sensitive Federated Learning with Fisher-Informed Pruning
• NeurIPS 2025Activation-Informed Merging of Large Language Models
• ICML 2025Geometry-Informed Neural Networks
• ICLR 2025Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraints
• CVPR 2025A Physics-Informed Blur Learning Framework for Imaging Systems
• NeurIPS 2024ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction
• ICML 2024A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Prediction
• ICLR 2024AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction
• CVPR 2024A Physics-informed Low-rank Deep Neural Network for Blind and Universal Lens Aberration Correction
• NeurIPS 2023ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation
• ICML 2023Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks
• ICLR 2023Bi-level Physics-Informed Neural Networks for PDE Constrained Optimization using Broyden's Hypergradients
• CVPR 20233D Human Pose Estimation via Intuitive Physics
• NeurIPS 2026Neural Modal Decomposition: Architectural Priors from Observables
• ICML 2026Fine-to-Coarse Fairness-Informed Multi-View Clustering
• ICLR 2026From Neural Networks to Logical Theories: The Correspondence between Fibring Modal Logics and Fibring Neural Networks
• CVPR 2026LaDy Lagrangian-Dynamic Informed Network for Skeleton-based Action Segmentation via Spatial-Temporal

All Physics-Informed ML papers

143 papers, page 1 of 3

1. ICLR 2026(U)NFV: Supervised and Unsupervised Neural Finite Volume Methods for Solving Hyperbolic PDEs
2. ICLR 2026**TandemFoilSet**: Datasets for Flow Field Prediction of Tandem-Airfoil Through the Reuse of Single Airfoils
3. ICLR 2026$\boldsymbol{\partial^\infty}$-Grid: A Neural Differential Equation Solver with Differentiable Feature Grids
4. ICLR 2026A Physics-Inspired Optimizer: Velocity Regularized Adam
5. ICLR 2026ASSESS: A Semantic and Structural Evaluation Framework for Statement Similarity
6. ICLR 2026ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networks
7. ICLR 2026BioBO: Biology-informed Bayesian Optimization for Perturbation Design
8. ICLR 2026Bird's-eye-view Informed Reasoning Driver
9. ICLR 2026Boolean Satisfiability via Imitation Learning
10. ICLR 2026ComPhy: Composing Physical Models with end-to-end Alignment
11. ICLR 2026Compositional Generalization from Learned Skills via CoT Training: A Theoretical and Structural Analysis for Reasoning
12. ICLR 2026CONSIGN: Conformal Segmentation Informed by Spatial Groupings via Decomposition
13. ICLR 2026Converge Faster, Talk Less: Hessian-Informed Federated Zeroth-Order Optimization
14. ICLR 2026DeepPrim: a Physics-Driven 3D Short-term Weather Forecaster via Primitive Equation Learning
15. ICLR 2026DGNet: Learning Spatiotemporal PDEs with Discrete Green Networks
16. ICLR 2026DiffWind: Physics-Informed Differentiable Modeling of Wind-Driven Object Dynamics
17. ICLR 2026Distribution-informed Online Conformal Prediction
18. ICLR 2026Divide and Abstract: Autoformalization via Decomposition and Abstraction Learning
19. ICLR 2026DRIFT: Decompose, Retrieve, Illustrate, then Formalize Theorems
20. ICLR 2026Enhancing Stability of Physics-Informed Neural Network Training Through Saddle-Point Reformulation
21. ICLR 2026ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning
22. ICLR 2026Fast Convergence of Natural Gradient Descent for Over-parameterized Physics-Informed Neural Networks
23. ICLR 2026Fast training of accurate physics-informed neural networks without gradient descent
24. ICLR 2026From Neural Networks to Logical Theories: The Correspondence between Fibring Modal Logics and Fibring Neural Networks
25. ICLR 2026GenSR: Symbolic regression based on equation generative space
26. ICLR 2026GeoFAR: Geography-Informed Frequency-Aware Super-Resolution for Climate Data
27. ICLR 2026Geometric Autoencoder Priors for Bayesian Inversion: Learn First Observe Later
28. ICLR 2026Gradient-Based Program Synthesis with Neurally Interpreted Languages
29. ICLR 2026GUIDE: Gated Uncertainty-Informed Disentangled Experts for Long-tailed Recognition
30. ICLR 2026Harmonized Cone for Feasible and Non-conflict Directions in Training Physics-Informed Neural Networks
31. ICLR 2026Improving Extreme Wind Prediction with Frequency-Informed Learning
32. ICLR 2026Iterative Training of Physics-Informed Neural Networks with Fourier-enhanced Features
33. ICLR 2026Joint Distribution–Informed Shapley Values for Sparse Counterfactual Explanations
34. ICLR 2026Light Differentiable Logic Gate Networks
35. ICLR 2026Locally Subspace-Informed Neural Operators for Efficient Multiscale PDE Solving
36. ICLR 2026LRIM: a Physics-Based Benchmark for Provably Evaluating Long-Range Capabilities in Graph Learning
37. ICLR 2026Meta-Learning Theory-Informed Inductive Biases using Deep Kernel Gaussian Processes
38. ICLR 2026Overtone: Cyclic Patch Modulation for Cleaner, Faster Physics Emulators
39. ICLR 2026PatchDNA: A Flexible and Biologically-Informed Alternative to Tokenization for DNA
40. ICLR 2026PepTri: Tri-Guided All-Atom Diffusion for Peptide Design via Physics, Evolution, and Mutual Information
41. ICLR 2026Physics vs Distributions: Pareto Optimal Flow Matching with Physics Constraints
42. ICLR 2026Physics-Constrained Fine-Tuning of Flow-Matching Models for Generation and Inverse Problems
43. ICLR 2026Physics-Informed Audio-Geometry-Grid Representation Learning for Universal Sound Source Localization
44. ICLR 2026Physics-Informed Inference Time Scaling for Solving High-Dimensional Partial Differential Equations
45. ICLR 2026Physics-informed learning under mixing: How physical knowledge speeds up learning
46. ICLR 2026PINFDiT: Energy-Based Physics-Informed Diffusion Transformers for General-purpose Time Series Tasks
47. ICLR 2026PolySHAP: Extending KernelSHAP with Interaction-Informed Polynomial Regression
48. ICLR 2026PoseX: AI Defeats Physics-based Methods on Protein Ligand Cross-Docking
49. ICLR 2026ProofFlow: A Dependency Graph Approach to Faithful Proof Autoformalization
50. ICLR 2026QLCoder: A Query Synthesizer For Static Analysis of Security Vulnerabilities

FAQ

How many Physics-Informed ML papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

481 in total: 50 in 2023, 85 in 2024, 147 in 2025, 199 in 2026.

How many Physics-Informed ML papers are at NeurIPS 2026?

NeurIPS 2026 has 54 Physics-Informed ML papers, versus 65 the year before.

How many Physics-Informed ML papers are at ICLR 2026?

ICLR 2026 has 64 Physics-Informed ML papers, versus 38 the year before.

How many Physics-Informed ML papers are at ICML 2026?

ICML 2026 has 51 Physics-Informed ML papers, versus 25 the year before.

How many Physics-Informed ML papers are at CVPR 2026?

CVPR 2026 has 30 Physics-Informed ML papers, versus 19 the year before.

Which conference publishes the most Physics-Informed ML papers?

NeurIPS, with 167 papers from 2023 to 2026.