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

147 papers, page 2 of 3

51. ICLR 2025Rethinking the role of frames for SE(3)-invariant crystal structure modeling
52. ICLR 2025Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis
53. ICLR 2025Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order Optimizer
54. ICLR 2025Solving Differential Equations with Constrained Learning
55. ICLR 2025Student-Informed Teacher Training
56. ICLR 2025Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length
57. ICLR 2025Towards Automated Knowledge Integration From Human-Interpretable Representations
58. ICML 2025A Machine Learning Approach to Duality in Statistical Physics
59. ICML 2025Calibrated Physics-Informed Uncertainty Quantification
60. ICML 2025Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel
61. ICML 2025Context-Informed Neural ODEs Unexpectedly Identify Broken Symmetries: Insights from the Poincaré–Hopf Theorem
62. ICML 2025CoPINN: Cognitive Physics-Informed Neural Networks
63. ICML 2025DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction
64. ICML 2025Evolving Minds: Logic-Informed Inference from Temporal Action Patterns
65. ICML 2025Geometry-Informed Neural Networks
66. ICML 2025Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space
67. ICML 2025Learning Single Index Models with Diffusion Priors
68. ICML 2025MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction
69. ICML 2025MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation
70. ICML 2025Near-optimal Sketchy Natural Gradients for Physics-Informed Neural Networks
71. ICML 2025NEAR: Neural Electromagnetic Array Response
72. ICML 2025PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction
73. ICML 2025Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identification
74. ICML 2025Physics-Informed Generative Modeling of Wireless Channels
75. ICML 2025Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models
76. ICML 2025Physics-Informed Weakly Supervised Learning For Interatomic Potentials
77. ICML 2025PINNsAgent: Automated PDE Surrogation with Large Language Models
78. ICML 2025Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural Networks
79. ICML 2025Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks
80. ICML 2025Structure-informed Risk Minimization for Robust Ensemble Learning
81. ICML 2025Sub-Sequential Physics-Informed Learning with State Space Model
82. ICML 2025Topology-aware Neural Flux Prediction Guided by Physics
83. NeurIPS 20253DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization
84. NeurIPS 2025A Differential and Pointwise Control Approach to Reinforcement Learning
85. NeurIPS 2025A Physics-preserved Transfer Learning Method for Differential Equations
86. NeurIPS 2025Activation-Informed Merging of Large Language Models
87. NeurIPS 2025Attention on the Sphere
88. NeurIPS 2025BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity
89. NeurIPS 2025Brain-Informed Fine-Tuning for Improved Multilingual Understanding in Language Models
90. NeurIPS 2025Consistency of Physics-Informed Neural Networks for Second-Order Elliptic Equations
91. NeurIPS 2025Deep learning for continuous-time stochastic control with jumps
92. NeurIPS 2025Distance-informed Neural Processes
93. NeurIPS 2025Energy Loss Functions for Physical Systems
94. NeurIPS 2025Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules
95. NeurIPS 2025Eulerian Neural Network Informed by Chemical Transport for Air Quality Forecasting
96. NeurIPS 2025FAIR Universe HiggsML Uncertainty Dataset and Competition
97. NeurIPS 2025FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design
98. NeurIPS 2025FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering
99. NeurIPS 2025FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks
100. NeurIPS 2025From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy

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.