物理约束 ML论文趋势 2023–2026

主要结论

• 物理约束 ML论文从 2023 年的 50 篇增长到 2026 年的 199 篇，三年间扩大到约 4.0 倍。
• NeurIPS 是发物理约束 ML论文最多的会议，2023–2026 年共 167 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是多模态大模型：同时属于两个主题的论文从 2023 年的 0 篇增至 2026 年的 11 篇。
• 在「气候与物理科学」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的天气预报是 6.1 倍，物理约束 ML是 4.0 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• 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

全部物理约束 ML论文

共 481 篇，第 10 / 10 页

451. ICML 2023Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process
452. ICML 2023Generalized Disparate Impact for Configurable Fairness Solutions in ML
453. ICML 2023Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks
454. ICML 2023Harmonic Neural Networks
455. ICML 2023Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks
456. ICML 2023Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling
457. ICML 2023MultiAdam: Parameter-wise Scale-invariant Optimizer for Multiscale Training of Physics-informed Neural Networks
458. ICML 2023NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition
459. ICML 2023Structured Cooperative Learning with Graphical Model Priors
460. ICML 2023Universal Physics-Informed Neural Networks: Symbolic Differential Operator Discovery with Sparse Data
461. NeurIPS 2023ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation
462. NeurIPS 2023Entropy-dissipation Informed Neural Network for McKean-Vlasov Type PDEs
463. NeurIPS 2023Gradient Informed Proximal Policy Optimization
464. NeurIPS 2023H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation
465. NeurIPS 2023High-dimensional Asymptotics of Denoising Autoencoders
466. NeurIPS 2023Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks
467. NeurIPS 2023Inferring Hybrid Neural Fluid Fields from Videos
468. NeurIPS 2023InsActor: Instruction-driven Physics-based Characters
469. NeurIPS 2023Lie Point Symmetry and Physics-Informed Networks
470. NeurIPS 2023Nonparametric Boundary Geometry in Physics Informed Deep Learning
471. NeurIPS 2023Physics-Driven ML-Based Modelling for Correcting Inverse Estimation
472. NeurIPS 2023Physics-Informed Bayesian Optimization of Variational Quantum Circuits
473. NeurIPS 2023PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification
474. NeurIPS 2023Proximity-Informed Calibration for Deep Neural Networks
475. NeurIPS 2023ResoNet: Noise-Trained Physics-Informed MRI Off-Resonance Correction
476. NeurIPS 2023Separable Physics-Informed Neural Networks
477. NeurIPS 2023Solving Inverse Physics Problems with Score Matching
478. NeurIPS 2023Stabilized Neural Differential Equations for Learning Dynamics with Explicit Constraints
479. NeurIPS 2023Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials
480. NeurIPS 2023SyncTREE: Fast Timing Analysis for Integrated Circuit Design through a Physics-informed Tree-based Graph Neural Network
481. NeurIPS 2023Versatile Energy-Based Probabilistic Models for High Energy Physics

常见问题

2023–2026 年四大会议一共有多少篇物理约束 ML论文？

共 481 篇，按年份分别是 2023 年 50 篇、2024 年 85 篇、2025 年 147 篇、2026 年 199 篇。

NeurIPS 2026 有多少篇物理约束 ML论文？

NeurIPS 2026 有 54 篇物理约束 ML论文，上一届是 65 篇。

ICLR 2026 有多少篇物理约束 ML论文？

ICLR 2026 有 64 篇物理约束 ML论文，上一届是 38 篇。

ICML 2026 有多少篇物理约束 ML论文？

ICML 2026 有 51 篇物理约束 ML论文，上一届是 25 篇。

CVPR 2026 有多少篇物理约束 ML论文？

CVPR 2026 有 30 篇物理约束 ML论文，上一届是 19 篇。

哪个会议的物理约束 ML论文最多？

NeurIPS，2023–2026 年共 167 篇。