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 25 篇，第 1 / 1 页

1. ICML 2025A Machine Learning Approach to Duality in Statistical Physics
2. ICML 2025Calibrated Physics-Informed Uncertainty Quantification
3. ICML 2025Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel
4. ICML 2025Context-Informed Neural ODEs Unexpectedly Identify Broken Symmetries: Insights from the Poincaré–Hopf Theorem
5. ICML 2025CoPINN: Cognitive Physics-Informed Neural Networks
6. ICML 2025DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction
7. ICML 2025Evolving Minds: Logic-Informed Inference from Temporal Action Patterns
8. ICML 2025Geometry-Informed Neural Networks
9. ICML 2025Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space
10. ICML 2025Learning Single Index Models with Diffusion Priors
11. ICML 2025MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction
12. ICML 2025MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation
13. ICML 2025Near-optimal Sketchy Natural Gradients for Physics-Informed Neural Networks
14. ICML 2025NEAR: Neural Electromagnetic Array Response
15. ICML 2025PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction
16. ICML 2025Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identification
17. ICML 2025Physics-Informed Generative Modeling of Wireless Channels
18. ICML 2025Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models
19. ICML 2025Physics-Informed Weakly Supervised Learning For Interatomic Potentials
20. ICML 2025PINNsAgent: Automated PDE Surrogation with Large Language Models
21. ICML 2025Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural Networks
22. ICML 2025Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks
23. ICML 2025Structure-informed Risk Minimization for Robust Ensemble Learning
24. ICML 2025Sub-Sequential Physics-Informed Learning with State Space Model
25. ICML 2025Topology-aware Neural Flux Prediction Guided by 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。