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 32 篇，第 1 / 1 页

1. ICLR 2024AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction
2. ICLR 2024An operator preconditioning perspective on training in physics-informed machine learning
3. ICLR 2024CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
4. ICLR 2024Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding
5. ICLR 2024DATS: Difficulty-Aware Task Sampler for Meta-Learning Physics-Informed Neural Networks
6. ICLR 2024Dynamics-Informed Protein Design with Structure Conditioning
7. ICLR 2024Generating Pragmatic Examples to Train Neural Program Synthesizers
8. ICLR 2024Guess & Sketch: Language Model Guided Transpilation
9. ICLR 2024How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data
10. ICLR 2024Incremental Randomized Smoothing Certification
11. ICLR 2024Interpreting Robustness Proofs of Deep Neural Networks
12. ICLR 2024Lagrangian Flow Networks for Conservation Laws
13. ICLR 2024Latent Intuitive Physics: Learning to Transfer Hidden Physics from A 3D Video
14. ICLR 2024Learning Grounded Action Abstractions from Language
15. ICLR 2024LEGO-Prover: Neural Theorem Proving with Growing Libraries
16. ICLR 2024Lemur: Integrating Large Language Models in Automated Program Verification
17. ICLR 2024Let's do the time-warp-attend: Learning topological invariants of dynamical systems
18. ICLR 2024LILO: Learning Interpretable Libraries by Compressing and Documenting Code
19. ICLR 2024Logical Languages Accepted by Transformer Encoders with Hard Attention
20. ICLR 2024Long-Short-Range Message-Passing: A Physics-Informed Framework to Capture Non-Local Interaction for Scalable Molecular Dynamics Simulation
21. ICLR 2024Long-Term Typhoon Trajectory Prediction: A Physics-Conditioned Approach Without Reanalysis Data
22. ICLR 2024MetaPhysiCa: Improving OOD Robustness in Physics-informed Machine Learning
23. ICLR 2024Neural-Symbolic Recursive Machine for Systematic Generalization
24. ICLR 2024NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
25. ICLR 2024Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings
26. ICLR 2024PINNACLE: PINN Adaptive ColLocation and Experimental points selection
27. ICLR 2024PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks
28. ICLR 2024Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spaces
29. ICLR 2024Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors
30. ICLR 2024Scaling physics-informed hard constraints with mixture-of-experts
31. ICLR 2024Sliced Denoising: A Physics-Informed Molecular Pre-Training Method
32. ICLR 2024Stabilizing Backpropagation Through Time to Learn Complex 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。