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 38 篇，第 1 / 1 页

1. ICLR 2025ANaGRAM: A Natural Gradient Relative to Adapted Model for efficient PINNs learning
2. ICLR 2025Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences
3. ICLR 2025Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraints
4. ICLR 2025Circuit Transformer: A Transformer That Preserves Logical Equivalence
5. ICLR 2025ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks
6. ICLR 2025Deep Learning Alternatives Of The Kolmogorov Superposition Theorem
7. ICLR 2025Differentiable Rule Induction from Raw Sequence Inputs
8. ICLR 2025Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination
9. ICLR 2025Generating Physical Dynamics under Priors
10. ICLR 2025KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI
11. ICLR 2025Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed Methods
12. ICLR 2025Learning Chaos In A Linear Way
13. ICLR 2025Learning system dynamics without forgetting
14. ICLR 2025Learning to Solve Differential Equation Constrained Optimization Problems
15. ICLR 2025Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups
16. ICLR 2025Logically Consistent Language Models via Neuro-Symbolic Integration
17. ICLR 2025MeshMask: Physics-Based Simulations with Masked Graph Neural Networks
18. ICLR 2025Metamizer: A Versatile Neural Optimizer for Fast and Accurate Physics Simulations
19. ICLR 2025NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains
20. ICLR 2025Neural Stochastic Differential Equations for Uncertainty-Aware Offline RL
21. ICLR 2025Neural Wave Equation for Irregularly Sampled Sequence Data
22. ICLR 2025Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems
23. ICLR 2025Physics-aligned field reconstruction with diffusion bridge
24. ICLR 2025Physics-Informed Diffusion Models
25. ICLR 2025Physics-informed Temporal Difference Metric Learning for Robot Motion Planning
26. ICLR 2025PIED: Physics-Informed Experimental Design for Inverse Problems
27. ICLR 2025PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations
28. ICLR 2025PINP: Physics-Informed Neural Predictor with latent estimation of fluid flows
29. ICLR 2025PIORF: Physics-Informed Ollivier-Ricci Flow for Long–Range Interactions in Mesh Graph Neural Networks
30. ICLR 2025PRDP: Progressively Refined Differentiable Physics
31. ICLR 2025Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learning
32. ICLR 2025Rethinking the role of frames for SE(3)-invariant crystal structure modeling
33. ICLR 2025Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis
34. ICLR 2025Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order Optimizer
35. ICLR 2025Solving Differential Equations with Constrained Learning
36. ICLR 2025Student-Informed Teacher Training
37. ICLR 2025Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length
38. ICLR 2025Towards Automated Knowledge Integration From Human-Interpretable Representations

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。