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 147 篇，第 1 / 3 页

1. CVPR 2025A Physics-Informed Blur Learning Framework for Imaging Systems
2. CVPR 2025DexGrasp Anything: Towards Universal Robotic Dexterous Grasping with Physics Awareness
3. CVPR 2025Electromyography-Informed Facial Expression Reconstruction for Physiological-Based Synthesis and Analysis
4. CVPR 2025FiRe: Fixed-points of Restoration Priors for Solving Inverse Problems
5. CVPR 2025FLAIR: VLM with Fine-grained Language-informed Image Representations
6. CVPR 2025FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity
7. CVPR 2025Learning Physics-Based Full-Body Human Reaching and Grasping from Brief Walking References
8. CVPR 2025Nested Diffusion Models Using Hierarchical Latent Priors
9. CVPR 2025Patient-Level Anatomy Meets Scanning-Level Physics: Personalized Federated Low-Dose CT Denoising Empowered by Large Language Model
10. CVPR 2025PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields
11. CVPR 2025Point Clouds Meets Physics: Dynamic Acoustic Field Fitting Network for Point Cloud Understanding
12. CVPR 2025POMP: Physics-consistent Motion Generative Model through Phase Manifolds
13. CVPR 2025Pose Priors from Language Models
14. CVPR 2025Relative Pose Estimation through Affine Corrections of Monocular Depth Priors
15. CVPR 2025S^3-Face: SSS-Compliant Facial Reflectance Estimation via Diffusion Priors
16. CVPR 2025SpatialLLM: A Compound 3D-Informed Design towards Spatially-Intelligent Large Multimodal Models
17. CVPR 2025Spectral Informed Mamba for Robust Point Cloud Processing
18. CVPR 2025UniPhy: Learning a Unified Constitutive Model for Inverse Physics Simulation
19. CVPR 2025VI^3NR: Variance Informed Initialization for Implicit Neural Representations
20. ICLR 2025ANaGRAM: A Natural Gradient Relative to Adapted Model for efficient PINNs learning
21. ICLR 2025Bayesian Optimization of Antibodies Informed by a Generative Model of Evolving Sequences
22. ICLR 2025Beyond the convexity assumption: Realistic tabular data generation under quantifier-free real linear constraints
23. ICLR 2025Circuit Transformer: A Transformer That Preserves Logical Equivalence
24. ICLR 2025ConFIG: Towards Conflict-free Training of Physics Informed Neural Networks
25. ICLR 2025Deep Learning Alternatives Of The Kolmogorov Superposition Theorem
26. ICLR 2025Differentiable Rule Induction from Raw Sequence Inputs
27. ICLR 2025Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination
28. ICLR 2025Generating Physical Dynamics under Priors
29. ICLR 2025KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI
30. ICLR 2025Learning a Neural Solver for Parametric PDEs to Enhance Physics-Informed Methods
31. ICLR 2025Learning Chaos In A Linear Way
32. ICLR 2025Learning system dynamics without forgetting
33. ICLR 2025Learning to Solve Differential Equation Constrained Optimization Problems
34. ICLR 2025Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups
35. ICLR 2025Logically Consistent Language Models via Neuro-Symbolic Integration
36. ICLR 2025MeshMask: Physics-Based Simulations with Masked Graph Neural Networks
37. ICLR 2025Metamizer: A Versatile Neural Optimizer for Fast and Accurate Physics Simulations
38. ICLR 2025NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains
39. ICLR 2025Neural Stochastic Differential Equations for Uncertainty-Aware Offline RL
40. ICLR 2025Neural Wave Equation for Irregularly Sampled Sequence Data
41. ICLR 2025Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems
42. ICLR 2025Physics-aligned field reconstruction with diffusion bridge
43. ICLR 2025Physics-Informed Diffusion Models
44. ICLR 2025Physics-informed Temporal Difference Metric Learning for Robot Motion Planning
45. ICLR 2025PIED: Physics-Informed Experimental Design for Inverse Problems
46. ICLR 2025PIG: Physics-Informed Gaussians as Adaptive Parametric Mesh Representations
47. ICLR 2025PINP: Physics-Informed Neural Predictor with latent estimation of fluid flows
48. ICLR 2025PIORF: Physics-Informed Ollivier-Ricci Flow for Long–Range Interactions in Mesh Graph Neural Networks
49. ICLR 2025PRDP: Progressively Refined Differentiable Physics
50. ICLR 2025Predicting the Energy Landscape of Stochastic Dynamical System via Physics-informed Self-supervised Learning

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。