物理约束 ML论文趋势 2023–2026

PINN 与物理先验

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 481 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

物理约束 ML论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202321911950
20242732151185
202565382519147
202654645130199

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

全部物理约束 ML论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 50 篇，第 1 / 1 页

  1. CVPR 20233D Human Pose Estimation via Intuitive Physics
  2. CVPR 2023DP-NeRF: Deblurred Neural Radiance Field With Physical Scene Priors
  3. CVPR 2023Imitation Learning As State Matching via Differentiable Physics
  4. CVPR 2023Learning 3D Scene Priors With 2D Supervision
  5. CVPR 2023Neural Part Priors: Learning To Optimize Part-Based Object Completion in RGB-D Scans
  6. CVPR 2023NLOST: Non-Line-of-Sight Imaging With Transformer
  7. CVPR 2023Physics-Driven Diffusion Models for Impact Sound Synthesis From Videos
  8. CVPR 2023Thermal Spread Functions (TSF): Physics-Guided Material Classification
  9. CVPR 2023Towards Unbiased Volume Rendering of Neural Implicit Surfaces With Geometry Priors
  10. ICLR 2023Bi-level Physics-Informed Neural Networks for PDE Constrained Optimization using Broyden's Hypergradients
  11. ICLR 2023Competitive Physics Informed Networks
  12. ICLR 2023DiffMimic: Efficient Motion Mimicking with Differentiable Physics
  13. ICLR 2023Guiding continuous operator learning through Physics-based boundary constraints
  14. ICLR 2023Improved Training of Physics-Informed Neural Networks Using Energy-Based Priors: a Study on Electrical Impedance Tomography
  15. ICLR 2023NTFields: Neural Time Fields for Physics-Informed Robot Motion Planning
  16. ICLR 2023Phase2vec: dynamical systems embedding with a physics-informed convolutional network
  17. ICLR 2023Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth
  18. ICLR 2023Zeroth-Order Optimization with Trajectory-Informed Derivative Estimation
  19. ICML 2023Achieving High Accuracy with PINNs via Energy Natural Gradient Descent
  20. ICML 2023Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process
  21. ICML 2023Generalized Disparate Impact for Configurable Fairness Solutions in ML
  22. ICML 2023Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks
  23. ICML 2023Harmonic Neural Networks
  24. ICML 2023Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks
  25. ICML 2023Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling
  26. ICML 2023MultiAdam: Parameter-wise Scale-invariant Optimizer for Multiscale Training of Physics-informed Neural Networks
  27. ICML 2023NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition
  28. ICML 2023Structured Cooperative Learning with Graphical Model Priors
  29. ICML 2023Universal Physics-Informed Neural Networks: Symbolic Differential Operator Discovery with Sparse Data
  30. NeurIPS 2023ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation
  31. NeurIPS 2023Entropy-dissipation Informed Neural Network for McKean-Vlasov Type PDEs
  32. NeurIPS 2023Gradient Informed Proximal Policy Optimization
  33. NeurIPS 2023H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation
  34. NeurIPS 2023High-dimensional Asymptotics of Denoising Autoencoders
  35. NeurIPS 2023Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks
  36. NeurIPS 2023Inferring Hybrid Neural Fluid Fields from Videos
  37. NeurIPS 2023InsActor: Instruction-driven Physics-based Characters
  38. NeurIPS 2023Lie Point Symmetry and Physics-Informed Networks
  39. NeurIPS 2023Nonparametric Boundary Geometry in Physics Informed Deep Learning
  40. NeurIPS 2023Physics-Driven ML-Based Modelling for Correcting Inverse Estimation
  41. NeurIPS 2023Physics-Informed Bayesian Optimization of Variational Quantum Circuits
  42. NeurIPS 2023PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification
  43. NeurIPS 2023Proximity-Informed Calibration for Deep Neural Networks
  44. NeurIPS 2023ResoNet: Noise-Trained Physics-Informed MRI Off-Resonance Correction
  45. NeurIPS 2023Separable Physics-Informed Neural Networks
  46. NeurIPS 2023Solving Inverse Physics Problems with Score Matching
  47. NeurIPS 2023Stabilized Neural Differential Equations for Learning Dynamics with Explicit Constraints
  48. NeurIPS 2023Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials
  49. NeurIPS 2023SyncTREE: Fast Timing Analysis for Integrated Circuit Design through a Physics-informed Tree-based Graph Neural Network
  50. NeurIPS 2023Versatile Energy-Based Probabilistic Models for High Energy Physics

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查物理约束 ML在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "physics-informed-ml"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「气候与物理科学」下的其他主题