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 102 篇，第 2 / 3 页

  1. ICML 2026Unbiased and Second-Order-Free Training for High-Dimensional PDEs
  2. ICML 2025A Machine Learning Approach to Duality in Statistical Physics
  3. ICML 2025Calibrated Physics-Informed Uncertainty Quantification
  4. ICML 2025Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel
  5. ICML 2025Context-Informed Neural ODEs Unexpectedly Identify Broken Symmetries: Insights from the Poincaré–Hopf Theorem
  6. ICML 2025CoPINN: Cognitive Physics-Informed Neural Networks
  7. ICML 2025DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction
  8. ICML 2025Evolving Minds: Logic-Informed Inference from Temporal Action Patterns
  9. ICML 2025Geometry-Informed Neural Networks
  10. ICML 2025Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space
  11. ICML 2025Learning Single Index Models with Diffusion Priors
  12. ICML 2025MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction
  13. ICML 2025MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation
  14. ICML 2025Near-optimal Sketchy Natural Gradients for Physics-Informed Neural Networks
  15. ICML 2025NEAR: Neural Electromagnetic Array Response
  16. ICML 2025PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction
  17. ICML 2025Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identification
  18. ICML 2025Physics-Informed Generative Modeling of Wireless Channels
  19. ICML 2025Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models
  20. ICML 2025Physics-Informed Weakly Supervised Learning For Interatomic Potentials
  21. ICML 2025PINNsAgent: Automated PDE Surrogation with Large Language Models
  22. ICML 2025Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural Networks
  23. ICML 2025Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks
  24. ICML 2025Structure-informed Risk Minimization for Robust Ensemble Learning
  25. ICML 2025Sub-Sequential Physics-Informed Learning with State Space Model
  26. ICML 2025Topology-aware Neural Flux Prediction Guided by Physics
  27. ICML 2024$S^2$IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting
  28. ICML 2024A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Prediction
  29. ICML 2024Boosting Offline Optimizers with Surrogate Sensitivity
  30. ICML 2024Challenges in Training PINNs: A Loss Landscape Perspective
  31. ICML 2024Deeper or Wider: A Perspective from Optimal Generalization Error with Sobolev Loss
  32. ICML 2024Efficient Error Certification for Physics-Informed Neural Networks
  33. ICML 2024Learning from Integral Losses in Physics Informed Neural Networks
  34. ICML 2024NeuralIndicator: Implicit Surface Reconstruction from Neural Indicator Priors
  35. ICML 2024Parameterized Physics-informed Neural Networks for Parameterized PDEs
  36. ICML 2024PARCv2: Physics-aware Recurrent Convolutional Neural Networks for Spatiotemporal Dynamics Modeling
  37. ICML 2024Physics and Lie symmetry informed Gaussian processes
  38. ICML 2024Physics-Informed Neural Network Policy Iteration: Algorithms, Convergence, and Verification
  39. ICML 2024PIPER: Primitive-Informed Preference-based Hierarchical Reinforcement Learning via Hindsight Relabeling
  40. ICML 2024Pluvial Flood Emulation with Hydraulics-informed Message Passing
  41. ICML 2024Stability-Informed Initialization of Neural Ordinary Differential Equations
  42. ICML 2023Achieving High Accuracy with PINNs via Energy Natural Gradient Descent
  43. ICML 2023Bayesian Progressive Deep Topic Model with Knowledge Informed Textual Data Coarsening Process
  44. ICML 2023Generalized Disparate Impact for Configurable Fairness Solutions in ML
  45. ICML 2023Gradient Descent Finds the Global Optima of Two-Layer Physics-Informed Neural Networks
  46. ICML 2023Harmonic Neural Networks
  47. ICML 2023Meta Learning of Interface Conditions for Multi-Domain Physics-Informed Neural Networks
  48. ICML 2023Mitigating Propagation Failures in Physics-informed Neural Networks using Retain-Resample-Release (R3) Sampling
  49. ICML 2023MultiAdam: Parameter-wise Scale-invariant Optimizer for Multiscale Training of Physics-informed Neural Networks
  50. ICML 2023NeuralStagger: Accelerating Physics-constrained Neural PDE Solver with Spatial-temporal Decomposition

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