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 481 篇，第 6 / 10 页

  1. ICLR 2025Robust Weight Initialization for Tanh Neural Networks with Fixed Point Analysis
  2. ICLR 2025Second-Order Fine-Tuning without Pain for LLMs: A Hessian Informed Zeroth-Order Optimizer
  3. ICLR 2025Solving Differential Equations with Constrained Learning
  4. ICLR 2025Student-Informed Teacher Training
  5. ICLR 2025Symbolic regression via MDLformer-guided search: from minimizing prediction error to minimizing description length
  6. ICLR 2025Towards Automated Knowledge Integration From Human-Interpretable Representations
  7. ICML 2025A Machine Learning Approach to Duality in Statistical Physics
  8. ICML 2025Calibrated Physics-Informed Uncertainty Quantification
  9. ICML 2025Causal-PIK: Causality-based Physical Reasoning with a Physics-Informed Kernel
  10. ICML 2025Context-Informed Neural ODEs Unexpectedly Identify Broken Symmetries: Insights from the Poincaré–Hopf Theorem
  11. ICML 2025CoPINN: Cognitive Physics-Informed Neural Networks
  12. ICML 2025DISCO: learning to DISCover an evolution Operator for multi-physics-agnostic prediction
  13. ICML 2025Evolving Minds: Logic-Informed Inference from Temporal Action Patterns
  14. ICML 2025Geometry-Informed Neural Networks
  15. ICML 2025Holistic Physics Solver: Learning PDEs in a Unified Spectral-Physical Space
  16. ICML 2025Learning Single Index Models with Diffusion Priors
  17. ICML 2025MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction
  18. ICML 2025MultiPDENet: PDE-embedded Learning with Multi-time-stepping for Accelerated Flow Simulation
  19. ICML 2025Near-optimal Sketchy Natural Gradients for Physics-Informed Neural Networks
  20. ICML 2025NEAR: Neural Electromagnetic Array Response
  21. ICML 2025PEINR: A Physics-enhanced Implicit Neural Representation for High-Fidelity Flow Field Reconstruction
  22. ICML 2025Physics-Informed DeepONets for drift-diffusion on metric graphs: simulation and parameter identification
  23. ICML 2025Physics-Informed Generative Modeling of Wireless Channels
  24. ICML 2025Physics-informed Temporal Alignment for Auto-regressive PDE Foundation Models
  25. ICML 2025Physics-Informed Weakly Supervised Learning For Interatomic Potentials
  26. ICML 2025PINNsAgent: Automated PDE Surrogation with Large Language Models
  27. ICML 2025Refined generalization analysis of the Deep Ritz Method and Physics-Informed Neural Networks
  28. ICML 2025Riemann Tensor Neural Networks: Learning Conservative Systems with Physics-Constrained Networks
  29. ICML 2025Structure-informed Risk Minimization for Robust Ensemble Learning
  30. ICML 2025Sub-Sequential Physics-Informed Learning with State Space Model
  31. ICML 2025Topology-aware Neural Flux Prediction Guided by Physics
  32. NeurIPS 20253DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization
  33. NeurIPS 2025A Differential and Pointwise Control Approach to Reinforcement Learning
  34. NeurIPS 2025A Physics-preserved Transfer Learning Method for Differential Equations
  35. NeurIPS 2025Activation-Informed Merging of Large Language Models
  36. NeurIPS 2025Attention on the Sphere
  37. NeurIPS 2025BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity
  38. NeurIPS 2025Brain-Informed Fine-Tuning for Improved Multilingual Understanding in Language Models
  39. NeurIPS 2025Consistency of Physics-Informed Neural Networks for Second-Order Elliptic Equations
  40. NeurIPS 2025Deep learning for continuous-time stochastic control with jumps
  41. NeurIPS 2025Distance-informed Neural Processes
  42. NeurIPS 2025Energy Loss Functions for Physical Systems
  43. NeurIPS 2025Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules
  44. NeurIPS 2025Eulerian Neural Network Informed by Chemical Transport for Air Quality Forecasting
  45. NeurIPS 2025FAIR Universe HiggsML Uncertainty Dataset and Competition
  46. NeurIPS 2025FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design
  47. NeurIPS 2025FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering
  48. NeurIPS 2025FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks
  49. NeurIPS 2025From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy
  50. NeurIPS 2025Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective

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