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 65 篇，第 1 / 2 页

  1. NeurIPS 20253DID: Direct 3D Inverse Design for Aerodynamics with Physics-Aware Optimization
  2. NeurIPS 2025A Differential and Pointwise Control Approach to Reinforcement Learning
  3. NeurIPS 2025A Physics-preserved Transfer Learning Method for Differential Equations
  4. NeurIPS 2025Activation-Informed Merging of Large Language Models
  5. NeurIPS 2025Attention on the Sphere
  6. NeurIPS 2025BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity
  7. NeurIPS 2025Brain-Informed Fine-Tuning for Improved Multilingual Understanding in Language Models
  8. NeurIPS 2025Consistency of Physics-Informed Neural Networks for Second-Order Elliptic Equations
  9. NeurIPS 2025Deep learning for continuous-time stochastic control with jumps
  10. NeurIPS 2025Distance-informed Neural Processes
  11. NeurIPS 2025Energy Loss Functions for Physical Systems
  12. NeurIPS 2025Enforcing Hard Linear Constraints in Deep Learning Models with Decision Rules
  13. NeurIPS 2025Eulerian Neural Network Informed by Chemical Transport for Air Quality Forecasting
  14. NeurIPS 2025FAIR Universe HiggsML Uncertainty Dataset and Competition
  15. NeurIPS 2025FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design
  16. NeurIPS 2025FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering
  17. NeurIPS 2025FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks
  18. NeurIPS 2025From Pixels to Views: Learning Angular-Aware and Physics-Consistent Representations for Light Field Microscopy
  19. NeurIPS 2025Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective
  20. NeurIPS 2025Hybrid Boundary Physics-Informed Neural Networks for Solving Navier-Stokes Equations with Complex Boundary
  21. NeurIPS 2025Hybrid Latent Representations for PDE Emulation
  22. NeurIPS 2025HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions
  23. NeurIPS 2025Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization
  24. NeurIPS 2025Informed Correctors for Discrete Diffusion Models
  25. NeurIPS 2025Joint Hierarchical Representation Learning of Samples and Features via Informed Tree-Wasserstein Distance
  26. NeurIPS 2025Learning Chern Numbers of Multiband Topological Insulators with Gauge Equivariant Neural Networks
  27. NeurIPS 2025Learning to price with resource constraints: from full information to machine-learned prices
  28. NeurIPS 2025Learning Urban Climate Dynamics via Physics-Guided Urban Surface–Atmosphere Interactions
  29. NeurIPS 2025Lorentz Local Canonicalization: How to make any Network Lorentz-Equivariant
  30. NeurIPS 2025MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs
  31. NeurIPS 2025Mitigating Instability in High Residual Adaptive Sampling for PINNs via Langevin Dynamics
  32. NeurIPS 2025Model-Informed Flows for Bayesian Inference
  33. NeurIPS 2025Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning
  34. NeurIPS 2025Neuro-Spectral Architectures for Causal Physics-Informed Networks
  35. NeurIPS 2025NOBLE - Neural Operator with Biologically-informed Latent Embeddings to Capture Experimental Variability in Biological Neuron Models
  36. NeurIPS 2025PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization
  37. NeurIPS 2025Partial Physics Informed Diffusion Model for Ocean Chlorophyll Concentration Reconstruction
  38. NeurIPS 2025PhysDiff: A Physically-Guided Diffusion Model for Multivariate Time Series Anomaly Detection
  39. NeurIPS 2025PhySense: Sensor Placement Optimization for Accurate Physics Sensing
  40. NeurIPS 2025PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors
  41. NeurIPS 2025Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers
  42. NeurIPS 2025Physics-informed machine learning with domain decomposition and global dynamics for three-dimensional intersecting flows
  43. NeurIPS 2025Physics-informed Neural Operator for Pansharpening
  44. NeurIPS 2025Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers
  45. NeurIPS 2025Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning
  46. NeurIPS 2025PhySwin: An Efficient and Physically-Informed Foundation Model for Multispectral Earth Observation
  47. NeurIPS 2025PINN Balls: Scaling Second-Order Methods for PINNs with Domain Decomposition and Adaptive Sampling
  48. NeurIPS 2025PINNs with Learnable Quadrature
  49. NeurIPS 2025PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series in Typhoon Forecasting
  50. NeurIPS 2025PMLF: A Physics-Guided Multiscale Loss Framework for Structurally Heterogeneous Time Series

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