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
- 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。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 21 | 9 | 11 | 9 | 50 |
| 2024 | 27 | 32 | 15 | 11 | 85 |
| 2025 | 65 | 38 | 25 | 19 | 147 |
| 2026 | 54 | 64 | 51 | 30 | 199 |
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 481 篇，第 7 / 10 页
- NeurIPS 2025Hybrid Boundary Physics-Informed Neural Networks for Solving Navier-Stokes Equations with Complex Boundary
- NeurIPS 2025Hybrid Latent Representations for PDE Emulation
- NeurIPS 2025HyPINO: Multi-Physics Neural Operators via HyperPINNs and the Method of Manufactured Solutions
- NeurIPS 2025Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization
- NeurIPS 2025Informed Correctors for Discrete Diffusion Models
- NeurIPS 2025Joint Hierarchical Representation Learning of Samples and Features via Informed Tree-Wasserstein Distance
- NeurIPS 2025Learning Chern Numbers of Multiband Topological Insulators with Gauge Equivariant Neural Networks
- NeurIPS 2025Learning to price with resource constraints: from full information to machine-learned prices
- NeurIPS 2025Learning Urban Climate Dynamics via Physics-Guided Urban Surface–Atmosphere Interactions
- NeurIPS 2025Lorentz Local Canonicalization: How to make any Network Lorentz-Equivariant
- NeurIPS 2025MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs
- NeurIPS 2025Mitigating Instability in High Residual Adaptive Sampling for PINNs via Langevin Dynamics
- NeurIPS 2025Model-Informed Flows for Bayesian Inference
- NeurIPS 2025Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning
- NeurIPS 2025Neuro-Spectral Architectures for Causal Physics-Informed Networks
- NeurIPS 2025NOBLE - Neural Operator with Biologically-informed Latent Embeddings to Capture Experimental Variability in Biological Neuron Models
- NeurIPS 2025PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization
- NeurIPS 2025Partial Physics Informed Diffusion Model for Ocean Chlorophyll Concentration Reconstruction
- NeurIPS 2025PhysDiff: A Physically-Guided Diffusion Model for Multivariate Time Series Anomaly Detection
- NeurIPS 2025PhySense: Sensor Placement Optimization for Accurate Physics Sensing
- NeurIPS 2025PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors
- NeurIPS 2025Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers
- NeurIPS 2025Physics-informed machine learning with domain decomposition and global dynamics for three-dimensional intersecting flows
- NeurIPS 2025Physics-informed Neural Operator for Pansharpening
- NeurIPS 2025Physics-informed Reduced Order Modeling of Time-dependent PDEs via Differentiable Solvers
- NeurIPS 2025Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning
- NeurIPS 2025PhySwin: An Efficient and Physically-Informed Foundation Model for Multispectral Earth Observation
- NeurIPS 2025PINN Balls: Scaling Second-Order Methods for PINNs with Domain Decomposition and Adaptive Sampling
- NeurIPS 2025PINNs with Learnable Quadrature
- NeurIPS 2025PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series in Typhoon Forecasting
- NeurIPS 2025PMLF: A Physics-Guided Multiscale Loss Framework for Structurally Heterogeneous Time Series
- NeurIPS 2025Position: Biology is the Challenge Physics-Informed ML Needs to Evolve
- NeurIPS 2025PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs
- NeurIPS 2025Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor
- NeurIPS 2025RoboScape: Physics-informed Embodied World Model
- NeurIPS 2025Shape-Informed Clustering of Multi-Dimensional Functional Data via Deep Functional Autoencoders
- NeurIPS 2025STaRFormer: Semi-Supervised Task-Informed Representation Learning via Dynamic Attention-Based Regional Masking for Sequential Data
- NeurIPS 2025TITAN: A Trajectory-Informed Technique for Adaptive Parameter Freezing in Large-Scale VQE
- NeurIPS 2025Towards Automated Petrography
- NeurIPS 2025Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study
- NeurIPS 2025Towards Prospective Medical Image Reconstruction via Knowledge-Informed Dynamic Optimal Transport
- NeurIPS 2025Uncertainty Estimation on Graphs with Structure Informed Stochastic Partial Differential Equations
- NeurIPS 2025Uncertainty Quantification for Physics-Informed Neural Networks with Extended Fiducial Inference
- NeurIPS 2025Uncover Governing Law of Pathology Propagation Mechanism Through A Mean-Field Game
- NeurIPS 2025Understanding Generalization in Physics Informed Models through Affine Variety Dimensions
- NeurIPS 2025X-Field: A Physically Informed Representation for 3D X-ray Reconstruction
- CVPR 2024A Physics-informed Low-rank Deep Neural Network for Blind and Universal Lens Aberration Correction
- CVPR 2024As-Plausible-As-Possible: Plausibility-Aware Mesh Deformation Using 2D Diffusion Priors
- CVPR 2024Bayesian Differentiable Physics for Cloth Digitalization
- CVPR 2024Capturing Closely Interacted Two-Person Motions with Reaction Priors
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"}
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。