应用 · chemistry physics and earth sciences论文趋势 2023–2026
应用方向：chemistry_physics_and_earth_sciences
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 3,316 篇被归入该主题的论文。
主要结论
- 应用 · chemistry physics and earth sciences论文从 2023 年的 293 篇增长到 2026 年的 1,217 篇，三年间扩大到约 4.2 倍。
- NeurIPS 是发应用 · chemistry physics and earth sciences论文最多的会议，2023–2026 年共 1,107 篇，占四个会议总量的 33%。
- 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 3 篇增至 2026 年的 95 篇。
- 在「应用领域」的 10 个主题里，它的 2026 年论文数排第 2；同组增长最快的应用 · health medicine是 61 倍，应用 · chemistry physics and earth sciences是 4.2 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 77 | 65 | 83 | 68 | 293 |
| 2024 | 276 | 160 | 164 | 80 | 680 |
| 2025 | 455 | 297 | 287 | 87 | 1,126 |
| 2026 | 299 | 373 | 441 | 104 | 1,217 |
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 2026(Strongly) Replicable Distribution Testers imply High Probability Distribution Testers
- ICML 2026(Be Cautious!) Bio-Foundation Models Are Not Yet Robust to Biologically Plausible Perturbations and ML Transformations
- ICLR 2026(U)NFV: Supervised and Unsupervised Neural Finite Volume Methods for Solving Hyperbolic PDEs
- CVPR 2026AssemblyBench Physics-Aware Assembly of Complex Industrial Objects
- NeurIPS 2025A Partition Cover Approach to Tokenization
- ICML 2025A Machine Learning Approach to Duality in Statistical Physics
- ICLR 2025A new framework for evaluating model out-of-distribution generalisation for the biochemical domain
- CVPR 2025Accurate Differential Operators for Hybrid Neural Fields
- NeurIPS 2024$\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials
- ICML 2024$\bf{\Phi}_\textrm{Flow}$: Differentiable Simulations for PyTorch, TensorFlow and Jax
- ICLR 2024A Foundation Model for Error Correction Codes
- CVPR 2024EarthLoc: Astronaut Photography Localization by Indexing Earth from Space
- NeurIPS 2023ANTN: Bridging Autoregressive Neural Networks and Tensor Networks for Quantum Many-Body Simulation
- ICML 2023A Deep Conjugate Direction Method for Iteratively Solving Linear Systems
- ICLR 2023A framework for benchmarking Class-out-of-distribution detection and its application to ImageNet
- CVPR 20233D Human Pose Estimation via Intuitive Physics
- NeurIPS 2026ADA: Resolving Attribution Ambiguity in End-to-End Power System Dispatch via Two-Time-Scale Stochastic Approximation
- ICML 2026(Sparse) Attention to the Details: Preserving Spectral Fidelity in ML-based Weather Forecasting Models
- ICLR 2026A Genetic Algorithm for Navigating Synthesizable Molecular Spaces
- CVPR 2026Brewing Stronger Features Dual-Teacher Distillation for Multispectral Earth Observation
全部应用 · chemistry physics and earth sciences论文
共 3,316 篇，第 12 / 67 页
- ICML 2026Contrastive Diffusion Alignment: Learning Structured Latents for Controllable Generation
- ICML 2026Contrastive Geometric Learning Unlocks Unified Structure- and Ligand-Based Drug Design
- ICML 2026Controllable Molecule Generation via Sparse Representation Editing: An Interpretability-Driven Perspective
- ICML 2026Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement Learning
- ICML 2026Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption
- ICML 2026Coupled Cluster con MoLe: Molecular Orbital Learning for Neural Wavefunctions
- ICML 2026Credible Information Subset Decomposition: An End-to-End Multi-fidelity Learning Model by Modeling Label Information
- ICML 2026Credit Assignment via Neural Manifold Noise Correlation
- ICML 2026Cross-Chirality Generalization by Axial Vectors for Hetero-Chiral Protein-Peptide Interaction Design
- ICML 2026DAISI: Data Assimilation with Inverse Sampling using Stochastic Interpolants
- ICML 2026DecAEvolve: Decompose, Adapt, and Evolve for Effective LLM-based Scientific Equation Discovery
- ICML 2026DecoderTCR: Compositional Pretraining and Entropy-Guided Decoding for TCR-pMHC Interactions
- ICML 2026Decoupling Universal Laws and Environmental Heterogeneity: A Physics-Inspired Framework for Robust Spatio-Temporal Forecasting
- ICML 2026DecoVer: A Decompose-and-Verify Neuro-Symbolic Framework for Embodied Task Planning with BC+
- ICML 2026Deep Coupling Learning for Solving PDEs
- ICML 2026Deep networks learn to parse uniform-depth context-free languages from local statistics
- ICML 2026Deep Scientific Reasoning under Physical Constraints: Structure-Aware Spectrum Prediction
- ICML 2026Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMs
- ICML 2026Demystifying Multimodal Biomolecular Co-design With Intrinsic Geodesic Coupling
- ICML 2026Demystifying When Pruning Works via Representation Hierarchies
- ICML 2026Derivative Informed Learning of Exchange-Correlation Functionals
- ICML 2026Di-BiLPS: Denoising induced Bidirectional Latent-PDE-Solver under Sparse Observations
- ICML 2026Discontinuous Galerkin Neural Operator for Pathology Defocus Deblurring
- ICML 2026Discovering Ordinary Differential Equations with LLM-Based Qualitative and Quantitative Evaluation
- ICML 2026Discovering Scaling Exponents with Physics-Informed Müntz-Szász Networks
- ICML 2026Discrete Diffusion Samplers and Bridges: Off-Policy Algorithms and Applications in Latent Spaces
- ICML 2026Disentangling Consensus and Value-Specific Representations for Controllable Pluralistic Value Alignment of LLMs
- ICML 2026Dissecting Post-Training: Uncovering the Complementary Roles of SFT and RL for Document Parsing
- ICML 2026DISSOLVR: An Interpretable and Fast Framework for Aqueous and Organic Solubility Prediction
- ICML 2026DLO-Lab: Benchmarking Deformable Linear Object Manipulations with Differentiable Physics
- ICML 2026DNACHUNKER: Learnable Tokenization for DNA Language Models
- ICML 2026dnaHNet: A Scalable and Hierarchical Foundation Model for Genomic Sequence Learning
- ICML 2026Do Neural Operators Forget Geometry? The Forgetting Hypothesis in Deep Operator Learning
- ICML 2026DOCKSMITH: Scaling Reliable Coding Environments via an Agentic Docker Builder
- ICML 2026Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer Review
- ICML 2026Drop-in Circulant Structural Priors for Transformer Decoding of Cyclic Codes
- ICML 2026DualTimesField: Rethinking Time Series as Continuous-Time Trends and Events
- ICML 2026DuRP: Dual-Stage Physics-Embedded Learning for Joint Radiance and Polarization Restoration
- ICML 2026Dynamic Regret via Discounted-to-Dynamic Reduction with Applications to Curved Losses and Adam Optimizer
- ICML 2026Dynamic Relational Priming Improves Transformer in Multivariate Time Series
- ICML 2026Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks
- ICML 2026ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation
- ICML 2026Effects of Structural Reward Shaping on Biophysical Properties in RL-Trained Plasmid Generators
- ICML 2026EffGen: Enabling Small Language Models as Capable Autonomous Agents
- ICML 2026Efficient Adaptive Testing via Gradient Path Matching Subset Selection for AI Education
- ICML 2026Efficient and Safe Molecular Assembly via Reinforcement Learning and Constraint Solving
- ICML 2026Efficient Equivariant High-Order Crystal Tensor Prediction via Cartesian Local-Environment Many-Body Coupling
- ICML 2026Efficient Prediction of SO(3)-Equivariant Hamiltonian Matrices via SO(2) Local Frames
- ICML 2026Efficient Training of Boltzmann Generators Using Off-Policy Log-Dispersion Regularization
- ICML 2026Elign: Equivariant Diffusion Model Alignment from Foundational Machine Learned Force Fields
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 查应用 · chemistry physics and earth sciences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": "app-chemistry-physics-and-earth-sciences"}
常见问题
- 2023–2026 年四大会议一共有多少篇应用 · chemistry physics and earth sciences论文？
- 共 3,316 篇，按年份分别是 2023 年 293 篇、2024 年 680 篇、2025 年 1,126 篇、2026 年 1,217 篇。
- NeurIPS 2026 有多少篇应用 · chemistry physics and earth sciences论文？
- NeurIPS 2026 有 299 篇应用 · chemistry physics and earth sciences论文，上一届是 455 篇。
- ICLR 2026 有多少篇应用 · chemistry physics and earth sciences论文？
- ICLR 2026 有 373 篇应用 · chemistry physics and earth sciences论文，上一届是 297 篇。
- ICML 2026 有多少篇应用 · chemistry physics and earth sciences论文？
- ICML 2026 有 441 篇应用 · chemistry physics and earth sciences论文，上一届是 287 篇。
- CVPR 2026 有多少篇应用 · chemistry physics and earth sciences论文？
- CVPR 2026 有 104 篇应用 · chemistry physics and earth sciences论文，上一届是 87 篇。
- 哪个会议的应用 · chemistry physics and earth sciences论文最多？
- NeurIPS，2023–2026 年共 1,107 篇。