分子建模论文趋势 2023–2026
分子性质与生成
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,038 篇被归入该主题的论文。
主要结论
- 分子建模论文从 2023 年的 137 篇增长到 2026 年的 373 篇，三年间扩大到约 2.7 倍。
- NeurIPS 是发分子建模论文最多的会议，2023–2026 年共 351 篇，占四个会议总量的 34%。
- 交叉方向里涨得最快的是应用 · chemistry physics and earth sciences：同时属于两个主题的论文从 2023 年的 5 篇增至 2026 年的 59 篇。
- 在「图与结构化数据」的 5 个主题里，它的 2026 年论文数排第 3；同组增长最快的时间序列是 3.2 倍，分子建模是 2.7 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 27 | 44 | 21 | 45 | 137 |
| 2024 | 78 | 38 | 60 | 31 | 207 |
| 2025 | 132 | 80 | 63 | 46 | 321 |
| 2026 | 114 | 90 | 107 | 62 | 373 |
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 2026Atomic Trajectory Modeling with State Space Models for Biomolecular Dynamics
- ICML 2026Controlled SDEs for Long-Horizon Motion Generation under Latent Decision Uncertainty
- ICLR 2026A Scalable Inter-edge Correlation Modeling in CopulaGNN for Link Sign Prediction
- CVPR 2026CARE A Molecular-Guided Foundation Model with Adaptive Region Modeling for
- NeurIPS 20253D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding
- ICML 2025BAnG: Bidirectional Anchored Generation for Conditional RNA Design
- ICLR 20253D-MolT5: Leveraging Discrete Structural Information for Molecule-Text Modeling
- CVPR 2025Bridging Gait Recognition and Large Language Models Sequence Modeling
- NeurIPS 20244DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on RDBs
- ICML 2024An amortized approach to non-linear mixed-effects modeling based on neural posterior estimation
- ICLR 2024$\texttt{NAISR}$: A 3D Neural Additive Model for Interpretable Shape Representation
- CVPR 2024EVS-assisted Joint Deblurring Rolling-Shutter Correction and Video Frame Interpolation through Sensor Inverse Modeling
- NeurIPS 2023Learning Invariant Molecular Representation in Latent Discrete Space
- ICML 2023Biases in Evaluation of Molecular Optimization Methods and Bias Reduction Strategies
- ICLR 2023$\mathcal{O}$-GNN: incorporating ring priors into molecular modeling
- CVPR 2023BAAM: Monocular 3D Pose and Shape Reconstruction With Bi-Contextual Attention Module and Attention-Guided Modeling
- NeurIPS 2026CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening
- ICML 2026Efficient Continuous-Depth Modeling with GRU Equivalents
- ICLR 2026Anime-Ready: Controllable 3D Anime Character Generation with Body-Aligned Component-Wise Garment Modeling
- CVPR 2026Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis
全部分子建模论文
共 321 篇，第 4 / 7 页
- ICML 2025Flexibility-conditioned protein structure design with flow matching
- ICML 2025Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages
- ICML 2025Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning
- ICML 2025Geometric Generative Modeling with Noise-Conditioned Graph Networks
- ICML 2025How Transformers Learn Structured Data: Insights From Hierarchical Filtering
- ICML 2025Improving Diversity in Language Models: When Temperature Fails, Change the Loss
- ICML 2025Improving Reward Model Generalization from Adversarial Process Enhanced Preferences
- ICML 2025Integration-free Kernels for Equivariant Gaussian Process Modelling
- ICML 2025KV Shifting Attention Enhances Language Modeling
- ICML 2025LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
- ICML 2025LASER: Attention with Exponential Transformation
- ICML 2025LAST SToP for Modeling Asynchronous Time Series
- ICML 2025Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction
- ICML 2025Learning-Order Autoregressive Models with Application to Molecular Graph Generation
- ICML 2025MIPT: Multilevel Informed Prompt Tuning for Robust Molecular Property Prediction
- ICML 2025Modeling Multi-Task Model Merging as Adaptive Projective Gradient Descent
- ICML 2025Modulated Diffusion: Accelerating Generative Modeling with Modulated Quantization
- ICML 2025Neural Graph Matching Improves Retrieval Augmented Generation in Molecular Machine Learning
- ICML 2025On-Device Collaborative Language Modeling via a Mixture of Generalists and Specialists
- ICML 2025OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling
- ICML 2025Overcoming Vocabulary Mismatch: Vocabulary-agnostic Teacher Guided Language Modeling
- ICML 2025PolyConf: Unlocking Polymer Conformation Generation through Hierarchical Generative Models
- ICML 2025Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation
- ICML 2025Quadruple Attention in Many-body Systems for Accurate Molecular Property Predictions
- ICML 2025Reaction Graph: Towards Reaction-Level Modeling for Chemical Reactions with 3D Structures
- ICML 2025Reinforcement Learning with Adaptive Reward Modeling for Expensive-to-Evaluate Systems
- ICML 2025Representation Surgery in Model Merging with Probabilistic Modeling
- ICML 2025Reward Modeling with Ordinal Feedback: Wisdom of the Crowd
- ICML 2025RISE: Radius of Influence based Subgraph Extraction for 3D Molecular Graph Explanation
- ICML 2025Self-Discriminative Modeling for Anomalous Graph Detection
- ICML 2025SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator
- ICML 2025Smooth Interpolation for Improved Discrete Graph Generative Models
- ICML 2025Sparse Autoencoders for Hypothesis Generation
- ICML 2025Symmetry-Driven Discovery of Dynamical Variables in Molecular Simulations
- ICML 2025Towards Escaping from Class Dependency Modeling for Multi-Dimensional Classification
- ICML 2025Visual Generation Without Guidance
- ICML 2025Wasserstein Flow Matching: Generative Modeling Over Families of Distributions
- ICML 2025WGFormer: An SE(3)-Transformer Driven by Wasserstein Gradient Flows for Molecular Ground-State Conformation Prediction
- ICML 2025When to retrain a machine learning model
- NeurIPS 20253D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding
- NeurIPS 2025Adaptive Preference Arithmetic: A Personalized Agent with Adaptive Preference Arithmetic for Dynamic Preference Modeling
- NeurIPS 2025Adjoint Schrödinger Bridge Sampler
- NeurIPS 2025Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling
- NeurIPS 2025ArchPower: Dataset for Architecture-Level Power Modeling of Modern CPU Design
- NeurIPS 2025ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction
- NeurIPS 2025Automatic Auxiliary Task Selection and Adaptive Weighting Boost Molecular Property Prediction
- NeurIPS 2025Beyond Node-Centric Modeling: Sketching Signed Networks with Simplicial Complexes
- NeurIPS 2025Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global Constraints
- NeurIPS 2025BioCG: Constrained Generative Modeling for Biochemical Interaction Prediction
- NeurIPS 2025BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models
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 查分子建模在 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": "molecular-modeling"}
常见问题
- 2023–2026 年四大会议一共有多少篇分子建模论文？
- 共 1,038 篇，按年份分别是 2023 年 137 篇、2024 年 207 篇、2025 年 321 篇、2026 年 373 篇。
- NeurIPS 2026 有多少篇分子建模论文？
- NeurIPS 2026 有 114 篇分子建模论文，上一届是 132 篇。
- ICLR 2026 有多少篇分子建模论文？
- ICLR 2026 有 90 篇分子建模论文，上一届是 80 篇。
- ICML 2026 有多少篇分子建模论文？
- ICML 2026 有 107 篇分子建模论文，上一届是 63 篇。
- CVPR 2026 有多少篇分子建模论文？
- CVPR 2026 有 62 篇分子建模论文，上一届是 46 篇。
- 哪个会议的分子建模论文最多？
- NeurIPS，2023–2026 年共 351 篇。