药物发现论文趋势 2023–2026

主要结论

• 药物发现论文从 2023 年的 79 篇增长到 2026 年的 211 篇，三年间扩大到约 2.7 倍。
• NeurIPS 是发药物发现论文最多的会议，2023–2026 年共 234 篇，占四个会议总量的 40%。
• 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 1 篇增至 2026 年的 42 篇。
• 在「健康与生命科学」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的临床 NLP是 3.2 倍，药物发现是 2.7 倍。

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 2026ACER: Towards Generalizable Protein-ligand Co-folding
• ICML 2026Adaptive Symmetry Discovery for Dynamical System Identification
• ICLR 2026Bures Generalized Category Discovery
• CVPR 2026Learning Like Humans Analogical Concept Learning for Generalized Category Discovery
• NeurIPS 2025AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation
• ICML 2025Explicit Discovery of Nonlinear Symmetries from Dynamic Data
• ICLR 2025CBGBench: Fill in the Blank of Protein-Molecule Complex Binding Graph
• CVPR 2025Adaptive Part Learning for Fine-Grained Generalized Category Discovery: A Plug-and-Play Enhancement
• NeurIPS 2024A SARS-CoV-2 Interaction Dataset and VHH Sequence Corpus for Antibody Language Models
• ICML 2024Amortized Equation Discovery in Hybrid Dynamical Systems
• ICLR 2024Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment
• CVPR 2024Federated Generalized Category Discovery
• NeurIPS 2023An Optimization-based Approach To Node Role Discovery in Networks: Approximating Equitable Partitions
• ICML 2023A Group Symmetric Stochastic Differential Equation Model for Molecule Multi-modal Pretraining
• ICLR 2023Context-enriched molecule representations improve few-shot drug discovery
• CVPR 2023Bootstrap Your Own Prior: Towards Distribution-Agnostic Novel Class Discovery
• NeurIPS 2026Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules
• ICML 2026CURE: Consistency-under-Unified Semantic Regularization for Generalized Category Discovery
• ICLR 2026Exploring Synthesizable Chemical Space with Iterative Pathway Refinements
• CVPR 2026TAR Token-Aware Refinement for Fine-grained Generalized Category Discovery

全部药物发现论文

共 234 篇，第 2 / 5 页

51. NeurIPS 2026Interpreting Latent Protein Language Model Features with Geometric Annotations
52. NeurIPS 2026Learning Generative Dynamics for 3D Molecule Generation via Sequential Neuro-Symbolic Constraints
53. NeurIPS 2026Lifting Biomolecular Data Acquisition
54. NeurIPS 2026LLM-AutoSciLab: Closed-Loop Scientific Law Discovery via Active Experimentation with LLMs
55. NeurIPS 2026LLMs Improving LLMs: Agentic Discovery for Test-Time Scaling
56. NeurIPS 2026Mapping Uncharted Symmetries: Machine Discovery in Combinatorics
57. NeurIPS 2026Mimicking the Physicist's Eye: A VLM-centric Approach for Physics Formula Discovery
58. NeurIPS 2026MIND-DDI: Multi-Omics Interpretable Drug-Drug Interaction Prediction with Joint Optimization of Graph Structure, Neural Architecture, and Symbolic Rules
59. NeurIPS 2026MolSpecFlow: Modality-Incomplete Molecular--Spectral Learning for MS/MS
60. NeurIPS 2026MOSAIC: Module Discovery via Sparse Additive Identifiable Causal Learning for Scientific Time Series
61. NeurIPS 2026Multi-Oracle Agreement Reveals the Limits of Self-Consistency Evaluation in RNA Design
62. NeurIPS 2026Multi-Part Object Representations via Graph Structures and Co-Part Discovery
63. NeurIPS 2026NORMA: Norm-Guided Explanation Subgraph Discovery
64. NeurIPS 2026On the Selectivity of Generative Models in Structure-Based Drug Design
65. NeurIPS 2026Open-Ended Scientific Discovery and the Social Dynamics of Evolving Agent Networks
66. NeurIPS 2026Optimizing Analytic Constants via AI-Guided Lean Proof Refinement
67. NeurIPS 2026PAIR-CI: Calibrated Conditional Independence Testing for Causal Discovery with Incomplete Data
68. NeurIPS 2026PIGRAM: An Interpretable Patch--Motif Interaction Grammar for Protein--Nucleic-Acid Recognition
69. NeurIPS 2026Position: Machine Learning Models for Reaction Transition States Deserve Better
70. NeurIPS 2026Preserving DEG Rankings for Gene Discovery in Histology-Based Spatial Gene Expression Prediction
71. NeurIPS 2026Probe Before You Edit: Probing-Guided Molecular Optimization for LLM Agents in Structure-Based Drug Design
72. NeurIPS 2026ProteinOPD: Towards Effective and Efficient Preference Alignment for Protein Design
73. NeurIPS 2026ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and Model
74. NeurIPS 2026Pushing Biomolecular Utility-Diversity Frontiers with Supergroup Relative Policy Optimization
75. NeurIPS 2026QT-Net: Rethinking Evaluation of AI Models in Atomic Chemical Space
76. NeurIPS 2026Reusable Conditional Resampling via Flow Matching for Constraint-Based Causal Discovery
77. NeurIPS 2026RnR: a meta-solver for causal discovery in undersampled time series data
78. NeurIPS 2026Runtime Analysis of Cartesian Genetic Programming on MAX: A Proven Exponential Speedup
79. NeurIPS 2026SCDM: Scalable Causal Discovery in Nonlinear Temporal Systems with Meta-Learning
80. NeurIPS 2026SciResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery
81. NeurIPS 2026ScopeSAE: Model-Scope Feature Discovery with Interpretable Layer Selection
82. NeurIPS 2026Screening Lipid Nanoparticles through Structure-Ratio Alignment
83. NeurIPS 2026ScreenShot: A Foundation Model for Few-Shot Combination Drug Screening
84. NeurIPS 2026Seen-Constrained Model-Order Selection for Unknown-$K$ Generalized Category Discovery
85. NeurIPS 2026Self-Improvement Imitation with Biologically Guided Search for Protein Design Under Oracle Budgets
86. NeurIPS 2026Self-Supervised Keyframe Discovery for Horizon-Invariant Behavior Cloning
87. NeurIPS 2026SLOT-IR: Learning Disentangled Slot Representations for Infrared Spectral Unmixing
88. NeurIPS 2026SNACK: A Sequential Notation Framework for Probabilistic Graph Generation
89. NeurIPS 2026Sparse Biological Features Reveal Early Functional Commitment in Diffusion Protein Language Models
90. NeurIPS 2026Structure-aware Reinforcement Learning for Protein Directed Evolution
91. NeurIPS 2026Temporal Selective Exploration for Reinforcement Learning-Guided Continuous-Discrete Flow Matching in 3D Molecular Design
92. NeurIPS 2026TrialAgentBench: Evaluating AI Agents for Clinical-Trial Analysis and Long-Horizon Drug-Development Decisions
93. NeurIPS 2026Trustworthy Retrosynthesis: Eliminating Hallucinations with a Diverse Ensemble of Reaction Scorers
94. NeurIPS 2026Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks
95. NeurIPS 2026UniFlowDock: Flexible Docking with Complete Equivariant Velocity Fields
96. NeurIPS 2026Unsupervised Concept Discovery with Dirichlet Concept Diffusion Models
97. NeurIPS 2026Virtual Double Oracle: Faster Convergence by Leveraging Strategies That Were Watching All Along
98. NeurIPS 2026Weather-Robust Cross-View Geo-Localization via Prototype-Based Semantic Part Discovery
99. NeurIPS 2026When Does Knowing the State Help? Diagnosing Process vs. Outcome Reward Design
100. NeurIPS 2026When Transcriptomic Foundation Models Scale: Domain-Focused Pretraining for Drug Development in Immunology and Inflammation

常见问题

2023–2026 年四大会议一共有多少篇药物发现论文？

共 578 篇，按年份分别是 2023 年 79 篇、2024 年 125 篇、2025 年 163 篇、2026 年 211 篇。

NeurIPS 2026 有多少篇药物发现论文？

NeurIPS 2026 有 100 篇药物发现论文，上一届是 64 篇。

ICLR 2026 有多少篇药物发现论文？

ICLR 2026 有 37 篇药物发现论文，上一届是 48 篇。

ICML 2026 有多少篇药物发现论文？

ICML 2026 有 63 篇药物发现论文，上一届是 39 篇。

CVPR 2026 有多少篇药物发现论文？

CVPR 2026 有 11 篇药物发现论文，上一届是 12 篇。

哪个会议的药物发现论文最多？

NeurIPS，2023–2026 年共 234 篇。