医疗政策建模论文趋势 2023–2026

主要结论

• 医疗政策建模论文从 2023 年的 134 篇增长到 2026 年的 335 篇，三年间扩大到约 2.5 倍。
• NeurIPS 是发医疗政策建模论文最多的会议，2023–2026 年共 332 篇，占四个会议总量的 38%。
• 交叉方向里涨得最快的是扩散模型：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 30 篇。
• 在「健康与生命科学」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的临床 NLP是 3.2 倍，医疗政策建模是 2.5 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 2026$\chi$-Bench: Can AI Agents Automate End-to-End, Long-Horizon, Policy-Rich Healthcare Workflows?
• ICML 2026Active Policy Optimization for Individualized Dosing via Gradient Variance Minimization
• ICLR 2026A Scalable Inter-edge Correlation Modeling in CopulaGNN for Link Sign Prediction
• CVPR 2026Continuous Exposure-Time Modeling for Realistic Atmospheric Turbulence Synthesis
• NeurIPS 2025$\textit{Hyper-GoalNet}$: Goal-Conditioned Manipulation Policy Learning with HyperNetworks
• ICML 2025How Transformers Learn Structured Data: Insights From Hierarchical Filtering
• ICLR 2025HyPoGen: Optimization-Biased Hypernetworks for Generalizable Policy Generation
• CVPR 2025Bridging Gait Recognition and Large Language Models Sequence Modeling
• NeurIPS 20244DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on RDBs
• ICML 2024ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
• ICLR 2024Learning to Act from Actionless Videos through Dense Correspondences
• CVPR 2024MonoHair: High-Fidelity Hair Modeling from a Monocular Video
• NeurIPS 2023AirDelhi: Fine-Grained Spatio-Temporal Particulate Matter Dataset From Delhi For ML based Modeling
• ICML 2023Adaptive Barrier Smoothing for First-Order Policy Gradient with Contact Dynamics
• ICLR 2023An Adaptive Policy to Employ Sharpness-Aware Minimization
• CVPR 2023BAAM: Monocular 3D Pose and Shape Reconstruction With Bi-Contextual Attention Module and Attention-Guided Modeling
• NeurIPS 2026Budgeted Multi-Source Counterfactual Annotation for Off-Policy Evaluation
• ICML 2026Efficient Continuous-Depth Modeling with GRU Equivalents
• ICLR 2026Chessformer: A Unified Architecture for Chess Modeling
• CVPR 2026D-Prism Differentiable Primitives for Structured Dynamic Modeling

全部医疗政策建模论文

共 875 篇，第 2 / 18 页

51. ICLR 2026Diffusion Fine-Tuning via Reparameterized Policy Gradient of the Soft Q-Function
52. ICLR 2026Discrete Variational Autoencoding via Policy Search
53. ICLR 2026Dynamic Chunking for End-to-End Hierarchical Sequence Modeling
54. ICLR 2026Efficient and Sharp Off-Policy Learning under Unobserved Confounding
55. ICLR 2026Evaluating GFlowNet from partial episodes for stable and flexible policy-based training
56. ICLR 2026Frozen Policy Iteration: Computationally Efficient RL under Linear $Q^{\pi}$ Realizability for Deterministic Dynamics
57. ICLR 2026Geometry-aware Policy Imitation
58. ICLR 2026Group Verification-based Policy Optimization for Interactive Coding Agents
59. ICLR 2026Group-Relative REINFORCE Is Secretly an Off-Policy Algorithm: Demystifying Some Myths About GRPO and Its Friends
60. ICLR 2026H$^3$DP: Triply‑Hierarchical Diffusion Policy for Visuomotor Learning
61. ICLR 2026Healthcare Insurance Fraud Detection via Continual Fiedler Vector Graph Model
62. ICLR 2026Is On-Policy Data always the Best Choice for Direct Preference Optimization-Based LM Alignment?
63. ICLR 2026Jackpot: Align Actor-Policy Distribution for scalable and stable RL for LLM
64. ICLR 2026Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning
65. ICLR 2026Learning What Matters Now: Dynamic Preference Inference under Contextual Shifts
66. ICLR 2026Markovian Transformers for Informative Language Modeling
67. ICLR 2026Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation
68. ICLR 2026Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies
69. ICLR 2026Off-Policy Safe Reinforcement Learning with Cost-Constrained Optimistic Exploration
70. ICLR 2026On the Computational Limits of AI4S-RL : A Unified $\varepsilon$-$N$ Analysis
71. ICLR 2026PHAT: Modeling Period Heterogeneity for Multivariate Time Series Forecasting
72. ICLR 2026Plan-R1: Safe and Feasible Trajectory Planning as Language Modeling
73. ICLR 2026Policy Newton Algorithm in Reproducing Kernel Hilbert Space
74. ICLR 2026Predictive CVaR Q-learning
75. ICLR 2026Pretrain Value, Not Reward: Decoupled Value Policy Optimization
76. ICLR 2026Prosperity before Collapse: How Far Can Off-Policy RL Reach with Stale Data on LLMs?
77. ICLR 2026Relative Value Learning
78. ICLR 2026Remotely Detectable Robot Policy Watermarking
79. ICLR 2026ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models
80. ICLR 2026Rethinking Policy Diversity in Ensemble Policy Gradient in Large-Scale Reinforcement Learning
81. ICLR 2026SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
82. ICLR 2026Safe Exploration via Policy Priors
83. ICLR 2026Sample Efficient Offline RL via T-Symmetry Enforced Latent State-Stitching
84. ICLR 2026SARM: Stage-Aware Reward Modeling for Long Horizon Robot Manipulation
85. ICLR 2026Single-stream Policy Optimization
86. ICLR 2026Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning
87. ICLR 2026SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
88. ICLR 2026Squeeze the Soaked Sponge: Efficient Off-policy RFT for Large Language Model
89. ICLR 2026Teach to Reason Safely: Policy-Guided Safety Tuning for MLRMs
90. ICLR 2026Temporally Detailed Hypergraph Neural ODE for Disease Progression Modeling
91. ICLR 2026Theoretical Modeling of Large Language Model Self-Improvement Training Dynamics Through Solver-Verifier Gap
92. ICLR 2026Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
93. ICLR 2026Towards Better Branching Policies: Leveraging the Sequential Nature of Branch-and-Bound Tree
94. ICLR 2026Translating Flow to Policy via Hindsight Online Imitation
95. ICLR 2026Using Reinforcement Learning to Train Large Language Models to Explain Human Decisions
96. ICML 2026$\texttt{PRISM}$:A 3D Probabilistic Neural Representation for Interpretable Shape Modeling
97. ICML 2026$V_0$: A Generalist Value Model for Any Policy at State Zero
98. ICML 2026Active Policy Optimization for Individualized Dosing via Gradient Variance Minimization
99. ICML 2026Adaptive Policy Backbone via Shared Network
100. ICML 2026Adversarial Dual On-Policy Distillation from Expressive Teacher

常见问题

2023–2026 年四大会议一共有多少篇医疗政策建模论文？

共 875 篇，按年份分别是 2023 年 134 篇、2024 年 194 篇、2025 年 212 篇、2026 年 335 篇。

NeurIPS 2026 有多少篇医疗政策建模论文？

NeurIPS 2026 有 138 篇医疗政策建模论文，上一届是 94 篇。

ICLR 2026 有多少篇医疗政策建模论文？

ICLR 2026 有 58 篇医疗政策建模论文，上一届是 39 篇。

ICML 2026 有多少篇医疗政策建模论文？

ICML 2026 有 102 篇医疗政策建模论文，上一届是 61 篇。

CVPR 2026 有多少篇医疗政策建模论文？

CVPR 2026 有 37 篇医疗政策建模论文，上一届是 18 篇。

哪个会议的医疗政策建模论文最多？

NeurIPS，2023–2026 年共 332 篇。