采样方法论文趋势 2023–2026

主要结论

• 采样方法论文从 2023 年的 122 篇增长到 2026 年的 195 篇，三年间扩大到约 1.6 倍。
• NeurIPS 是发采样方法论文最多的会议，2023–2026 年共 221 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是MCTS：同时属于两个主题的论文从 2023 年的 4 篇增至 2026 年的 31 篇。
• 在「概率与贝叶斯」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的高斯过程是 2.2 倍，采样方法是 1.6 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 2026A Model of Diverse Sampling from Language Models
• ICML 2026BFTS: Thompson Sampling with Bayesian Additive Regression Trees
• ICLR 2026Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
• CVPR 2026Active Inference for Micro-Gesture Recognition EFE-Guided Temporal Sampling and Adaptive
• NeurIPS 2025Antidistillation Sampling
• ICML 2025Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret
• ICLR 2025Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space
• CVPR 2025AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning
• NeurIPS 2024In-and-Out: Algorithmic Diffusion for Sampling Convex Bodies
• ICML 2024Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
• ICLR 2024Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning
• CVPR 2024G-FARS: Gradient-Field-based Auto-Regressive Sampling for 3D Part Grouping
• NeurIPS 2023A Dynamical System View of Langevin-Based Non-Convex Sampling
• ICML 2023Adaptive Annealed Importance Sampling with Constant Rate Progress
• ICLR 2023Any-scale Balanced Samplers for Discrete Space
• CVPR 2023Change-Aware Sampling and Contrastive Learning for Satellite Images
• NeurIPS 2026A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering
• ICML 2026Box Thirding: Anytime Best Arm Identification under Insufficient Sampling
• ICLR 2026On Coreset for LASSO Regression Problem with Sensitivity Sampling
• CVPR 2026Designing Instance-Level Sampling Schedules via REINFORCE with James-Stein Shrinkage

全部采样方法论文

共 156 篇，第 2 / 4 页

51. ICLR 2024Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling
52. ICLR 2024Order-Preserving GFlowNets
53. ICLR 2024Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models
54. ICLR 2024Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
55. ICLR 2024Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
56. ICLR 2024Probabilistically Rewired Message-Passing Neural Networks
57. ICLR 2024Protein Discovery with Discrete Walk-Jump Sampling
58. ICLR 2024Reverse Diffusion Monte Carlo
59. ICLR 2024Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization
60. ICLR 2024Variational Bayesian Last Layers
61. ICML 2024$\mathtt{VITS}$ : Variational Inference Thompson Sampling for contextual bandits
62. ICML 2024A sampling theory perspective on activations for implicit neural representations
63. ICML 2024A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
64. ICML 2024Accelerated Speculative Sampling Based on Tree Monte Carlo
65. ICML 2024Accelerating Parallel Sampling of Diffusion Models
66. ICML 2024Adaptive Sampling of k-Space in Magnetic Resonance for Rapid Pathology Prediction
67. ICML 2024Ai-sampler: Adversarial Learning of Markov kernels with involutive maps
68. ICML 2024Align Your Steps: Optimizing Sampling Schedules in Diffusion Models
69. ICML 2024Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
70. ICML 2024Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling
71. ICML 2024Bifurcated Attention for Single-Context Large-Batch Sampling
72. ICML 2024Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
73. ICML 2024Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?
74. ICML 2024Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics
75. ICML 2024Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond
76. ICML 2024Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution
77. ICML 2024Diffusion Posterior Sampling is Computationally Intractable
78. ICML 2024Diffusion Rejection Sampling
79. ICML 2024Diffusive Gibbs Sampling
80. ICML 2024EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
81. ICML 2024Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing
82. ICML 2024Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling
83. ICML 2024Embarrassingly Parallel GFlowNets
84. ICML 2024EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence
85. ICML 2024Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning
86. ICML 2024Estimating the Permanent by Nesting Importance Sampling
87. ICML 2024Fast Sampling-Based Sketches for Tensors
88. ICML 2024Faster Sampling via Stochastic Gradient Proximal Sampler
89. ICML 2024Feel-Good Thompson Sampling for Contextual Dueling Bandits
90. ICML 2024Generalization Analysis of Stochastic Weight Averaging with General Sampling
91. ICML 2024Gibbs Sampling of Continuous Potentials on a Quantum Computer
92. ICML 2024How Private are DP-SGD Implementations?
93. ICML 2024Improving Gradient-Guided Nested Sampling for Posterior Inference
94. ICML 2024Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
95. ICML 2024Learning to Explore for Stochastic Gradient MCMC
96. ICML 2024Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions
97. ICML 2024No Dimensional Sampling Coresets for Classification
98. ICML 2024On the Trajectory Regularity of ODE-based Diffusion Sampling
99. ICML 2024Optimal bounds for $\ell_p$ sensitivity sampling via $\ell_2$ augmentation
100. ICML 2024Path-Guided Particle-based Sampling

常见问题

2023–2026 年四大会议一共有多少篇采样方法论文？

共 640 篇，按年份分别是 2023 年 122 篇、2024 年 156 篇、2025 年 167 篇、2026 年 195 篇。

NeurIPS 2026 有多少篇采样方法论文？

NeurIPS 2026 有 64 篇采样方法论文，上一届是 67 篇。

ICLR 2026 有多少篇采样方法论文？

ICLR 2026 有 46 篇采样方法论文，上一届是 48 篇。

ICML 2026 有多少篇采样方法论文？

ICML 2026 有 71 篇采样方法论文，上一届是 36 篇。

CVPR 2026 有多少篇采样方法论文？

CVPR 2026 有 14 篇采样方法论文，上一届是 16 篇。

哪个会议的采样方法论文最多？

NeurIPS，2023–2026 年共 221 篇。