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 122 篇，第 2 / 3 页

51. ICML 2023On Sampling with Approximate Transport Maps
52. ICML 2023Optimality of Thompson Sampling with Noninformative Priors for Pareto Bandits
53. ICML 2023Optimizing DDPM Sampling with Shortcut Fine-Tuning
54. ICML 2023PixelAsParam: A Gradient View on Diffusion Sampling with Guidance
55. ICML 2023Posterior Sampling for Deep Reinforcement Learning
56. ICML 2023Quantum Speedups for Zero-Sum Games via Improved Dynamic Gibbs Sampling
57. ICML 2023Revisiting Sampling for Combinatorial Optimization
58. ICML 2023Rigid Body Flows for Sampling Molecular Crystal Structures
59. ICML 2023Sampling-Based Accuracy Testing of Posterior Estimators for General Inference
60. ICML 2023Sampling-based Nyström Approximation and Kernel Quadrature
61. ICML 2023Self-Repellent Random Walks on General Graphs - Achieving Minimal Sampling Variance via Nonlinear Markov Chains
62. ICML 2023Sharper Bounds for $\ell_p$ Sensitivity Sampling
63. ICML 2023Stochastic Gradient Descent under Markovian Sampling Schemes
64. ICML 2023The Power of Uniform Sampling for k-Median
65. ICML 2023Thompson Sampling for High-Dimensional Sparse Linear Contextual Bandits
66. ICML 2023Thompson Sampling with Diffusion Generative Prior
67. ICML 2023Thompson Sampling with Less Exploration is Fast and Optimal
68. ICML 2023TIPS: Topologically Important Path Sampling for Anytime Neural Networks
69. ICML 2023Uncertainty Estimation for Molecules: Desiderata and Methods
70. ICML 2023User-defined Event Sampling and Uncertainty Quantification in Diffusion Models for Physical Dynamical Systems
71. ICML 2023Weighted Sampling without Replacement for Deep Top-$k$ Classification
72. ICML 2023Why Target Networks Stabilise Temporal Difference Methods
73. NeurIPS 2023A Dynamical System View of Langevin-Based Non-Convex Sampling
74. NeurIPS 2023A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems
75. NeurIPS 2023Adversarial Robustness through Random Weight Sampling
76. NeurIPS 2023Block Broyden's Methods for Solving Nonlinear Equations
77. NeurIPS 2023Block Coordinate Plug-and-Play Methods for Blind Inverse Problems
78. NeurIPS 2023Block-Coordinate Methods and Restarting for Solving Extensive-Form Games
79. NeurIPS 2023DELTA: Diverse Client Sampling for Fasting Federated Learning
80. NeurIPS 2023Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick
81. NeurIPS 2023DISCS: A Benchmark for Discrete Sampling
82. NeurIPS 2023Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee
83. NeurIPS 2023DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics
84. NeurIPS 2023Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models
85. NeurIPS 2023Epidemic Learning: Boosting Decentralized Learning with Randomized Communication
86. NeurIPS 2023Expressive probabilistic sampling in recurrent neural networks
87. NeurIPS 2023Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions
88. NeurIPS 2023Fast Exact Leverage Score Sampling from Khatri-Rao Products with Applications to Tensor Decomposition
89. NeurIPS 2023Fast Rank-1 Lattice Targeted Sampling for Black-box Optimization
90. NeurIPS 2023FouriDown: Factoring Down-Sampling into Shuffling and Superposing
91. NeurIPS 2023Gradient-Free Kernel Stein Discrepancy
92. NeurIPS 2023Greedy Poisson Rejection Sampling
93. NeurIPS 2023How Re-sampling Helps for Long-Tail Learning?
94. NeurIPS 2023K-Nearest-Neighbor Local Sampling Based Conditional Independence Testing
95. NeurIPS 2023Kernel Quadrature with Randomly Pivoted Cholesky
96. NeurIPS 2023Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards
97. NeurIPS 2023Langevin Quasi-Monte Carlo
98. NeurIPS 2023Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs
99. NeurIPS 2023Learning Re-sampling Methods with Parameter Attribution for Image Super-resolution
100. NeurIPS 2023Metropolis Sampling for Constrained Diffusion Models

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。