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 640 篇，第 2 / 13 页

51. ICLR 2026Sampling Complexity of TD and PPO in RKHS
52. ICLR 2026Score-Based Density Estimation from Pairwise Comparisons
53. ICLR 2026SPREAD: Sampling-based Pareto front Refinement via Efficient Adaptive Diffusion
54. ICLR 2026Stable coresets: Unleashing the power of uniform sampling
55. ICLR 2026STORK: Faster Diffusion and Flow Matching Sampling by Resolving both Stiffness and Structure-Dependence
56. ICLR 2026Strictly Constrained Generative Modeling via Split Augmented Langevin Sampling
57. ICLR 2026Taming Imperfect Process Verifiers: A Sampling Perspective on Backtracking
58. ICLR 2026Towards Sampling Data Structures for Tensor Products in Turnstile Streams
59. ICLR 2026vAttention: Verified Sparse Attention via Sampling
60. ICLR 2026When Scores Learn Geometry: Rate Separations under the Manifold Hypothesis
61. ICML 2026$f$-Divergence Regularized RLHF: Two Tales of Sampling and Unified Analyses
62. ICML 2026A geometric relation of the error introduced by sampling a language model's output distribution to its internal state
63. ICML 2026Accelerating Langevin Monte Carlo via Efficient Stochastic Runge-Kutta Methods beyond Log-Concavity
64. ICML 2026Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo
65. ICML 2026Adversarial Attack and Defense for Denoising Diffusion Sampling
66. ICML 2026Annotations Mitigate Post-Training Mode Collapse
67. ICML 2026ASIR: Steganography for Diffusion Models via Antipodal Sampling and Iterative Recovery
68. ICML 2026Avoid What You Know: Divergent Trajectory Balance for GFlowNets
69. ICML 2026BFTS: Thompson Sampling with Bayesian Additive Regression Trees
70. ICML 2026Box Thirding: Anytime Best Arm Identification under Insufficient Sampling
71. ICML 2026Bridge Matching Sampler: Scalable Sampling via Generalized Fixed-Point Diffusion Matching
72. ICML 2026Can Microcanonical Langevin Dynamics Leverage Mini-Batch Gradient Noise?
73. ICML 2026Conditional Diffusion Sampling
74. ICML 2026ConFu: Contemplate the Future for Better Speculative Sampling
75. ICML 2026Constrained Adaptive Rejection Sampling
76. ICML 2026Contrastive Flow Map Matching
77. ICML 2026ContrastiveCFG: Guiding Diffusion Sampling by Contrasting Positive and Negative Concepts
78. ICML 2026Corrected Samplers for Discrete Flow Models
79. ICML 2026Covariance estimation using Markov chain Monte Carlo
80. ICML 2026DAISI: Data Assimilation with Inverse Sampling using Stochastic Interpolants
81. ICML 2026DC-LA: Difference-of-Convex Langevin Algorithm
82. ICML 2026Dimension-Free Multimodal Sampling via Preconditioned Annealed Langevin Dynamics
83. ICML 2026Dimension-Independent Convergence of Underdamped Langevin Monte Carlo in KL Divergence
84. ICML 2026Entropic Mirror Monte Carlo
85. ICML 2026Fast Estimation for Forest Matrix of Signed Graphs
86. ICML 2026Fast k-means Seeding Under The Manifold Hypothesis
87. ICML 2026Flatness-Aware Stochastic Gradient Langevin Dynamics
88. ICML 2026FlowState: Sampling-Rate‑Equivariant Time‑Series Forecasting
89. ICML 2026Forward-KL Convergence of Time-Inhomogeneous Langevin Diffusions
90. ICML 2026Functional Adjoint Sampler: Scalable Sampling on Infinite Dimensional Spaces
91. ICML 2026Geometry-Correct Diffusion Posterior Sampling with Denoiser-Pullback Curvature Guidance and Manifold-Aligned Damping
92. ICML 2026High-accuracy and dimension-free sampling with diffusions
93. ICML 2026High-Accuracy Sampling for Diffusion Models and Log-Concave Distributions
94. ICML 2026HOBIT: Hardness Optimized Batch Sampling for InfoNCE Training
95. ICML 2026How does Bayesian Sampling help Membership Inference Attacks?
96. ICML 2026Improving Zero-Shot Offline RL via Behavioral Task Sampling
97. ICML 2026Initialization is Half the Battle: Generating Diverse Images from a Guidance Potential Posterior
98. ICML 2026Inverting Data Transformations via Diffusion Sampling
99. ICML 2026Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo
100. ICML 2026Less Data, Faster Training: repeating smaller datasets speeds up learning via sampling biases

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。