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 167 篇，第 2 / 4 页

51. ICLR 2025Provably Accurate Shapley Value Estimation via Leverage Score Sampling
52. ICLR 2025Representative Guidance: Diffusion Model Sampling with Coherence
53. ICLR 2025Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior
54. ICLR 2025Sequential Controlled Langevin Diffusions
55. ICLR 2025SFESS: Score Function Estimators for $k$-Subset Sampling
56. ICLR 2025SoftCVI: Contrastive variational inference with self-generated soft labels
57. ICLR 2025Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
58. ICLR 2025Structural-Entropy-Based Sample Selection for Efficient and Effective Learning
59. ICLR 2025T-Stitch: Accelerating Sampling in Pre-Trained Diffusion Models with Trajectory Stitching
60. ICLR 2025TIS-DPO: Token-level Importance Sampling for Direct Preference Optimization With Estimated Weights
61. ICLR 2025Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers
62. ICLR 2025Variational Diffusion Posterior Sampling with Midpoint Guidance
63. ICLR 2025When do GFlowNets learn the right distribution?
64. ICLR 2025Zigzag Diffusion Sampling: Diffusion Models Can Self-Improve via Self-Reflection
65. ICML 2025Accelerated Diffusion Models via Speculative Sampling
66. ICML 2025Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching
67. ICML 2025AutoStep: Locally adaptive involutive MCMC
68. ICML 2025Connecting Thompson Sampling and UCB: Towards More Efficient Trade-offs Between Privacy and Regret
69. ICML 2025Convergence of Consistency Model with Multistep Sampling under General Data Assumptions
70. ICML 2025Demystifying the Paradox of Importance Sampling with an Estimated History-Dependent Behavior Policy in Off-Policy Evaluation
71. ICML 2025Differentiable Solver Search for Fast Diffusion Sampling
72. ICML 2025Diffusion Sampling Correction via Approximately 10 Parameters
73. ICML 2025Distributional Diffusion Models with Scoring Rules
74. ICML 2025Efficiently Vectorized MCMC on Modern Accelerators
75. ICML 2025Exploring Large Action Sets with Hyperspherical Embeddings using von Mises-Fisher Sampling
76. ICML 2025Fast Tensor Completion via Approximate Richardson Iteration
77. ICML 2025Feasible Action Search for Bandit Linear Programs via Thompson Sampling
78. ICML 2025Fundamental Bias in Inverting Random Sampling Matrices with Application to Sub-sampled Newton
79. ICML 2025HPS: Hard Preference Sampling for Human Preference Alignment
80. ICML 2025Importance Corrected Neural JKO Sampling
81. ICML 2025Importance Sampling for Nonlinear Models
82. ICML 2025Improved Lower Bounds for First-order Stochastic Non-convex Optimization under Markov Sampling
83. ICML 2025LEAPS: A discrete neural sampler via locally equivariant networks
84. ICML 2025MoEQuant: Enhancing Quantization for Mixture-of-Experts Large Language Models via Expert-Balanced Sampling and Affinity Guidance
85. ICML 2025Near-Optimal Sample Complexity for MDPs via Anchoring
86. ICML 2025Non-asymptotic Error Bounds in $\mathcal{W}_2$-Distance with Sqrt(d) Dimension Dependence and First Order Convergence for Langevin Monte Carlo beyond Log-Concavity
87. ICML 2025On the Convergence of Continuous Single-timescale Actor-critic
88. ICML 2025Progressive Tempering Sampler with Diffusion
89. ICML 2025Provable Benefit of Random Permutations over Uniform Sampling in Stochastic Coordinate Descent
90. ICML 2025QuRe: Query-Relevant Retrieval through Hard Negative Sampling in Composed Image Retrieval
91. ICML 2025Revisiting Unbiased Implicit Variational Inference
92. ICML 2025ROS: A GNN-based Relax-Optimize-and-Sample Framework for Max-$k$-Cut Problems
93. ICML 2025S4S: Solving for a Fast Diffusion Model Solver
94. ICML 2025Sampling Binary Data by Denoising through Score Functions
95. ICML 2025Sampling from Binary Quadratic Distributions via Stochastic Localization
96. ICML 2025Scalable Equilibrium Sampling with Sequential Boltzmann Generators
97. ICML 2025SITCOM: Step-wise Triple-Consistent Diffusion Sampling For Inverse Problems
98. ICML 2025System-Aware Unlearning Algorithms: Use Lesser, Forget Faster
99. ICML 2025The Polynomial Stein Discrepancy for Assessing Moment Convergence
100. ICML 2025Tuning Sequential Monte Carlo Samplers via Greedy Incremental Divergence Minimization

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。