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 3 / 4 页

101. ICML 2024Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds
102. ICML 2024Principled Gradient-Based MCMC for Conditional Sampling of Text
103. ICML 2024Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent
104. ICML 2024Reparameterized Importance Sampling for Robust Variational Bayesian Neural Networks
105. ICML 2024Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
106. ICML 2024Sample as you Infer: Predictive Coding with Langevin Dynamics
107. ICML 2024Sampling in Unit Time with Kernel Fisher-Rao Flow
108. ICML 2024Sampling is as easy as keeping the consistency: convergence guarantee for Consistency Models
109. ICML 2024Sampling-based Multi-dimensional Recalibration
110. ICML 2024Stochastic Localization via Iterative Posterior Sampling
111. ICML 2024Stochastic Optimization with Arbitrary Recurrent Data Sampling
112. ICML 2024Stochastic Quantum Sampling for Non-Logconcave Distributions and Estimating Partition Functions
113. ICML 2024Symmetric Matrix Completion with ReLU Sampling
114. ICML 2024The Surprising Effectiveness of Skip-Tuning in Diffusion Sampling
115. ICML 2024Theory of Consistency Diffusion Models: Distribution Estimation Meets Fast Sampling
116. ICML 2024Understanding the Training Speedup from Sampling with Approximate Losses
117. NeurIPS 2024A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
118. NeurIPS 2024Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity
119. NeurIPS 2024Adaptive Sampling for Efficient Softmax Approximation
120. NeurIPS 2024BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
121. NeurIPS 2024Constrained Diffusion with Trust Sampling
122. NeurIPS 2024Constrained Sampling with Primal-Dual Langevin Monte Carlo
123. NeurIPS 2024Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module
124. NeurIPS 2024Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
125. NeurIPS 2024Efficient Leverage Score Sampling for Tensor Train Decomposition
126. NeurIPS 2024Efficient Streaming Algorithms for Graphlet Sampling
127. NeurIPS 2024Ensemble sampling for linear bandits: small ensembles suffice
128. NeurIPS 2024Exactly Minimax-Optimal Locally Differentially Private Sampling
129. NeurIPS 2024Fast samplers for Inverse Problems in Iterative Refinement models
130. NeurIPS 2024Functional Gradient Flows for Constrained Sampling
131. NeurIPS 2024Gradient-based Discrete Sampling with Automatic Cyclical Scheduling
132. NeurIPS 2024Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning
133. NeurIPS 2024Improved Regret of Linear Ensemble Sampling
134. NeurIPS 2024In-and-Out: Algorithmic Diffusion for Sampling Convex Bodies
135. NeurIPS 2024Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models
136. NeurIPS 2024John Ellipsoids via Lazy Updates
137. NeurIPS 2024Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk
138. NeurIPS 2024On Sampling Strategies for Spectral Model Sharding
139. NeurIPS 2024Online Posterior Sampling with a Diffusion Prior
140. NeurIPS 2024pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization
141. NeurIPS 2024Practical Bayesian Algorithm Execution via Posterior Sampling
142. NeurIPS 2024Provable Posterior Sampling with Denoising Oracles via Tilted Transport
143. NeurIPS 2024Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling
144. NeurIPS 2024Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data
145. NeurIPS 2024Scale-invariant Optimal Sampling for Rare-events Data and Sparse Models
146. NeurIPS 2024Score-Optimal Diffusion Schedules
147. NeurIPS 2024SeeA*: Efficient Exploration-Enhanced A* Search by Selective Sampling
148. NeurIPS 2024Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations
149. NeurIPS 2024Simple and Fast Distillation of Diffusion Models
150. NeurIPS 2024Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir 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。