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 221 篇，第 3 / 5 页

101. NeurIPS 2025Metropolis Adjusted Microcanonical Hamiltonian Monte Carlo
102. NeurIPS 2025Metropolis-Hastings Sampling for 3D Gaussian Reconstruction
103. NeurIPS 2025MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling
104. NeurIPS 2025Mitigating Instability in High Residual Adaptive Sampling for PINNs via Langevin Dynamics
105. NeurIPS 2025No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes
106. NeurIPS 2025Parallelizing MCMC Across the Sequence Length
107. NeurIPS 2025PID-controlled Langevin Dynamics for Faster Sampling on Generative Models
108. NeurIPS 2025Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics
109. NeurIPS 2025Riemannian Proximal Sampler for High-accuracy Sampling on Manifolds
110. NeurIPS 2025Robust Sampling for Active Statistical Inference
111. NeurIPS 2025Sample-Adaptivity Tradeoff in On-Demand Sampling
112. NeurIPS 2025Sampled Estimators For Softmax Must Be Biased
113. NeurIPS 2025Sampling 3D Molecular Conformers with Diffusion Transformers
114. NeurIPS 2025Sampling by averaging: A multiscale approach to score estimation
115. NeurIPS 2025Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusion
116. NeurIPS 2025Scalable Exploration via Ensemble++
117. NeurIPS 2025Sequential Attention-based Sampling for Histopathological Analysis
118. NeurIPS 2025Solving Inverse Problems with FLAIR
119. NeurIPS 2025Sparse Optimistic Information Directed Sampling
120. NeurIPS 2025Split Gibbs Discrete Diffusion Posterior Sampling
121. NeurIPS 2025SPMDM: Enhancing Masked Diffusion Models through Simplifing Sampling Path
122. NeurIPS 2025Stable Coresets via Posterior Sampling: Aligning Induced and Full Loss Landscapes
123. NeurIPS 2025Structure-Aware Spectral Sparsification via Uniform Edge Sampling
124. NeurIPS 2025TADA: Improved Diffusion Sampling with Training-free Augmented DynAmics
125. NeurIPS 2025Thompson Sampling for Multi-Objective Linear Contextual Bandit
126. NeurIPS 2025Thompson Sampling in Function Spaces via Neural Operators
127. NeurIPS 2025TPP-SD: Accelerating Transformer Point Process Sampling with Speculative Decoding
128. NeurIPS 2025Two‑Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion
129. NeurIPS 2025Unveiling Extraneous Sampling Bias with Data Missing-Not-At-Random
130. NeurIPS 2025Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits
131. NeurIPS 2025Variational Task Vector Composition
132. NeurIPS 2024A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
133. NeurIPS 2024Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity
134. NeurIPS 2024Adaptive Sampling for Efficient Softmax Approximation
135. NeurIPS 2024BoNBoN Alignment for Large Language Models and the Sweetness of Best-of-n Sampling
136. NeurIPS 2024Constrained Diffusion with Trust Sampling
137. NeurIPS 2024Constrained Sampling with Primal-Dual Langevin Monte Carlo
138. NeurIPS 2024Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module
139. NeurIPS 2024Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
140. NeurIPS 2024Efficient Leverage Score Sampling for Tensor Train Decomposition
141. NeurIPS 2024Efficient Streaming Algorithms for Graphlet Sampling
142. NeurIPS 2024Ensemble sampling for linear bandits: small ensembles suffice
143. NeurIPS 2024Exactly Minimax-Optimal Locally Differentially Private Sampling
144. NeurIPS 2024Fast samplers for Inverse Problems in Iterative Refinement models
145. NeurIPS 2024Functional Gradient Flows for Constrained Sampling
146. NeurIPS 2024Gradient-based Discrete Sampling with Automatic Cyclical Scheduling
147. NeurIPS 2024Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning
148. NeurIPS 2024Improved Regret of Linear Ensemble Sampling
149. NeurIPS 2024In-and-Out: Algorithmic Diffusion for Sampling Convex Bodies
150. NeurIPS 2024Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language 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。