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 2 / 5 页

51. NeurIPS 2026Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels
52. NeurIPS 2026Systematic Hazard Sampling: Minimal-Variance Inference for Discrete Diffusion and Flow Models
53. NeurIPS 2026Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems
54. NeurIPS 2026Temporal Alignment Guidance: On-manifold Sampling in Diffusion Models
55. NeurIPS 2026The Alien Space of Science: Sampling Coherent but Cognitively Unavailable Research Directions
56. NeurIPS 2026The Sampling Complexity of Condorcet Winner Identification in Dueling Bandits
57. NeurIPS 2026Towards instance-dependent regret optimality in Episodic MDPs with Posterior Sampling
58. NeurIPS 2026Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling
59. NeurIPS 2026Training-Free Generative Sampling via Moment-Matched Score Smoothing
60. NeurIPS 2026Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and Dispersion
61. NeurIPS 2026Variational Inference via Entropic Transport Descent
62. NeurIPS 2026Wasserstein Gradient Flows and Forward-Only Diffusion Are Not Enough for Multimodal Sampling
63. NeurIPS 2026What Does the AI Doctor Value? Auditing Pluralism in the Clinical Ethics of Language Models
64. NeurIPS 2026Where to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised Learning
65. NeurIPS 2025$\Psi$-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models
66. NeurIPS 2025A Black-Box Debiasing Framework for Conditional Sampling
67. NeurIPS 2025Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking
68. NeurIPS 2025Accelerating data-driven algorithm selection for combinatorial partitioning problems
69. NeurIPS 2025AdaptGrad: Adaptive Sampling to Reduce Noise
70. NeurIPS 2025Adaptive Stochastic Coefficients for Accelerating Diffusion Sampling
71. NeurIPS 2025Amortized Sampling with Transferable Normalizing Flows
72. NeurIPS 2025Antidistillation Sampling
73. NeurIPS 2025Breaking AR’s Sampling Bottleneck: Provable Acceleration via Diffusion Language Models
74. NeurIPS 2025CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation
75. NeurIPS 2025Channel Simulation and Distributed Compression with Ensemble Rejection Sampling
76. NeurIPS 2025Consistency of the $k_n$-nearest neighbor rule under adaptive sampling
77. NeurIPS 2025Constrained Linear Thompson Sampling
78. NeurIPS 2025Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective
79. NeurIPS 2025Convex Potential Mirror Langevin Algorithm for Efficient Sampling of Energy-Based Models
80. NeurIPS 2025Corrector Sampling in Language Models
81. NeurIPS 2025Coupled Data and Measurement Space Dynamics for Enhanced Diffusion Posterior Sampling
82. NeurIPS 2025Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models
83. NeurIPS 2025DGSolver: Diffusion Generalist Solver with Universal Posterior Sampling for Image Restoration
84. NeurIPS 2025Discrete Neural Flow Samplers with Locally Equivariant Transformer
85. NeurIPS 2025Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation
86. NeurIPS 2025Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling
87. NeurIPS 2025Efficient semantic uncertainty quantification in language models via diversity-steered sampling
88. NeurIPS 2025Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling
89. NeurIPS 2025Exploration via Feature Perturbation in Contextual Bandits
90. NeurIPS 2025Fast constrained sampling in pre-trained diffusion models
91. NeurIPS 2025Fast Local Search Algorithms for Clustering with Adaptive Sampling and Bandit Strategies
92. NeurIPS 2025Fast Non-Log-Concave Sampling under Nonconvex Equality and Inequality Constraints with Landing
93. NeurIPS 2025FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling
94. NeurIPS 2025Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown
95. NeurIPS 2025From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling
96. NeurIPS 2025GIST: Greedy Independent Set Thresholding for Max-Min Diversification with Submodular Utility
97. NeurIPS 2025GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection
98. NeurIPS 2025Learnable Sampler Distillation for Discrete Diffusion Models
99. NeurIPS 2025Leveraging Importance Sampling to Detach Alignment Modules from Large Language Models
100. NeurIPS 2025Masked Diffusion Models as Energy 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。