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 1 / 5 页

1. NeurIPS 2026A Model of Diverse Sampling from Language Models
2. NeurIPS 2026A Semantic-Sampling Framework for Evaluating Calibration in Open-Ended Question Answering
3. NeurIPS 2026Adaptive Prior Selection in Gaussian Process Bandits with Thompson Sampling
4. NeurIPS 2026ART for Diffusion Sampling: A Reinforcement Learning Approach to Timestep Scheduling
5. NeurIPS 2026AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs
6. NeurIPS 2026Beyond Langevin: Sampling Multimodal Densities using the Witten Laplacian on 1-forms
7. NeurIPS 2026Breaking the $\sqrt{d}$ Communication Barrier in Federated Sampling with Adaptive Hamiltonian Monte Carlo
8. NeurIPS 2026BridgeTwist: Twisting Schrödinger Bridges for Training-Free Conditional Sampling
9. NeurIPS 2026Characterizing Memorization in Diffusion Language Models: Generalized Extraction and Sampling Effects
10. NeurIPS 2026Colored Noise Diffusion Sampling
11. NeurIPS 2026Contour Monte Carlo: Sampling via Energy Level Sets
12. NeurIPS 2026DETS: An Interval-Censored Evidential Sampling Framework for Cross-Domain Scientific Discovery
13. NeurIPS 2026Diffusion-warm sampling of the XY model enables fast thermalization at scale
14. NeurIPS 2026Does Mixed Label Imbalance Matter to Minority Collapse in Imbalanced Learning?
15. NeurIPS 2026Efficient Learning of Truncated Boolean Product Distributions: Influence to the Rescue
16. NeurIPS 2026Estimating the expected output of wide random MLPs more efficiently than sampling
17. NeurIPS 2026Finetuning with Sampling: Make SFT Generalize, Not Forget
18. NeurIPS 2026FLASH: Efficient Visuomotor Policy via Sparse Sampling
19. NeurIPS 2026GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
20. NeurIPS 2026Gumbo: Gumbel Optimized High-Temperature Speculative Sampling
21. NeurIPS 2026Informed Posterior Sampling: More Efficient Online Learning with Few Offline Demonstrations in Average-Reward MDPs
22. NeurIPS 2026Language Models Can Coarsely Modulate Entropy Under Instruction
23. NeurIPS 2026Linear Ensemble Sampling with Fewer Ensembles
24. NeurIPS 2026Metropolis-Adjusted Diffusion Models
25. NeurIPS 2026NanoFold: Designing Reproducible Protein Structure Benchmarks through Principled Sampling
26. NeurIPS 2026On Concentration Inequalities for Sampling without Replacement
27. NeurIPS 2026On Inherent Privacy of Posterior Sampling: A Unified R\'enyi-Divergence Framework
28. NeurIPS 2026Online Active Testing: Adaptive Importance Sampling for Unbiased Risk Estimation in Data Streams
29. NeurIPS 2026Optimal Dimension-Free Sampling for Regularized Classification
30. NeurIPS 2026Outlier-robust Diffusion Posterior Sampling for Bayesian Inverse Problems
31. NeurIPS 2026Parallel Computation Algorithms and Convergence Guarantees for Mean-Field Langevin Dynamics
32. NeurIPS 2026ParaPC-FM: Accelerating Parallel Sampling via Principled Initialization
33. NeurIPS 2026PEEK: One-Step Look-Ahead Exposure Bias Correction for Diffusion Sampling
34. NeurIPS 2026Personalized and Collaborative Online LQR via Thompson Sampling
35. NeurIPS 2026Power Distribution Bridges Sampling, Self-Reward RL, and Self-Distillation
36. NeurIPS 2026PRECISE: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
37. NeurIPS 2026Preconditioned Implicit Midpoint Langevin Sampling for Non-Smooth Bayesian Imaging
38. NeurIPS 2026Predict-Project-Renoise: Sampling Diffusion Models under Hard Constraints
39. NeurIPS 2026Provably Accurate Shapley Value Estimation in High Dimensions via Sparse Leverage Sampling
40. NeurIPS 2026Query Lower Bounds for Diffusion Sampling
41. NeurIPS 2026Recovery Guarantees for Posterior Sampling of One-Bit Compressed Sensing
42. NeurIPS 2026Robust Importance Sampling for Rare Events via Constrained Gaussian Mixtures
43. NeurIPS 2026Sampling-Based Safe Reinforcement Learning
44. NeurIPS 2026Sampling-Free Privacy Accounting for Matrix Mechanisms under Random Allocation
45. NeurIPS 2026Search at the Cost of Sampling: Nearly-Instant Latent Space Bayesian Optimization
46. NeurIPS 2026Show Me What You Don’t Know: Efficient Sampling from Invariant Sets for Model Validation
47. NeurIPS 2026Smoothed Score Queries and the Complexity of Sampling
48. NeurIPS 2026Spherical Flows for Sampling Categorical Data
49. NeurIPS 2026Stable Max Coverage Under a Cardinality Constraint
50. NeurIPS 2026Statistical Estimation of Adversarial Risk in Large Language Models under Best-of-N 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。