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 56 篇，第 1 / 2 页

1. ICML 2024$\mathtt{VITS}$ : Variational Inference Thompson Sampling for contextual bandits
2. ICML 2024A sampling theory perspective on activations for implicit neural representations
3. ICML 2024A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models
4. ICML 2024Accelerated Speculative Sampling Based on Tree Monte Carlo
5. ICML 2024Accelerating Parallel Sampling of Diffusion Models
6. ICML 2024Adaptive Sampling of k-Space in Magnetic Resonance for Rapid Pathology Prediction
7. ICML 2024Ai-sampler: Adversarial Learning of Markov kernels with involutive maps
8. ICML 2024Align Your Steps: Optimizing Sampling Schedules in Diffusion Models
9. ICML 2024Bespoke Non-Stationary Solvers for Fast Sampling of Diffusion and Flow Models
10. ICML 2024Beyond ELBOs: A Large-Scale Evaluation of Variational Methods for Sampling
11. ICML 2024Bifurcated Attention for Single-Context Large-Batch Sampling
12. ICML 2024Closing the Gap: Achieving Global Convergence (Last Iterate) of Actor-Critic under Markovian Sampling with Neural Network Parametrization
13. ICML 2024Connecting the Dots: Is Mode-Connectedness the Key to Feasible Sample-Based Inference in Bayesian Neural Networks?
14. ICML 2024Constrained Exploration via Reflected Replica Exchange Stochastic Gradient Langevin Dynamics
15. ICML 2024Data-Efficient Learning via Clustering-Based Sensitivity Sampling: Foundation Models and Beyond
16. ICML 2024Differentiable Annealed Importance Sampling Minimizes The Jensen-Shannon Divergence Between Initial and Target Distribution
17. ICML 2024Diffusion Posterior Sampling is Computationally Intractable
18. ICML 2024Diffusion Rejection Sampling
19. ICML 2024Diffusive Gibbs Sampling
20. ICML 2024EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
21. ICML 2024Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing
22. ICML 2024Efficient Exploration in Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal Regret With Posterior Sampling
23. ICML 2024Embarrassingly Parallel GFlowNets
24. ICML 2024EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence
25. ICML 2024Energy-Guided Diffusion Sampling for Offline-to-Online Reinforcement Learning
26. ICML 2024Estimating the Permanent by Nesting Importance Sampling
27. ICML 2024Fast Sampling-Based Sketches for Tensors
28. ICML 2024Faster Sampling via Stochastic Gradient Proximal Sampler
29. ICML 2024Feel-Good Thompson Sampling for Contextual Dueling Bandits
30. ICML 2024Generalization Analysis of Stochastic Weight Averaging with General Sampling
31. ICML 2024Gibbs Sampling of Continuous Potentials on a Quantum Computer
32. ICML 2024How Private are DP-SGD Implementations?
33. ICML 2024Improving Gradient-Guided Nested Sampling for Posterior Inference
34. ICML 2024Iterated Denoising Energy Matching for Sampling from Boltzmann Densities
35. ICML 2024Learning to Explore for Stochastic Gradient MCMC
36. ICML 2024Minimax Optimality of Score-based Diffusion Models: Beyond the Density Lower Bound Assumptions
37. ICML 2024No Dimensional Sampling Coresets for Classification
38. ICML 2024On the Trajectory Regularity of ODE-based Diffusion Sampling
39. ICML 2024Optimal bounds for $\ell_p$ sensitivity sampling via $\ell_2$ augmentation
40. ICML 2024Path-Guided Particle-based Sampling
41. ICML 2024Posterior Sampling-Based Bayesian Optimization with Tighter Bayesian Regret Bounds
42. ICML 2024Principled Gradient-Based MCMC for Conditional Sampling of Text
43. ICML 2024Q-Star Meets Scalable Posterior Sampling: Bridging Theory and Practice via HyperAgent
44. ICML 2024Reparameterized Importance Sampling for Robust Variational Bayesian Neural Networks
45. ICML 2024Reprompting: Automated Chain-of-Thought Prompt Inference Through Gibbs Sampling
46. ICML 2024Sample as you Infer: Predictive Coding with Langevin Dynamics
47. ICML 2024Sampling in Unit Time with Kernel Fisher-Rao Flow
48. ICML 2024Sampling is as easy as keeping the consistency: convergence guarantee for Consistency Models
49. ICML 2024Sampling-based Multi-dimensional Recalibration
50. ICML 2024Stochastic Localization via Iterative Posterior 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。