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 640 篇，第 1 / 13 页

1. CVPR 2026Active Inference for Micro-Gesture Recognition EFE-Guided Temporal Sampling and Adaptive
2. CVPR 2026Adaptive 3D Perception for Small Aerial Targets Under Sparse Sampling
3. CVPR 2026Ani3DHuman Photorealistic 3D Human Animation with Self-guided Stochastic Sampling
4. CVPR 2026Conditional Factuality Controlled LLMs with Generalization Certificates via Conformal Sampling
5. CVPR 2026Designing Instance-Level Sampling Schedules via REINFORCE with James-Stein Shrinkage
6. CVPR 2026Diffusion Sampling Path Tells More An Efficient Plug-and-Play Strategy for
7. CVPR 2026Efficient All-Pairs Correlation Volume Sampling for Optical Flow Estimation
8. CVPR 2026Few-Step Diffusion Sampling Through Instance-Aware Discretizations
9. CVPR 2026FG-Portrait 3D Flow Guided Editable Portrait Animation
10. CVPR 2026Guiding Diffusion Models with Fine-Grained Conditions and Semantics-Preserving Sampling for
11. CVPR 2026Region-Adaptive Sampling for Diffusion Transformers
12. CVPR 2026Revisiting F-measure Optimization in Multi-Label Classification A Sampling-based Approach
13. CVPR 2026Sampling-Aware Quantization for Diffusion Models
14. CVPR 2026Taming Sampling Perturbations with Variance Expansion Loss for Latent Diffusion
15. ICLR 2026$p\textrm{-less}$ Sampling: A Robust Hyperparameter-Free Approach for LLM Decoding
16. ICLR 2026A Statistical Benchmark for Diffusion Posterior Sampling Algorithms
17. ICLR 2026AC-Sampler: Accelerate and Correct Diffusion Sampling with Metropolis-Hastings Algorithm
18. ICLR 2026Accelerating Diffusion Large Language Models with SlowFast Sampling: The Three Golden Principles
19. ICLR 2026Alternating Diffusion for Proximal Sampling with Zeroth Order Queries
20. ICLR 2026Asynchronous Matching with Dynamic Sampling for Multimodal Dataset Distillation
21. ICLR 2026Beyond Speedup - Utilizing KV Cache for Sampling and Reasoning
22. ICLR 2026Break the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models
23. ICLR 2026Bringing Stability to Diffusion: Decomposing and Reducing Variance of Training Masked Diffusion Models
24. ICLR 2026Cactus: Accelerating Auto-Regressive Decoding with Constrained Acceptance Speculative Sampling
25. ICLR 2026Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond
26. ICLR 2026Contractive Diffusion Policies: Robust Action Diffusion via Contractive Score-Based Sampling with Differential Equations
27. ICLR 2026Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling
28. ICLR 2026Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching
29. ICLR 2026Efficient Approximate Posterior Sampling with Annealed Langevin Monte Carlo
30. ICLR 2026Error as Signal: Stiffness-Aware Diffusion Sampling via Embedded Runge-Kutta Guidance
31. ICLR 2026Flow Map Learning via Games
32. ICLR 2026Foresight Diffusion: Improving Sampling Consistency in Predictive Diffusion Models
33. ICLR 2026From Predictors to Samplers via the Training Trajectory
34. ICLR 2026Global Resolution: Optimal Multi-Draft Speculative Sampling via Convex Optimization
35. ICLR 2026Hallucination Begins Where Saliency Drops
36. ICLR 2026HiGS: History-Guided Sampling for Plug-and-Play Enhancement of Diffusion Models
37. ICLR 2026How to train data-efficient LLMs
38. ICLR 2026Learn to Guide Your Diffusion Model
39. ICLR 2026Learning Boltzmann Generators via Constrained Mass Transport
40. ICLR 2026Learning Survival Distributions with Individually Calibrated Asymmetric Laplace Distribution
41. ICLR 2026Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall
42. ICLR 2026NI Sampling: Accelerating Discrete Diffusion Sampling by Token Order Optimization
43. ICLR 2026Noise-Adaptive Diffusion Sampling for Inverse Problems Without Task-Specific Tuning
44. ICLR 2026On Coreset for LASSO Regression Problem with Sensitivity Sampling
45. ICLR 2026Parallel Sampling from Masked Diffusion Models via Conditional Independence Testing
46. ICLR 2026Poisson Midpoint Method for Log Concave Sampling: Beyond the Strong Error Lower Bounds
47. ICLR 2026Policy Likelihood-based Query Sampling and Critic-Exploited Reset for Efficient Preference-based Reinforcement Learning
48. ICLR 2026Q-learning with Posterior Sampling
49. ICLR 2026Random-projection ensemble dimension reduction
50. ICLR 2026Reasoning with Sampling: Your Base Model is Smarter Than You Think

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。