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 167 篇，第 1 / 4 页

1. CVPR 2025Adaptive Non-Uniform Timestep Sampling for Accelerating Diffusion Model Training
2. CVPR 2025AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning
3. CVPR 2025Boltzmann Attention Sampling for Image Analysis with Small Objects
4. CVPR 2025Consistency Posterior Sampling for Diverse Image Synthesis
5. CVPR 2025Depth-Guided Bundle Sampling for Efficient Generalizable Neural Radiance Field Reconstruction
6. CVPR 2025Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders
7. CVPR 2025HeMoRa: Unsupervised Heuristic Consensus Sampling for Robust Point Cloud Registration
8. CVPR 2025Identity-preserving Distillation Sampling by Fixed-Point Iterator
9. CVPR 2025Improving the Training of Data-Efficient GANs via Quality Aware Dynamic Discriminator Rejection Sampling
10. CVPR 2025Multi-modal Contrastive Learning with Negative Sampling Calibration for Phenotypic Drug Discovery
11. CVPR 2025PCM : Picard Consistency Model for Fast Parallel Sampling of Diffusion Models
12. CVPR 2025SAMBLE: Shape-Specific Point Cloud Sampling for an Optimal Trade-Off Between Local Detail and Global Uniformity
13. CVPR 2025Sampling Innovation-Based Adaptive Compressive Sensing
14. CVPR 2025Spatiotemporal Skip Guidance for Enhanced Video Diffusion Sampling
15. CVPR 2025StyleSSP: Sampling StartPoint Enhancement for Training-free Diffusion-based Method for Style Transfer
16. CVPR 2025Zero-Shot Blind-spot Image Denoising via Implicit Neural Sampling
17. ICLR 2025Action abstractions for amortized sampling
18. ICLR 2025Ambient Diffusion Posterior Sampling: Solving Inverse Problems with Diffusion Models Trained on Corrupted Data
19. ICLR 2025Anti-Exposure Bias in Diffusion Models
20. ICLR 2025Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space
21. ICLR 2025Budgeted Online Continual Learning by Adaptive Layer Freezing and Frequency-based Sampling
22. ICLR 2025CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion
23. ICLR 2025Distilled Decoding 1: One-step Sampling of Image Auto-regressive Models with Flow Matching
24. ICLR 2025Efficient Model-Based Reinforcement Learning Through Optimistic Thompson Sampling
25. ICLR 2025Enhanced Diffusion Sampling via Extrapolation with Multiple ODE Solutions
26. ICLR 2025Estimating the Probabilities of Rare Outputs in Language Models
27. ICLR 2025Exact Byte-Level Probabilities from Tokenized Language Models for FIM-Tasks and Model Ensembles
28. ICLR 2025Fast training and sampling of Restricted Boltzmann Machines
29. ICLR 2025Faster Diffusion Sampling with Randomized Midpoints: Sequential and Parallel
30. ICLR 2025FLOPS: Forward Learning with OPtimal Sampling
31. ICLR 2025From Search to Sampling: Generative Models for Robust Algorithmic Recourse
32. ICLR 2025Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits
33. ICLR 2025Improved Sampling Algorithms for Lévy-Itô Diffusion Models
34. ICLR 2025Judge Decoding: Faster Speculative Sampling Requires Going Beyond Model Alignment
35. ICLR 2025Jump Your Steps: Optimizing Sampling Schedule of Discrete Diffusion Models
36. ICLR 2025Learning Harmonized Representations for Speculative Sampling
37. ICLR 2025Learning to Discretize Denoising Diffusion ODEs
38. ICLR 2025Linear Multistep Solver Distillation for Fast Sampling of Diffusion Models
39. ICLR 2025Manifold Constraint Reduces Exposure Bias in Accelerated Diffusion Sampling
40. ICLR 2025Matrix Product Sketching via Coordinated Sampling
41. ICLR 2025Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks
42. ICLR 2025Multi-Draft Speculative Sampling: Canonical Decomposition and Theoretical Limits
43. ICLR 2025Multilevel Generative Samplers for Investigating Critical Phenomena
44. ICLR 2025MuseGNN: Forming Scalable, Convergent GNN Layers that Minimize a Sampling-Based Energy
45. ICLR 2025Neural Sampling from Boltzmann Densities: Fisher-Rao Curves in the Wasserstein Geometry
46. ICLR 2025Non-Equilibrium Dynamics of Hybrid Continuous-Discrete Ground-State Sampling
47. ICLR 2025Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization
48. ICLR 2025Provable Benefit of Annealed Langevin Monte Carlo for Non-log-concave Sampling
49. ICLR 2025Provable Convergence and Limitations of Geometric Tempering for Langevin Dynamics
50. ICLR 2025Provable Convergence Bounds for Hybrid Dynamical Sampling and Optimization

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。