变分推断论文趋势 2023–2026

主要结论

• 变分推断论文从 2023 年的 106 篇降到 2026 年的 91 篇，热度在回落。
• NeurIPS 是发变分推断论文最多的会议，2023–2026 年共 124 篇，占四个会议总量的 35%。
• 交叉方向里涨得最快的是采样方法：同时属于两个主题的论文从 2023 年的 1 篇增至 2026 年的 6 篇。
• 在「概率与贝叶斯」的 5 个主题里，它的 2026 年论文数排第 5；同组增长最快的高斯过程是 2.2 倍，变分推断是 0.9 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 Reproducible Evaluation Protocol for Quantum Non-Linearity in Variational Quantum Models
• ICML 2026Beyond Independence: Learning Correlated Views for Variational Incomplete Multi-View Clustering
• ICLR 2026Optimizing Data Augmentation through Bayesian Model Selection
• CVPR 2026BrepVGAE Variational Graph Autoencoder with Unified Latent Representation for B-rep
• NeurIPS 2025Covariate-moderated Empirical Bayes Matrix Factorization
• ICML 2025A Variational Information Theoretic Approach to Out-of-Distribution Detection
• ICLR 2025Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space
• CVPR 2025Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders
• NeurIPS 2024Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming
• ICML 2024Amortized Variational Deep Kernel Learning
• ICLR 2024Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder
• CVPR 2024WorDepth: Variational Language Prior for Monocular Depth Estimation
• NeurIPS 2023[Re] Variational Neural Cellular Automata
• ICML 2023Coupled Variational Autoencoder
• ICLR 2023A VAE for Transformers with Nonparametric Variational Information Bottleneck
• CVPR 2023Confidence-Aware Personalized Federated Learning via Variational Expectation Maximization
• NeurIPS 2026Adaptive Delayed-Update Cyclic Algorithm for Variational Inequalities
• ICML 2026Dual-stage Contrastive Learning-enhanced Multi-view Variational Clustering
• ICLR 2026Pareto Variational Autoencoder
• CVPR 2026Variational Graph-based Normal Integration

全部变分推断论文

共 110 篇，第 1 / 3 页

1. ICLR 2026Amortising Inference and Meta-Learning Priors in Neural Networks
2. ICLR 2026Bayesian Parameter Shift Rules in Variational Quantum Eigensolvers
3. ICLR 2026Bridging Kolmogorov Complexity and Deep Learning: Asymptotically Optimal Description Length Objectives for Transformers
4. ICLR 2026Decision Aggregation under Quantal Response
5. ICLR 2026Diffusion Bridge Variational Inference for Deep Gaussian Processes
6. ICLR 2026Discrete Variational Autoencoding via Policy Search
7. ICLR 2026Flow Map Learning via Games
8. ICLR 2026Forward-Learned Discrete Diffusion: Learning how to noise to denoise faster
9. ICLR 2026Learning Boltzmann Generators via Constrained Mass Transport
10. ICLR 2026Learning Survival Distributions with Individually Calibrated Asymmetric Laplace Distribution
11. ICLR 2026Multilevel Control Functional
12. ICLR 2026Neural Posterior Estimation with Latent Basis Expansions
13. ICLR 2026On the Mechanisms of Collaborative Learning in VAE Recommenders
14. ICLR 2026Optimizing Data Augmentation through Bayesian Model Selection
15. ICLR 2026Pareto Variational Autoencoder
16. ICLR 2026Permutation-Consistent Variational Encoding for Incomplete Multi-View Multi-Label Classification
17. ICLR 2026Proximal Diffusion Neural Sampler
18. ICLR 2026Random-projection ensemble dimension reduction
19. ICLR 2026Robust Generalized Schr\"{o}dinger Bridge via Sparse Variational Gaussian Processes
20. ICLR 2026Score-Based Density Estimation from Pairwise Comparisons
21. ICLR 2026Synthesising Counterfactual Explanations via Label-Conditional Gaussian Mixture Variational Autoencoders
22. ICLR 2026Variational Deep Learning via Implicit Regularization
23. ICLR 2026Variational Inference for Cyclic Learning
24. ICLR 2025Accelerating Neural ODEs: A Variational Formulation-based Approach
25. ICLR 2025Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space
26. ICLR 2025Connecting Federated ADMM to Bayes
27. ICLR 2025Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIs
28. ICLR 2025ELBOing Stein: Variational Bayes with Stein Mixture Inference
29. ICLR 2025Flow-based Variational Mutual Information: Fast and Flexible Approximations
30. ICLR 2025Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent
31. ICLR 2025Injective flows for star-like manifolds
32. ICLR 2025Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks
33. ICLR 2025Nonlinear multiregion neural dynamics with parametric impulse response communication channels
34. ICLR 2025Nonlinear Sequence Embedding by Monotone Variational Inequality
35. ICLR 2025On the Relation between Trainability and Dequantization of Variational Quantum Learning Models
36. ICLR 2025Random-Set Neural Networks
37. ICLR 2025Repulsive Latent Score Distillation for Solving Inverse Problems
38. ICLR 2025Residual Deep Gaussian Processes on Manifolds
39. ICLR 2025Risk-Sensitive Variational Actor-Critic: A Model-Based Approach
40. ICLR 2025Scalable Bayesian Learning with posteriors
41. ICLR 2025SoftCVI: Contrastive variational inference with self-generated soft labels
42. ICLR 2025Solving hidden monotone variational inequalities with surrogate losses
43. ICLR 2025Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold
44. ICLR 2025Support is All You Need for Certified VAE Training
45. ICLR 2025Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
46. ICLR 2025VAE-Var: Variational Autoencoder-Enhanced Variational Methods for Data Assimilation in Meteorology
47. ICLR 2025Variational Bayesian Pseudo-Coreset
48. ICLR 2025Variational Best-of-N Alignment
49. ICLR 2025Variational Diffusion Posterior Sampling with Midpoint Guidance
50. ICLR 2025Variational Search Distributions

常见问题

2023–2026 年四大会议一共有多少篇变分推断论文？

共 359 篇，按年份分别是 2023 年 106 篇、2024 年 76 篇、2025 年 86 篇、2026 年 91 篇。

NeurIPS 2026 有多少篇变分推断论文？

NeurIPS 2026 有 30 篇变分推断论文，上一届是 28 篇。

ICLR 2026 有多少篇变分推断论文？

ICLR 2026 有 23 篇变分推断论文，上一届是 28 篇。

ICML 2026 有多少篇变分推断论文？

ICML 2026 有 35 篇变分推断论文，上一届是 28 篇。

CVPR 2026 有多少篇变分推断论文？

CVPR 2026 有 3 篇变分推断论文，上一届是 2 篇。

哪个会议的变分推断论文最多？

NeurIPS，2023–2026 年共 124 篇。