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 106 篇，第 2 / 3 页

51. ICML 2023MixFlows: principled variational inference via mixed flows
52. ICML 2023Modality-Agnostic Variational Compression of Implicit Neural Representations
53. ICML 2023Neural Network Approximations of PDEs Beyond Linearity: A Representational Perspective
54. ICML 2023Practical and Matching Gradient Variance Bounds for Black-Box Variational Bayesian Inference
55. ICML 2023QuantumDARTS: Differentiable Quantum Architecture Search for Variational Quantum Algorithms
56. ICML 2023Revisiting Structured Variational Autoencoders
57. ICML 2023Robust Weak Supervision with Variational Auto-Encoders
58. ICML 2023Sample Complexity of Probability Divergences under Group Symmetry
59. ICML 2023Variational Autoencoding Neural Operators
60. ICML 2023Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills
61. ICML 2023Variational Open-Domain Question Answering
62. ICML 2023Variational Sparse Inverse Cholesky Approximation for Latent Gaussian Processes via Double Kullback-Leibler Minimization
63. NeurIPS 2023[Re] Variational Neural Cellular Automata
64. NeurIPS 2023A Finite-Particle Convergence Rate for Stein Variational Gradient Descent
65. NeurIPS 2023A Heavy-Tailed Algebra for Probabilistic Programming
66. NeurIPS 2023A Variational Perspective on High-Resolution ODEs
67. NeurIPS 2023AdaVAE: Bayesian Structural Adaptation for Variational Autoencoders
68. NeurIPS 2023Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics
69. NeurIPS 2023Amortized Reparametrization: Efficient and Scalable Variational Inference for Latent SDEs
70. NeurIPS 2023Approximate inference of marginals using the IBIA framework
71. NeurIPS 2023ARTree: A Deep Autoregressive Model for Phylogenetic Inference
72. NeurIPS 2023Attention as Implicit Structural Inference
73. NeurIPS 2023Conditional Matrix Flows for Gaussian Graphical Models
74. NeurIPS 2023Conformalized matrix completion
75. NeurIPS 2023Discriminative Calibration: Check Bayesian Computation from Simulations and Flexible Classifier
76. NeurIPS 2023Embracing the chaos: analysis and diagnosis of numerical instability in variational flows
77. NeurIPS 2023End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics
78. NeurIPS 2023Estimating Noise Correlations Across Continuous Conditions With Wishart Processes
79. NeurIPS 2023Function Space Bayesian Pseudocoreset for Bayesian Neural Networks
80. NeurIPS 2023Gacs-Korner Common Information Variational Autoencoder
81. NeurIPS 2023GeoPhy: Differentiable Phylogenetic Inference via Geometric Gradients of Tree Topologies
82. NeurIPS 2023Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration
83. NeurIPS 2023Joint Prompt Optimization of Stacked LLMs using Variational Inference
84. NeurIPS 2023Latent SDEs on Homogeneous Spaces
85. NeurIPS 2023On permutation symmetries in Bayesian neural network posteriors: a variational perspective
86. NeurIPS 2023On the Convergence of Black-Box Variational Inference
87. NeurIPS 2023On the Statistical Consistency of Risk-Sensitive Bayesian Decision-Making
88. NeurIPS 2023Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure
89. NeurIPS 2023Particle-based Variational Inference with Generalized Wasserstein Gradient Flow
90. NeurIPS 2023Penguin: Parallel-Packed Homomorphic Encryption for Fast Graph Convolutional Network Inference
91. NeurIPS 2023Pointwise uncertainty quantification for sparse variational Gaussian process regression with a Brownian motion prior
92. NeurIPS 2023Provable convergence guarantees for black-box variational inference
93. NeurIPS 2023Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation
94. NeurIPS 2023Pseudo-Likelihood Inference
95. NeurIPS 2023Score-based Data Assimilation
96. NeurIPS 2023Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions
97. NeurIPS 2023Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory
98. NeurIPS 2023Sub-optimality of the Naive Mean Field approximation for proportional high-dimensional Linear Regression
99. NeurIPS 2023Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent
100. NeurIPS 2023Variational Gaussian processes for linear inverse problems

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。