Variational Inference papers, 2023–2026

Key findings

• Variational Inference fell from 106 papers in 2023 to 91 in 2026, so interest is cooling.
• NeurIPS publishes the most Variational Inference work: 124 papers from 2023 to 2026, 35% of the four-venue total.
• The fastest-growing overlap is with Sampling Methods: papers tagged with both rose from 1 in 2023 to 6 in 2026.
• Among the 5 topics under Probabilistic and Bayesian, it ranks #5 by 2026 paper count; the fastest grower in the group, Gaussian Processes, is up 2.2x versus 0.9x here.

Representative papers

Spread across years and venues so every edition shows up

• 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

All Variational Inference papers

28 papers, page 1 of 1

1. ICLR 2025Accelerating Neural ODEs: A Variational Formulation-based Approach
2. ICLR 2025Bridging the Gap between Variational Inference and Stochastic Gradient MCMC in Function Space
3. ICLR 2025Connecting Federated ADMM to Bayes
4. ICLR 2025Efficient Interpolation between Extragradient and Proximal Methods for Weak MVIs
5. ICLR 2025ELBOing Stein: Variational Bayes with Stein Mixture Inference
6. ICLR 2025Flow-based Variational Mutual Information: Fast and Flexible Approximations
7. ICLR 2025Improved Finite-Particle Convergence Rates for Stein Variational Gradient Descent
8. ICLR 2025Injective flows for star-like manifolds
9. ICLR 2025Microcanonical Langevin Ensembles: Advancing the Sampling of Bayesian Neural Networks
10. ICLR 2025Nonlinear multiregion neural dynamics with parametric impulse response communication channels
11. ICLR 2025Nonlinear Sequence Embedding by Monotone Variational Inequality
12. ICLR 2025On the Relation between Trainability and Dequantization of Variational Quantum Learning Models
13. ICLR 2025Random-Set Neural Networks
14. ICLR 2025Repulsive Latent Score Distillation for Solving Inverse Problems
15. ICLR 2025Residual Deep Gaussian Processes on Manifolds
16. ICLR 2025Risk-Sensitive Variational Actor-Critic: A Model-Based Approach
17. ICLR 2025Scalable Bayesian Learning with posteriors
18. ICLR 2025SoftCVI: Contrastive variational inference with self-generated soft labels
19. ICLR 2025Solving hidden monotone variational inequalities with surrogate losses
20. ICLR 2025Stochastic variance-reduced Gaussian variational inference on the Bures-Wasserstein manifold
21. ICLR 2025Support is All You Need for Certified VAE Training
22. ICLR 2025Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
23. ICLR 2025VAE-Var: Variational Autoencoder-Enhanced Variational Methods for Data Assimilation in Meteorology
24. ICLR 2025Variational Bayesian Pseudo-Coreset
25. ICLR 2025Variational Best-of-N Alignment
26. ICLR 2025Variational Diffusion Posterior Sampling with Midpoint Guidance
27. ICLR 2025Variational Search Distributions
28. ICLR 2025When do GFlowNets learn the right distribution?

FAQ

How many Variational Inference papers were published at NeurIPS, ICLR, ICML and CVPR from 2023 to 2026?

359 in total: 106 in 2023, 76 in 2024, 86 in 2025, 91 in 2026.

How many Variational Inference papers are at NeurIPS 2026?

NeurIPS 2026 has 30 Variational Inference papers, versus 28 the year before.

How many Variational Inference papers are at ICLR 2026?

ICLR 2026 has 23 Variational Inference papers, versus 28 the year before.

How many Variational Inference papers are at ICML 2026?

ICML 2026 has 35 Variational Inference papers, versus 28 the year before.

How many Variational Inference papers are at CVPR 2026?

CVPR 2026 has 3 Variational Inference papers, versus 2 the year before.

Which conference publishes the most Variational Inference papers?

NeurIPS, with 124 papers from 2023 to 2026.