Research map / Probabilistic and scientific modeling / Variational and generative sampling
Variational methods for sequence models
Applies variational inference to recurrent models, deep networks and GFlowNets.
40 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Variational and generative sampling, keyword cluster “variational inference · vi · lower”
State History Tried Preprints Export
Where it stands
Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.
5 papers in 2023–24 and 3 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 1.2% to 0.6%.
How this is decided
A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.
How it got here
Most cited paper of each year
- 2016 · Composing graphical models with neural networks for structured representations and fast inference (NeurIPS 2016 · 216 citations)
- 2017 · Discovering Discrete Latent Topics with Neural Variational Inference (ICML 2017 · 215 citations)
- 2018 · Latent Alignment and Variational Attention (NeurIPS 2018 · 79 citations)
- 2019 · Variational Smoothing in Recurrent Neural Network Language Models (ICLR 2019 · 3 citations)
- 2020 · Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posterior (AAAI 2020 · 107 citations)
- 2021 · not-MIWAE: Deep Generative Modelling with Missing not at Random Data (ICLR 2021 · 20 citations)
- 2022 · Variational Sparse Coding with Learned Thresholding (ICML 2022 · 3 citations)
- 2023 · GFlowNets and variational inference (ICLR 2023 · 0 citations)
- 2024 · Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming (NeurIPS 2024 · 1 citation)
- 2025 · Large Language Bayes (NeurIPS 2025 · 1 citation)
- 2026 · Pseudo-Mallows for Efficient Probabilistic Preference Learning (ICML 2026)
Earliest papers here
- Composing graphical models with neural networks for structured representations and fast inference (NeurIPS 2016 · 216 citations)
- Sequential Neural Models with Stochastic Layers (NeurIPS 2016 · 156 citations)
- Collapsed Variational Inference for Sum-Product Networks (ICML 2016 · 25 citations)
What has been tried
36 papers here report 337 measured changes (a component added, removed or swapped, compared with a baseline): helped 62%, no clear effect 13%, hurt 21%, mixed 5%. Papers mostly publish changes that helped, so "helped" is over-represented.
Ablations in recent papers
| What was changed | Measured on | Result | Effect | Paper |
|---|---|---|---|---|
| add deviation matrix Z to model weight correlations | CIFAR-10, VGG16, 1W32A · testing accuracy (%) | 92.85 ± 0.09 -> 93.25 ± 0.11 | Helped | Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming (NeurIPS 2024 · 1 citation) |
Recent preprints
Loading recent arXiv preprints…
Use it
Download BibTeX of 26 key papersOpen the topic in the interactive map
Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.
Related approaches
Same keyword cluster
- Variational inference theory and gradients (89 papers)
- Annealing and divergence-based variational objectives (79 papers)
- Amortized and online variational inference (59 papers)
Elsewhere in the topic
- Likelihood-free and graphical model estimation (161 papers)
- Flow matching and flow sampling (144 papers)
- Posterior sampling with diffusion guidance (137 papers)
- Score-based generative modeling analysis (128 papers)
- Structured latent VAEs (125 papers)
- Exact inference for probabilistic programs (103 papers)
- Disentangled and discrete latent models (92 papers)
- Latent variable marginalization and estimators (91 papers)
Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).