Research map / Probabilistic and scientific modeling / Variational and generative sampling
Flexible and accurate inference and learning for deep generative models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use DDC-HM instead of IWAE k=50 | Hierarchical generative models of natural image patches · Natural image patches, all five tested latent-dimension settings | MMD: 0.126 -> 0.0388; 0.0754 -> 0.0269; 0.247 -> 0.00313; 0.076 -> 0.0211; 0.171 -> 0.00355 | Helped |
| Use DDC-HM instead of VIMCO | Three-layer sigmoid belief network · Binarised MNIST test set | MMD: 2e-3 -> 6e-4 | Helped |
| Use DDC-HM instead of VAE or IWAE | Two-layer continuous latent-variable model · Synthetic data | MMD | Helped |
| Use DDC-HM instead of VAE or IWAE | Two-layer continuous latent-variable model · Synthetic data | recovery of latent posterior structure | Helped |
Closest papers by meaning
- Bidirectional Helmholtz Machines (ICML 2016 · similarity 0.93)
- An Architecture for Deep, Hierarchical Generative Models (NeurIPS 2016 · similarity 0.89)
- A Likelihood Based Approach to Distribution Regression Using Conditional Deep Generative Models (ICML 2025 · similarity 0.86)
- DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents (ICML 2024 · similarity 0.85)
- Boosting Generative Image Modeling via Joint Image-Feature Synthesis (NeurIPS 2025 · similarity 0.85)
- A solvable model of learning generative diffusion: theory and insights (NeurIPS 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.