Research map / Probabilistic and scientific modeling / Variational and generative sampling
Representing Closed Transformation Paths in Encoded Network Latent Space
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 |
|---|---|---|---|
| Fine-tune the autoencoder weights and transport operators together (ablation) | Manifold autoencoder · Rotated MNIST | rotation-path generation | Helped |
| Fine-tune the autoencoder weights and transport operators together (ablation) | Manifold offset distance · Rotated MNIST | nearest-neighbor classification accuracy | Helped |
| Use manifold offset distance instead of Euclidean distance | Manifold autoencoder · Concentric circles | same-circle classification AUC | Helped |
| Use manifold offset distance instead of Euclidean or hyperspherical geodesic distance | Rotated MNIST nearest-neighbor classifier · Rotated MNIST | nearest-neighbor classification accuracy at large rotation angles | Helped |
| Use a learned transport-operator path instead of a linear latent path | Manifold autoencoder · CMU gait sequences, test sequences 30–34 | ground-truth gait-sequence estimation error | Helped |
| Use a learned transport-operator path instead of a linear latent path | Manifold autoencoder · Rotated MNIST | identity-preserving rotation-path generation | Helped |
| Use a learned transport-operator path instead of a hyperspherical VAE geodesic path | Manifold autoencoder · Rotated MNIST | identity-preserving rotation-path generation | Helped |
| Add a learned manifold model to the autoencoder latent space | Manifold autoencoder · Concentric circles | preservation of individual circular manifolds in the latent embedding | Helped |
Closest papers by meaning
- What Matters for Diffusion-Friendly Latent Manifold? Prior-Aligned Autoencoders for Latent Diffusion (NeurIPS 2026 · similarity 0.87)
- Connecting Neural Models Latent Geometries with Relative Geodesic Representations (NeurIPS 2025 · similarity 0.87)
- Isometric Representation Learning for Disentangled Latent Space of Diffusion Models (ICML 2024 · similarity 0.86)
- What Secrets Do Your Manifolds Hold? Understanding the Local Geometry of Generative Models (ICLR 2025 · similarity 0.86)
- Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation (ICML 2025 · similarity 0.86)
- Graph Geometry-Preserving Autoencoders (ICML 2024 · similarity 0.86)
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.