Research map / Probabilistic and scientific modeling / Variational and generative sampling
Manifold Interpolating Optimal-Transport Flows for Trajectory Inference
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 |
|---|---|---|---|
| replace TrajectoryNet/DSB with MIOFlow | trajectory inference · Petal held-out t=2 | W1: 0.181 -> 0.090 (vs TrajectoryNet) | Helped |
| replace TrajectoryNet with MIOFlow | trajectory inference · Dyngen held-out t=2 | W1: 1.499 -> 0.783 | Helped |
| replace TrajectoryNet with MIOFlow | trajectory inference · Petal | runtime: 64 (m) -> 284.60 (s) | Helped |
| add geodesic autoencoder embedding (ablation) | MIOFlow · EB held-out t=2 | W1: 29.243 -> 25.744 | Helped |
| add geodesic autoencoder embedding (ablation) | MIOFlow · EB held-out t=3 | MMD(G): 0.119 -> 0.138 | Hurt |
| add geodesic autoencoder embedding (ablation) | MIOFlow · Dyngen | 10-NN distance: 21.589 -> 15.427 | Helped |
| add density loss (ablation) | MIOFlow · Petal/Dyngen | qualitative | Helped |
| choice of alpha-decay vs Gaussian GAE kernel (ablation) | MIOFlow · EB | W1: 25.744 vs 26.318 | No clear effect |
Closest papers by meaning
- Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation (NeurIPS 2026 · similarity 0.87)
- Metric Flow Matching for Smooth Interpolations on the Data Manifold (NeurIPS 2024 · similarity 0.87)
- Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport (ICLR 2025 · similarity 0.87)
- GeoSPRINT: Geometric Redundancy-Aware Step Pruning for Inference in Diffusion Trajectories (NeurIPS 2026 · similarity 0.86)
- Enforcing Latent Euclidean Geometry in Single-Cell VAEs for Manifold Interpolation (ICML 2025 · similarity 0.86)
- TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics (NeurIPS 2026 · 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.