Research map / Probabilistic and scientific modeling / Variational and generative sampling
Matching Normalizing Flows and Probability Paths on Manifolds
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 |
|---|---|---|---|
| Train CNFs with probability path divergence instead of Moser Flow | CNFM versus Moser Flow · Earth and Climate: Earthquake | negative log likelihood: -0.09 -> -0.38 | Helped |
| Train CNFs with probability path divergence instead of Moser Flow | CNFM versus Moser Flow · Earth and Climate: Flood | negative log likelihood: 0.62 -> 0.25 | Helped |
| Train CNFs with probability path divergence instead of Moser Flow | CNFM versus Moser Flow · Earth and Climate: Fire | negative log likelihood: -1.03 -> -1.40 | Helped |
| Train CNFs with probability path divergence instead of Moser Flow | CNFM versus Moser Flow · Earth and Climate: Volcano | negative log likelihood: -2.02 -> -2.38 | Helped |
| Train a manifold CNF with probability path divergence instead of S-FFJORD | CNFM versus S-FFJORD · S^15: r_2 | negative log likelihood: 0.77 -> 0.73 | Helped |
| Train a manifold CNF with probability path divergence instead of S-FFJORD | CNFM versus S-FFJORD · S^15: r_3 | negative log likelihood: 0.97 -> 0.83 | Helped |
| Train a manifold CNF with probability path divergence instead of S-FFJORD | CNFM versus S-FFJORD · S^15: r_4 | negative log likelihood: 1.04 -> 0.95 | Helped |
Closest papers by meaning
- An Error Analysis of Flow Matching for Deep Generative Modeling (ICML 2025 · similarity 0.89)
- Categorical Flow Matching on Statistical Manifolds (NeurIPS 2024 · similarity 0.89)
- Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows (NeurIPS 2024 · similarity 0.88)
- Learning Distributions on Manifolds with Free-Form Flows (NeurIPS 2024 · similarity 0.88)
- Flow Matching on General Geometries (ICLR 2024 · similarity 0.87)
- Rectifying Categorical Flows on Statistical Manifolds for One-Step Generation (NeurIPS 2026 · similarity 0.87)
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.