Research map / Probabilistic and scientific modeling / Variational and generative sampling
Building Normalizing Flows with Stochastic Interpolants
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 |
|---|---|---|---|
| Interpolant-based simulation-free velocity regression (quadratic loss) instead of maximum likelihood through ODE solver | continuous flow (InterFlow) · UCI tabular density estimation (POWER, GAS, HEPMASS, MINIBOONE, BSDS300) | test NLL | Mixed |
| Interpolant flow trained on CIFAR-10 without data augmentation with beta time reweighting | InterFlow · CIFAR-10 | NLL (bits/dim) and FID | Mixed |
| Interpolant flow trained on ImageNet-32x32 | InterFlow · ImageNet-32x32 | NLL (bits/dim) | Helped |
Closest papers by meaning
- Normalizing Flows are Capable Generative Models (ICML 2025 · similarity 0.89)
- Stochastic Interpolants via Conditional Dependent Coupling (NeurIPS 2026 · similarity 0.89)
- Fast and unified path gradient estimators for normalizing flows (ICLR 2024 · similarity 0.88)
- Stochastic Interpolants with Data-Dependent Couplings (ICML 2024 · similarity 0.88)
- Normalizing Trajectory Models (NeurIPS 2026 · similarity 0.88)
- Beckmann Transport Models: From Autonomous Flows to One-Step Maps (NeurIPS 2026 · similarity 0.88)
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.