Research map / Probabilistic and scientific modeling / Variational and generative sampling
McFlow: Monte Carlo Flow Models for Data Imputation
Check 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 MCFlow instead of the strongest reported baseline | Imputation on UCI datasets with 20% missing data · Default Credit Card Clients, Online News Popularity, and Letter Recognition | RMSE: Default Credit Card Clients: .1441 ± .0007 -> .1233±.0012; Online News Popularity: .1858 ± .0010 -> .1760±.0032; Letter | Helped |
| Use MCFlow instead of the strongest reported baseline | Image imputation · MNIST, CIFAR-10, and CelebA at 10%, 50%, and 90% missing rates | RMSE: MNIST: .07464 vs .11508, .10045 vs .12174, .20801 vs .27806; CIFAR-10: .06012 vs .10053, .08311 vs .12451, .16939 vs .31 | Helped |
| Use MCFlow instead of the strongest reported baseline | Imputed MNIST image quality · MNIST, 10% missing | FID: .0529 -> .0521 | Helped |
| Use MCFlow instead of MisGAN | Imputed MNIST image quality · MNIST, 90% missing | FID: 6.325 -> 15.11 | Hurt |
| Use MCFlow instead of the strongest reported baseline | Semantic preservation after imputation · MNIST classification, 10% to 90% missing | classification accuracy: 10%: .989 -> .991; 90%: .334 -> .705 | Helped |
Closest papers by meaning
- Rethinking the Diffusion Models for Missing Data Imputation: A Gradient Flow Perspective (NeurIPS 2024 · similarity 0.90)
- Missing Data Imputation by Reducing Mutual Information with Rectified Flows (NeurIPS 2025 · similarity 0.89)
- Distribution Shift in Missing Data Imputation: A Risk-Based Perspective and Importance-Weighted Correction under MAR (NeurIPS 2026 · similarity 0.89)
- DiffPuter: Empowering Diffusion Models for Missing Data Imputation (ICLR 2025 · similarity 0.88)
- Learning What Not to Impute: An Uncertainty-Aware Diffusion Framework for Meaningful Missingness (NeurIPS 2026 · similarity 0.88)
- Generative Modeling under Non-Monotone MAR Missingness via Approximate Wasserstein Gradient Flows (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.