Research map / Probabilistic and scientific modeling / Variational and generative sampling
Residual Flows for Invertible Generative Modeling
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 biased log-det estimator with unbiased Russian roulette estimator (ablation) | invertible residual networks · CIFAR-10 | bits/dim | Helped |
| use LipSwish activation instead of softplus or ELU (ablation) | Residual Flow · CIFAR-10 | bits/dim | Helped |
| Residual Flow vs i-ResNet | flow models · CIFAR-10 | bits/dim: 3.45 -> 3.280 | Helped |
| Residual Flow vs Glow | flow models · CIFAR-10 | FID: 46.90 -> 46.37 | Helped |
| use residual blocks instead of coupling blocks (ablation) | hybrid generative-discriminative model · CIFAR-10 lambda=1 | accuracy: 67.62% -> 70.32% | Helped |
Closest papers by meaning
- Invertible Residual Networks (ICML 2019 · similarity 0.92)
- Invertible DenseNets with Concatenated LipSwish (NeurIPS 2021 · similarity 0.91)
- Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design (ICML 2019 · similarity 0.89)
- Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks (ICLR 2025 · similarity 0.87)
- Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity (ICLR 2024 · similarity 0.87)
- Inverse Flow and Consistency Models (ICML 2025 · 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.