Research map / Probabilistic and scientific modeling / Differential equations and PDEs
TO-FLOW: Efficient Continuous Normalizing Flows With Temporal Optimization Adjoint With Moving Speed
Shian Du, Yihong Luo, Wei Chen, Jian Xu, Delu Zeng
Check your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Optimize stopping time alongside network weights | FFJORD · MNIST | Time(h): 79.641 -> 46.363 | Improved |
| Optimize stopping time alongside network weights | FFJORD · Fashion-MNIST | Time(h): 87.845 -> 63.482 | Improved |
| Optimize stopping time alongside network weights | FFJORD · CIFAR-10 | Time(h): 108.314 -> 82.607 | Improved |
| Optimize stopping time alongside network weights | FFJORD · MNIST | Bits/dim: 1.017 -> 1.026 | Hurt |
| Optimize stopping time alongside network weights | FFJORD · Fashion-MNIST | Bits/dim: 2.806 -> 2.807 | Hurt |
| Optimize stopping time alongside network weights | FFJORD · CIFAR-10 | Bits/dim: 3.414 -> 3.429 | Hurt |
| Add temporal regularization to stopping time (ablation) | TO-FLOW · MNIST and Fashion-MNIST | training stability | Improved |
| Vary temporal regularization coefficient (ablation) | TO-FLOW · MNIST and Fashion-MNIST | Bits/dim | No clear effect |
| Clip the stopping time to a bounded interval (ablation) | TO-FLOW · MNIST and Fashion-MNIST | training stability | Improved |
| Vary the clipping parameter (ablation) | TO-FLOW · MNIST and Fashion-MNIST | Bits/dim | No clear effect |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FFJORD — FFJORD: Free-Form Continuous Dynamics for Scalable Reversible Generative Models (ICLR 2019) · better on 6 of 9 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Improving Neural ODE Training with Temporal Adaptive Batch Normalization (NeurIPS 2024 · similarity 0.87)
- Switched Flow Matching: Eliminating Singularities via Switching ODEs (ICML 2024 · similarity 0.87)
- Simulation-Free Training of Neural ODEs on Paired Data (NeurIPS 2024 · similarity 0.87)
- On the Universality of Volume-Preserving and Coupling-Based Normalizing Flows (ICML 2024 · similarity 0.86)
- An Error Analysis of Flow Matching for Deep Generative Modeling (ICML 2025 · similarity 0.86)
- Annealing Flow Generative Models Towards Sampling High-Dimensional and Multi-Modal Distributions (ICML 2025 · 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.
