Research map / Probabilistic and scientific modeling / Dynamical systems
TrajectoryNet: A Dynamic Optimal Transport Network for Modeling Cellular Dynamics
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 |
|---|---|---|---|
| Add velocity regularization (ablation) | TrajectoryNet Base · Arch artificial data | EMD: 0.691 -> 0.243 | Helped |
| Add velocity regularization (ablation) | TrajectoryNet Base · Tree artificial data | EMD: 0.490 -> 0.143 | Helped |
| Add velocity regularization (ablation) | TrajectoryNet Base · Cycle artificial data | MSE: 0.190 -> 0.068 | Helped |
| Add density regularization (ablation) | TrajectoryNet Base · Mouse cortex | EMD: 0.897 ± 0.06 -> 0.888 ± 0.03 | No clear effect |
| Add velocity regularization (ablation) | TrajectoryNet Base · Mouse cortex | EMD: 0.897 ± 0.06 -> 0.899 ± 0.10 | No clear effect |
| Add density and velocity regularization (ablation) | TrajectoryNet Base · Mouse cortex | EMD: 0.897 ± 0.06 -> 0.859 ± 0.07 | Helped |
| Add density regularization (ablation) | TrajectoryNet Base · Embryoid body | EMD: 0.813 -> 0.784 | Helped |
| Add velocity regularization (ablation) | TrajectoryNet Base · Embryoid body | EMD: 0.813 -> 0.840 | Hurt |
| Add energy regularization (ablation) | TrajectoryNet Base · Embryoid body | EMD: 0.764 -> 0.737; 0.811 -> 0.896; 0.863 -> 0.842 | Mixed |
| Add growth regularization (ablation) | TrajectoryNet Base · Embryoid body | EMD: 0.764 -> 0.700; 0.811 -> 0.913; 0.863 -> 0.829 | Mixed |
| Add density regularization to Base + V (ablation) | TrajectoryNet Base · Arch artificial data | EMD: 0.243 -> 0.415 | Hurt |
Closest papers by meaning
- TracingFlow: A Simulation-Free Trajectory Inference Framework Based on Second-Order Dynamics (NeurIPS 2026 · similarity 0.88)
- Joint Velocity-Growth Flow Matching for Single-Cell Dynamics Modeling (NeurIPS 2025 · similarity 0.87)
- Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action (NeurIPS 2025 · similarity 0.86)
- GENOT: Entropic (Gromov) Wasserstein Flow Matching with Applications to Single-Cell Genomics (NeurIPS 2024 · similarity 0.86)
- A Biconvex Formulation for Stable Transport of Mixture Models with a Unique Solution (NeurIPS 2026 · similarity 0.85)
- Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport (ICLR 2025 · similarity 0.85)
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.