Research map / Probabilistic and scientific modeling / Dynamical systems
Beyond Continuity: Simulation-free Reconstruction of Discrete Branching Dynamics from Single-cell Snapshots
Junda Ying, Yuxuan Wang, Bowen Yang, Peijie Zhou, Lei Zhang
Read the paperCheck 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 |
|---|---|---|---|
| model stochasticity and unbalanced mass jointly (USB) instead of balanced SF2M | SF2M · Simulation 2D, Dyngen, Gaussian 1000D | W1: 0.224 -> 0.019; 1.277 -> 0.131; 3.543 -> 2.136 | Improved |
| add stochastic bridge (USB) to unbalanced WFR-FM | WFR-FM · Gaussian 1000D | W1: 2.233 -> 2.136 | Improved |
| add stochastic bridge (USB) to unbalanced WFR-FM | WFR-FM · Simulation 2D | W1: 0.019 -> 0.019 | No clear effect |
| add stochastic bridge (USB) to unbalanced WFR-FM | WFR-FM · Dyngen 5D | RME: 0.005 -> 0.007 | Hurt |
| use USB instead of WFR-FM | WFR-FM · Gaussian 1000D | RME: 0.044 -> 0.004 | Improved |
| use USB instead of WFR-FM for held-out interpolation | WFR-FM · Mouse (50D) held-out | mean W1: 6.586 -> 6.988 | Hurt |
| use USB instead of WFR-FM for held-out interpolation | WFR-FM · CITE (50D) held-out | mean W1: 37.221 -> 37.087 | Improved |
| use USB instead of DeepRUOT for held-out interpolation | DeepRUOT · EB (50D) held-out | mean W1: 10.075 -> 10.177 | Hurt |
| use USB growth rate network | WFR-FM · Simulation gene | growth-rate Pearson correlation: mean 0.9739 | Improved |
| use branching inference with USB growth rate | USB · Simulation event counts | Pearson correlation: 0.9950, relative error 10.7% | Improved |
| use branching inference for branch occupancy | USB · Dyngen terminal states | branch ratio: ground truth 0.708 : 0.292 vs USB 0.650 : 0.350 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- WFR-FM — WFR-FM: Simulation-Free Dynamic Unbalanced Optimal Transport (ICLR 2026) · better on 4 of 10 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
- Modeling Cell Dynamics and Interactions with Unbalanced Mean Field Schrödinger Bridge (NeurIPS 2025 · similarity 0.89)
- Learning stochastic dynamics from snapshots through regularized unbalanced optimal transport (ICLR 2025 · similarity 0.88)
- Inferring stochastic dynamics with growth from cross-sectional data (NeurIPS 2025 · similarity 0.88)
- Joint Velocity-Growth Flow Matching for Single-Cell Dynamics Modeling (NeurIPS 2025 · similarity 0.87)
- Curly Flow Matching for Learning Non-gradient Field Dynamics (NeurIPS 2025 · similarity 0.86)
- Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-free (NeurIPS 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.
