# Distributional Matching on ICU GIB

Source: [Distributional Matching on ICU GIB](<https://www.sota2.com/research/sota/distributional-matching-on-icu-gib>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:49:58.299Z

Evaluation of distributional matching performance on the ICU GIB dataset, typically measured using Maximum Mean Discrepancy (MMD).

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Distributional Matching |
| Dataset (including any stated split) | ICU GIB |
| Metric | MMD |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [MMD](<https://www.sota2.com/research/sota/distributional-matching-on-icu-gib.md?metric=MMD>): Lower is better; unit: SCALAR.

## Recorded results

| Method | MMD | Result date | Report paper |
| --- | --- | --- | --- |
| TFM | 0.844 | Not recorded | 68fa76d51e209131cea6f662 |
| TFM-ODE | 1.087 | Not recorded | 68fa76d51e209131cea6f662 |
| NeuralSDE | 1.332 | Not recorded | 68fa76d51e209131cea6f662 |
| NeuralODE | 2.09 | Not recorded | 68fa76d51e209131cea6f662 |

### TFM

MMD: 0.844. Result ID: 69944f983a6c3148491c6c3f.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76d51e209131cea6f662.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76d51e209131cea6f662.md>)

[Implementation](<https://github.com/nZhangx/TrajectoryFlowMatching>)

Recorded evaluation configuration: {"Model Type":"Stochastic"}. This record does not assert independent reproduction.

### TFM-ODE

MMD: 1.087. Result ID: 69944f983a6c3148491c6c3d.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76d51e209131cea6f662.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76d51e209131cea6f662.md>)

[Implementation](<https://github.com/nZhangx/TrajectoryFlowMatching>)

Recorded evaluation configuration: {"Model Type":"Deterministic"}. This record does not assert independent reproduction.

### NeuralSDE

MMD: 1.332. Result ID: 69944f983a6c3148491c6c3e.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76d51e209131cea6f662.md>)

Recorded evaluation configuration: {"Model Type":"Stochastic"}. This record does not assert independent reproduction.

### NeuralODE

MMD: 2.09. Result ID: 69944f983a6c3148491c6c3c.

[Reporting paper](<https://www.sota2.com/research/paper/68fa76d51e209131cea6f662.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa66cb1e209131cea12502.md>)

[Implementation](<https://www.sota2.com/github.com/rtqichen/torchdiffeq>)

Recorded evaluation configuration: {"Model Type":"Deterministic"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
