# Egocentric vision-language motion generation on Nymeria (test)

Source: [Egocentric vision-language motion generation on Nymeria (test)](<https://www.sota2.com/research/sota/egocentric-vision-language-motion-generation-on-nymeria-test>)

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

Data updated: 2026-04-23T08:02:22.763Z

Evaluation of models generating egocentric vision-language motion sequences conditioned on prompts, using the test split of the Nymeria dataset. Metrics include FID, R@Top1, MM-Dist, FS, FC, Acce, and Jerk.

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 | Egocentric vision-language motion generation |
| Dataset (including any stated split) | Nymeria (test) |
| Metric | R@Top1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 6 of 6 |
| 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

- [R@Top1](<https://www.sota2.com/research/sota/egocentric-vision-language-motion-generation-on-nymeria-test.md?metric=R%40Top1>): Higher is better; unit: PERCENT.

- [FID](<https://www.sota2.com/research/sota/egocentric-vision-language-motion-generation-on-nymeria-test.md?metric=FID>): Lower is better; unit: SCALAR.

- [MM-Dist](<https://www.sota2.com/research/sota/egocentric-vision-language-motion-generation-on-nymeria-test.md?metric=MM-Dist>): Lower is better; unit: SCALAR.

- [FS](<https://www.sota2.com/research/sota/egocentric-vision-language-motion-generation-on-nymeria-test.md?metric=FS>): Higher is better; unit: SCALAR.

- [FC](<https://www.sota2.com/research/sota/egocentric-vision-language-motion-generation-on-nymeria-test.md?metric=FC>): Higher is better; unit: SCALAR.

- [Accuracy](<https://www.sota2.com/research/sota/egocentric-vision-language-motion-generation-on-nymeria-test.md?metric=Accuracy>): Higher is better; unit: PERCENT.

- [Jerk](<https://www.sota2.com/research/sota/egocentric-vision-language-motion-generation-on-nymeria-test.md?metric=Jerk>): Lower is better; unit: SCALAR.

## Recorded results

| Method | R@Top1 | Result date | Report paper |
| --- | --- | --- | --- |
| EgoMotion | 69.4 | Not recorded | 69e85b9e7d0172140ec80f6c |
| Real | 67.4 | Not recorded | 69e85b9e7d0172140ec80f6c |
| MoMask | 41.2 | Not recorded | 69e85b9e7d0172140ec80f6c |
| MotionDiffuse | 37.2 | Not recorded | 69e85b9e7d0172140ec80f6c |
| MMM | 36.1 | Not recorded | 69e85b9e7d0172140ec80f6c |
| T2M-GPT | 28.1 | Not recorded | 69e85b9e7d0172140ec80f6c |

### EgoMotion

R@Top1: 69.4. Result ID: 69e9d20d47f34ce924d0cdd0.

[Reporting paper](<https://www.sota2.com/research/paper/69e85b9e7d0172140ec80f6c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e85b9e7d0172140ec80f6c.md>)

Recorded evaluation configuration: {"Motion Generator":"Latent Diffusion","Training Strategy":"Two-stage"}. This record does not assert independent reproduction.

### Real

R@Top1: 67.4. Result ID: 69e9d20d47f34ce924d0cdcb.

[Reporting paper](<https://www.sota2.com/research/paper/69e85b9e7d0172140ec80f6c.md>)

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

### MoMask

R@Top1: 41.2. Result ID: 69e9d20d47f34ce924d0cdce.

[Reporting paper](<https://www.sota2.com/research/paper/69e85b9e7d0172140ec80f6c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa715d1e209131cea50e45.md>)

[Implementation](<https://ericguo5513.github.io/momask/>)

Recorded evaluation configuration: {"adaptation":"adapted to egocentric vision-language setting"}. This record does not assert independent reproduction.

### MotionDiffuse

R@Top1: 37.2. Result ID: 69e9d20d47f34ce924d0cdcf.

[Reporting paper](<https://www.sota2.com/research/paper/69e85b9e7d0172140ec80f6c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6d571e209131cea3944b.md>)

[Implementation](<https://mingyuan-zhang.github.io/projects/MotionDiffuse.html>)

Recorded evaluation configuration: {"adaptation":"adapted to egocentric vision-language setting"}. This record does not assert independent reproduction.

### MMM

R@Top1: 36.1. Result ID: 69e9d20d47f34ce924d0cdcd.

[Reporting paper](<https://www.sota2.com/research/paper/69e85b9e7d0172140ec80f6c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa72ac1e209131cea57c37.md>)

[Implementation](<https://exitudio.github.io/MMM-page>)

Recorded evaluation configuration: {"adaptation":"adapted to egocentric vision-language setting"}. This record does not assert independent reproduction.

### T2M-GPT

R@Top1: 28.1. Result ID: 69e9d20d47f34ce924d0cdcc.

[Reporting paper](<https://www.sota2.com/research/paper/69e85b9e7d0172140ec80f6c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa70b31e209131cea4ca96.md>)

[Implementation](<https://mael-zys.github.io/T2M-GPT/>)

Recorded evaluation configuration: {"adaptation":"adapted to egocentric vision-language setting"}. This record does not assert independent reproduction.

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