# Nonverbal (NV) Location Prediction on NonverbalTTS

Source: [Nonverbal (NV) Location Prediction on NonverbalTTS](<https://www.sota2.com/research/sota/nonverbal-nv-location-prediction-on-nonverbaltts>)

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

Data updated: 2026-03-17T10:14:44.509Z

Evaluation of Nonverbal Location Prediction performance on the NonverbalTTS dataset, measured using accuracy metrics (Acc@1/3/5), Jensen-Shannon Divergence (JSD), and Hausdorff Distance (HD).

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 | Nonverbal (NV) Location Prediction |
| Dataset (including any stated split) | NonverbalTTS |
| Metric | Accuracy @1 |
| Unit | PERCENT |
| Direction | Higher is better |
| Results loaded | 5 of 5 |
| 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

- [Accuracy @1](<https://www.sota2.com/research/sota/nonverbal-nv-location-prediction-on-nonverbaltts.md?metric=Accuracy%20%401>): Higher is better; unit: PERCENT.

- [Accuracy @3](<https://www.sota2.com/research/sota/nonverbal-nv-location-prediction-on-nonverbaltts.md?metric=Accuracy%20%403>): Higher is better; unit: PERCENT.

- [Accuracy @5](<https://www.sota2.com/research/sota/nonverbal-nv-location-prediction-on-nonverbaltts.md?metric=Accuracy%20%405>): Higher is better; unit: PERCENT.

- [Jensen-Shannon Divergence (JSD)](<https://www.sota2.com/research/sota/nonverbal-nv-location-prediction-on-nonverbaltts.md?metric=Jensen-Shannon%20Divergence%20(JSD)>): Lower is better; unit: SCALAR.

- [Hausdorff Distance (HD)](<https://www.sota2.com/research/sota/nonverbal-nv-location-prediction-on-nonverbaltts.md?metric=Hausdorff%20Distance%20(HD)>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Accuracy @1 | Result date | Report paper |
| --- | --- | --- | --- |
| GPT-oss-20B | 26.84 | Not recorded | 69b8e0180636e5bf4afbeaed |
| Vicuna-7B | 13.78 | Not recorded | 69b8e0180636e5bf4afbeaed |
| Affectron-330M | 12.59 | Not recorded | 69b8e0180636e5bf4afbeaed |
| Qwen 2.5-7B | 7.48 | Not recorded | 69b8e0180636e5bf4afbeaed |
| LLaMA 3.1-8B | 5.46 | Not recorded | 69b8e0180636e5bf4afbeaed |

### GPT-oss-20B

Accuracy @1: 26.84. Result ID: 69b9298347f34ce924a26c55.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0180636e5bf4afbeaed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7ab01e209131cea84a0c.md>)

Recorded evaluation configuration: {"zero-shot":"true"}. This record does not assert independent reproduction.

### Vicuna-7B

Accuracy @1: 13.78. Result ID: 69b9298347f34ce924a26c56.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0180636e5bf4afbeaed.md>)

Recorded evaluation configuration: {"zero-shot":"true"}. This record does not assert independent reproduction.

### Affectron-330M

Accuracy @1: 12.59. Result ID: 69b9298347f34ce924a26c57.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0180636e5bf4afbeaed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69b8e0180636e5bf4afbeaed.md>)

Recorded evaluation configuration: {"zero-shot":"true"}. This record does not assert independent reproduction.

### Qwen 2.5-7B

Accuracy @1: 7.48. Result ID: 69b9298347f34ce924a26c53.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0180636e5bf4afbeaed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75b71e209131cea6981e.md>)

Recorded evaluation configuration: {"zero-shot":"true"}. This record does not assert independent reproduction.

### LLaMA 3.1-8B

Accuracy @1: 5.46. Result ID: 69b9298347f34ce924a26c54.

[Reporting paper](<https://www.sota2.com/research/paper/69b8e0180636e5bf4afbeaed.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa75d11e209131cea6a028.md>)

[Implementation](<https://github.com/meta-llama/llama-agentic-system>)

Recorded evaluation configuration: {"zero-shot":"true"}. This record does not assert independent reproduction.

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