masterleopold commited on
Commit
3bc2fc1
路
verified 路
1 Parent(s): fbaf797

Widen the card to the on-board model work and state where it is developed

Browse files
Files changed (1) hide show
  1. README.md +11 -3
README.md CHANGED
@@ -9,9 +9,17 @@ pinned: false
9
 
10
  # Vox
11
 
12
- **Applied AI, research datasets, and developer tools.**
13
 
14
- Vox builds AI-powered products and tools. Here on Hugging Face, we share datasets for patent research and agent evaluation, including resources developed for [Parallax](https://parallax.modelina.ai). Explore our software and agent frameworks on [GitHub](https://github.com/VoxTechnologies).
 
 
 
 
 
 
 
 
15
 
16
  ## Featured datasets
17
 
@@ -20,6 +28,6 @@ Vox builds AI-powered products and tools. Here on Hugging Face, we share dataset
20
 
21
  ## Explore and contribute
22
 
23
- Read each dataset card for its scope, provenance, schema, limitations, citation, and license terms. For questions, feedback, or data-quality reports, open a discussion in the relevant repository.
24
 
25
  [Website](https://vox.delivery) 路 [GitHub](https://github.com/VoxTechnologies) 路 [LinkedIn](https://www.linkedin.com/company/v13s)
 
9
 
10
  # Vox
11
 
12
+ **Applied AI: on-board models, research datasets, and developer tools.**
13
 
14
+ Vox builds AI-powered products and tools. Here on Hugging Face we publish work in two areas: models that run on board unmanned aircraft for disaster reconnaissance, and datasets for patent research and agent evaluation, including resources developed for [Parallax](https://parallax.modelina.ai). Explore our software and agent frameworks on [GitHub](https://github.com/VoxTechnologies).
15
+
16
+ **Models published under this organization are developed in Japan by Vox, which operates from Tokyo.**
17
+
18
+ ## Disaster-response models
19
+
20
+ Our on-board work targets the first hours after a flood or an earthquake, when a drone has to decide what to look at next rather than fly a route fixed before take-off. The models read the current view and emit a viewpoint sequence, which a separate safety layer checks against a pre-approved volume before anything reaches the flight controller. They are fine-tunes of open base models, trained on public UAV footage published by the Geospatial Information Authority of Japan under the Japanese Public Data License.
21
+
22
+ Model cards carry the measured results, the retracted ones, and the limits, including what has not been tested.
23
 
24
  ## Featured datasets
25
 
 
28
 
29
  ## Explore and contribute
30
 
31
+ Read each model and dataset card for its scope, provenance, measurements, limitations, citation, and license terms. For questions, feedback, or data-quality reports, open a discussion in the relevant repository.
32
 
33
  [Website](https://vox.delivery) 路 [GitHub](https://github.com/VoxTechnologies) 路 [LinkedIn](https://www.linkedin.com/company/v13s)