update readme
Browse files
README.md
CHANGED
|
@@ -230,10 +230,10 @@ Increasing input from 64 to 128 frames doubles the number of visual tokens (13,4
|
|
| 230 |
## Potential Applications
|
| 231 |
|
| 232 |
ViCA-7B supports a broad range of spatially grounded multimodal applications:
|
| 233 |
-
-
|
| 234 |
-
-
|
| 235 |
-
-
|
| 236 |
-
-
|
| 237 |
|
| 238 |
## Known Limitations
|
| 239 |
|
|
|
|
| 230 |
## Potential Applications
|
| 231 |
|
| 232 |
ViCA-7B supports a broad range of spatially grounded multimodal applications:
|
| 233 |
+
- Indoor navigation assistants
|
| 234 |
+
- Robotics planning and spatial querying
|
| 235 |
+
- Smart room arrangement and AR layout analysis
|
| 236 |
+
- Scene understanding for embodied AI agents
|
| 237 |
|
| 238 |
## Known Limitations
|
| 239 |
|