Video-Text-to-Text
English
gui
agent
GUI-Vid / README.md
Dongping-Chen
revise readme
2e4713d
|
raw
history blame
368 Bytes
---
license: cc-by-4.0
datasets:
- shuaishuaicdp/GUI-World
language:
- en
metrics:
- bertscore
- LLM-as-a-Judge
tags:
- gui
- agent
---
This is the first VideoLLM with powerful GUI-oriented capabilities, retrained on [GUI-World](https://gui-world.github.io). See [Github](https://github.com/Dongping-Chen/GUI-World) for how to use GUI-Vid for GUI understanding tasks.