v.2.0.0
deuxfleurs-org/garagev.2.0.0Feb 13, 2025by yadong-lu
AI Summary
V2.0.0 introduces a larger dataset, 60% latency improvement, and strong performance metrics. It consolidates functionality into a single OmniTool for controlling Windows 11 VMs.
Key Highlights
- 60% improvement in latency compared to V1
- 39.6 average accuracy on ScreenSpot Pro
- OmniTool unifies vision models (OpenAI, DeepSeek, Qwen, Anthropic)
- Support for Windows 11 VM control
New Features
- Larger and cleaner icon caption + grounding dataset
- OmniTool integration
- Support for Anthropic Computer Use
- Support for OpenAI 4o/o1/o3-mini
- Support for DeepSeek R1
- Support for Qwen 2.5VL
Full Release Notes
# What's new in V2.0.0? - Larger and cleaner set of icon caption + grounding dataset - 60% improvement in latency compared to V1 [model checkpoints](https://huggingface.co/microsoft/OmniParser-v2.0) - Strong performance: 39.6 average accuracy on [ScreenSpot Pro](https://github.com/likaixin2000/ScreenSpot-Pro-GUI-Grounding) - Your agent only need one tool: OmniTool. Control a Windows 11 VM with OmniParser + your vision model of choice. OmniTool supports out of the box the following large language models - OpenAI (4o/o1/o3-mini), DeepSeek (R1), Qwen (2.5VL) or Anthropic Computer Use.