v.2.0.0

shadowsocks/shadowsocks-windowsv.2.0.0Feb 13, 2025by yadong-lu

AI Summary

This release introduces significant performance improvements and a unified tooling experience. It features a larger dataset, a 60% reduction in latency, and the introduction of 'OmniTool,' which simplifies agent control for Windows 11 VMs by supporting various LLMs natively.

Key Highlights

60% improvement in latency compared to V1
Introduction of OmniTool for unified agent control
Native support for OpenAI (4o/o1/o3-mini), DeepSeek (R1), Qwen (2.5VL), and Anthropic Computer Use
Improved accuracy of 39.6 on ScreenSpot Pro benchmark

New Features

Larger and cleaner icon caption and grounding dataset
OmniTool integration
Support for multiple large language models (LLMs)

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.