v.2.0.0
TanStack/routerv.2.0.0Feb 13, 2025by yadong-lu
AI Summary
This release introduces a significant performance boost with a 60% reduction in latency and improved accuracy. It introduces OmniTool, a unified interface for controlling Windows 11 VMs using vision models, alongside an expanded and cleaner dataset.
Key Highlights
- 60% improvement in latency compared to V1
- Strong performance: 39.6 average accuracy on ScreenSpot Pro
- Introduction of OmniTool for controlling Windows 11 VMs
- OmniTool supports OpenAI, DeepSeek, Qwen, and Anthropic out of the box
- Larger and cleaner set of icon caption + grounding dataset
New Features
- OmniTool integration
- Windows 11 VM control
- Multi-LLM support (OpenAI 4o/o1/o3-mini, DeepSeek R1, Qwen 2.5VL, Anthropic Computer Use)
- Enhanced grounding dataset
- Performance optimizations
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.