v.2.0.0

OpenBMB/VoxCPMv.2.0.0Feb 13, 2025by yadong-lu

AI Summary

A major version update featuring a 60% reduction in latency and strong performance on the ScreenSpot Pro benchmark. It introduces a unified OmniTool for controlling Windows 11 VMs and provides an expanded dataset for icon captioning and grounding.

Key Highlights

60% improvement in latency compared to V1
39.6 average accuracy on ScreenSpot Pro
Unified OmniTool for Windows 11 VM control
Expanded icon captioning and grounding dataset

New Features

OmniTool integration supporting OpenAI (4o/o1/o3-mini), DeepSeek (R1), Qwen (2.5VL), and Anthropic Computer Use
Windows 11 VM control
Enhanced dataset for icon captioning and grounding

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.