Huggingface
H Company has released its largest UI localization model yet, Holo2-235B-A22B Preview, setting new State-of-the-Art records on benchmarks like Screenspot-Pro and OSWorld G. The model utilizes agentic localization to improve accuracy on high-resolution interfaces.
AI 生成摘要
H公司發布了其迄今為止最大的UI本地化模型Holo2-235B-A22B Preview，在Screenspot-Pro和OSWorld G等基準測試中創下新的最先進（SOTA）紀錄。該模型採用了代理本地化技術，以提高在高解析度介面上的準確性。
Two months since releasing our first batch of Holo2 models, H Company is back with our largest UI localization model yet: Holo2-235B-A22B Preview. This model achieves a new State-of-the-Art (SOTA) record of 78.5% on Screenspot-Pro and 79.0% on OSWorld G.
Available on Hugging Face, Holo2-235B-A22B Preview is a research release focused on UI element localization.
Agentic Localization
High-resolution 4K interfaces are challenging for localization models. Small UI elements can be difficult to pinpoint on a large display. With agentic localization, however, Holo2 can iteratively refine its predictions, improving accuracy with each step and unlocking 10-20% relative gains across all Holo2 model sizes.
Holo2-235B-A22B's Performance on ScreenSpot-Pro
Holo2-235B-A22B Preview reaches 70.6% accuracy on ScreenSpot-Pro in a single step. In agent mode, it achieves 78.5% within 3 steps, setting a new state-of-the-art on the most challenging GUI grounding benchmark.
·
Sign up or
log in to comment