English(EN) Decoupling What from Where: How Should a Small GUI Grounding Model Receive the Action Type?

新研究探讨小型GUI基础模型最优动作类型输入方法

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-07 04:00

研究人员探索了小型GUI基础模型有效接收动作类型的方法，并比较了五种不同方法。在Android in the Wild数据集上使用LoRA对Qwen2-VL-2B模型进行微调，他们发现辅助损失、加性学习嵌入和基于提示的动作词显著提高了性能，优于基线。然而，硬路由和前缀标记没有显示出明显的好处，而将屏幕外触摸点夹紧的预处理选择对基础准确性产生了负面影响。 AI

影响这项研究为提高小型AI模型在GUI交互中的效率和准确性提供了见解，可能影响更强大的辅助技术的开发。

排序理由学术论文，详细介绍了一种新颖的模型训练和评估方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 学术论文，详细介绍了一种新颖的模型训练和评估方法。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Aadi Chauhan, Arthur Ilyasov · 2026-10-07 04:00

解耦“什么”与“哪里”：小型GUI基础模型应如何接收动作类型？

arXiv:2610.07444v1 Announce Type: new Abstract: A GUI agent decides which action to take and where to take it; we ask how a small grounding model should receive the action type. Fine-tuning Qwen2-VL-2B with LoRA on Android in the Wild, we compare a flat baseline with five ways of…

本文如何被排名

报道来源 [1]

解耦“什么”与“哪里”：小型GUI基础模型应如何接收动作类型？

相关实体

相关话题