English(EN) Learning from Reliable Negatives: Confidence-Anchored Test-Time Adaptation for GUI Grounding

新的GUI基础方法从负样本中学习

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员开发了一种新的无标签测试时训练方法，用于GUI基础，这是自主代理解释自然语言命令的关键步骤。该方法称为置信度锚定负学习（CANL），利用坐标标记中的置信度模式，并优先从负样本中学习，而不是潜在的嘈杂正样本。CANL-7B在ScreenSpot-V2基准测试中取得了92.1%的准确率，并在更具挑战性的ScreenSpot-Pro数据集上取得了8.9%的绝对提升，显示出显著的改进。 AI

影响这种新方法可以显著降低训练自主代理的标注成本，从而实现更具可扩展性的GUI基础能力的开发。

排序理由详细介绍GUI基础新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.CV 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: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍GUI基础新方法的学术论文。[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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.CV TIER_1 English(EN) · Yizhou Liu, Fei Tang, Yuchen Yan, Zhengxi Lu, Songqin Nong, Tao Jiang, Wenhao Xu, Wenqi Zhang, Weiming Lu, Jun Xiao, Yongliang Shen · 2026-09-15 04:00

从可靠的负样本中学习：置信度锚定的测试时自适应用于GUI基础

arXiv:2609.15307v1 Announce Type: new Abstract: Graphical User Interface (GUI) grounding is essential for autonomous agents to map natural language instructions to precise screen coordinates. However, existing supervised fine-tuning and reinforcement learning methods are constrai…

本文如何被排名

报道来源 [1]

从可靠的负样本中学习：置信度锚定的测试时自适应用于GUI基础

相关实体

相关话题