English(EN) ExBind: A Controlled Diagnostic Benchmark for Visual-to-Executable Correspondence

新的ExBind基准测试多模态模型视觉到可执行代码的准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-02 04:00

研究人员推出ExBind，一个旨在评估多模态模型将视觉或语义参考映射到特定可执行对象准确性的新型诊断基准。该基准隔离了视觉到可执行代码的对应层，超越了简单的执行成功，以查明对象选择中的失败。ExBind包含一套广泛的250个案例和一套有针对性的240个案例，格式包括SVG、DOM和表格等。早期评估显示，Qwen2.5-VL-3B在该基准上实现了76.4%的精确准确率，而Qwen3-VL-4B达到了98.8%的精确准确率。 AI

影响该基准有望推动多模态模型在准确解释和交互视觉界面方面的能力得到提升。

排序理由该条目描述了一个用于评估多模态模型的新基准，发表在arXiv论文中。[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: 31 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目描述了一个用于评估多模态模型的新基准，发表在arXiv论文中。[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, product; 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) · Ziqian Wang, Yuxiao Cheng, Tingxiong Xiao, Jinli Suo · 2026-09-02 04:00

ExBind：视觉到可执行代码对应关系的受控诊断基准

arXiv:2609.01344v1 Announce Type: new Abstract: Multimodal coding and editing systems must map a visible or semantic referent to the exact executable object that can be edited. A wrong reference may select a valid but incorrect DOM node, SVG element, graph endpoint, hierarchy mem…

本文如何被排名

报道来源 [1]

ExBind：视觉到可执行代码对应关系的受控诊断基准

相关实体

相关话题