English(EN) Towards Generalizable Visually Grounded Exploration of Household Devices

新的VGEBench基准评估视觉语言模型的设备探索能力

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

研究人员推出了VGEBench，这是一个旨在评估视觉语言模型（VLM）可泛化的视觉基础探索能力的新基准。目前的具身探索方法通常依赖于模仿学习，这限制了智能体的泛化能力。VGEBench旨在通过使用一个逻辑驱动的状态机框架来模拟多轮交互循环，迫使智能体通过主动的视觉感知和反馈驱动的纠正来实现目标，而不依赖于显式文档或标注轨迹。初步实验表明，现有的VLM在将语义知识转化为物理执行和维持长时程状态跟踪方面存在困难。 AI

影响该基准可以通过提供一种标准化的方法来测试和改进VLM在交互环境中的泛化能力，从而推动具身AI的进步。

排序理由该项目是一篇学术论文，介绍了一个用于评估AI能力的新基准。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 30 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目是一篇学术论文，介绍了一个用于评估AI能力的新基准。[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.AI TIER_1 English(EN) · Linhao Zheng, Zeming Liu, Wangke Chen, Li Zeng, Wanxiang Che, Heyan Huang, Yuhang Guo · 2026-09-02 04:00

面向通用化、视觉基础的家用设备探索

arXiv:2609.00845v1 Announce Type: new Abstract: Recent advancements in Vision-Language Models (VLMs) have demonstrated impressive capabilities in static visual recognition and high-level semantic reasoning. However, current embodied exploration paradigms still heavily rely on imi…

本文如何被排名

报道来源 [1]

面向通用化、视觉基础的家用设备探索

相关实体

相关话题