English(EN) Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning

发布新的电商跨视频推理基准测试和智能体框架

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-05 04:00

研究人员推出了AdsCVR，一个旨在评估电商跨视频推理能力的新基准测试，包含2,483个视频和6,110个跨六个推理维度的问答对。为了解决整合来自多个视频的视觉细节、语音和屏幕文本的挑战，他们还提出了AdSeek，一个动态选择工具以获取证据的智能体框架。AdSeek在AdsCVR测试集上达到了74.30%的准确率，显著优于其Qwen3-VL-8B-Instruct骨干模型27.90个百分点，并展示了对CrossVid基准测试的泛化能力。 AI

影响这项研究可能催生更复杂的AI系统，能够理解和比较来自多个视频源的复杂信息，从而改进电商产品分析和营销。

排序理由该集群描述了一篇介绍特定AI任务基准测试和框架的新学术论文。[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: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群描述了一篇介绍特定AI任务基准测试和框架的新学术论文。[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, 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: 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.AI TIER_1 English(EN) · Jinghan Zhao, Yiman Hu, Liang Wu, Jian Xu, Bo Zheng · 2026-10-05 04:00

超越单视频：电商跨视频推理的基准测试与主动证据搜寻

arXiv:2610.03099v1 Announce Type: cross Abstract: E-commerce videos are information-dense and frequently compared by consumers evaluating products and merchants assessing marketing strategies. However, existing multimodal models mainly focus on single-video understanding and have…

本文如何被排名

报道来源 [1]

超越单视频：电商跨视频推理的基准测试与主动证据搜寻

相关实体

相关话题