Hugging Face Papers ↗ · 2026-11-16
VideoNexus: Video Perception Beyond the Reasoning Context
媒体报道 Hugging Face Papers 原文语言:中文
论文摘要(作者报告,未经本站复测):Understanding long videos requires locating evidence, resolving visual details, and integrating observations into an answer.
全文
VideoNexus separates detailed video perception from evidence-driven planning and reasoning, using perception sub-agents to return compact temporally grounded evidence and achieving higher accuracy at lower cost on long-video benchmarks.
正文以来源语言显示。