OmniEcho: Spatial Audio Understanding for Embodied Agents

  • 类型:arxiv
  • 标识:2609.23407
  • 链接:https://arxiv.org/abs/2609.23407
  • 主分类:multimodal
  • 形态:benchmark
  • TLDR:Humans can effortlessly localize the direction of a sound source and integrate it with visual cues for reasoning, yet this remains challenging for embodied agents. In particular, it is still unclear how to effectively evaluate and model spatial audio understanding in embodied settings. To address this gap, we introduce OmniEchoBench, a unified benchmark for spatial audio-visual perception and audio-vision-language navigation. OmniEchoBench comprises six tasks over 197 real-world spatial audio-visual scenes, 2,972 question-answer pairs, and 900 navigation samples with first-order ambisonics (FO
  • 副分类:agent
  • 待LLM分类:否
  • 来源文件:
  • /inbox/tom/_candidates/2026-09-25-agent-rag-longcontext-candidates.json