智能体能否察言观色 多模态仿真场景下视觉社交智能基准评测 Can Agents Read the Room Benchmarking Visual Social Intelligence in Multimodal Simulation.pptx

智能体能否察言观色 多模态仿真场景下视觉社交智能基准评测 Can Agents Read the Room Benchmarking Visual Social Intelligence in Multimodal Simulation.pptx

Abstract

Socialinteractiondependsonbothlanguageandvisiblesocialsignals,suchasfacialexpres-sions,posture,gaze,andemotionalshifts.Yetexistingsocial-agentbenchmarksarelargelytext-basedandrarelytestwhethermultimodalagentscanusevisual

文档评论(0)

1亿VIP精品文档

相关文档