PAIR:实时多模态对话代理中的感知情感推断与调节
Get the story
2026年10月7日,arXiv Human-Computer Interaction 频道发布一手研究,提出 PAIR(Perceptual Affective Inference and Regulation),一种面向实时多模态对话的智能体。该智能体通过评估框架生成 valence-arousal-dominance(效价-唤醒-支配)情感估计,并据此选择调节指引;在呈现上以语音、颜色和虚拟形象线索协同表达情感状态;同时采用滚动记忆机制,使上下文能够跨会话延续。目前报道仅给出方法框架描述,未披露实验数据、评估指标或实际部署情况。
Generated from reports · updated 3 hr ago
Timeline
Follow the coverage from different angles.
- arXiv · Human-Computer InteractionPAIR:实时多模态对话智能体中的感知情感推断与调节
研究者提出 PAIR(Perceptual Affective Inference and Regulation),一种实时多模态对话智能体,通过评估框架生成 valence-arousal-dominance 估计并选择调节指引,以语音、颜色和虚拟形象线索协同呈现,滚动记忆跨会话延续上下文。
Heat trend
Current heat 9·Comparable peak 10(Oct 7)·Comparable change over 24 hours –
The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.