Skip to content
Hot eventLive

Moshi全双工语音模型情绪激活引导研究

1 reports1 sources4 hr ago updated

Get the story

AI overview

该研究在全开源全双工语音语言模型Moshi中探索情绪转向,采用均值差激活转向覆盖四种情绪,每帧只需几次向量加法、无需重训。研究发现情绪可从残差流线性解码,但激活转向仅部分可行且不均衡:happy、angry与surprise共享同一方向,sad则可独立转向,且三者共享成分无法从所有情绪中等量投影剔除。论文提出情绪转向遵循几何结构而非标签,并被NeurIPS 2026实时会话智能体研讨会(RTCA)接收。

Generated from reports · updated 3 hr ago

Timeline

Follow the coverage from different angles.

Oct 8, 2026
  1. arXiv · Computation and Language
    情绪转向遵循几何结构而非标签:全双工语音模型中的情绪方向

    研究在全开源全双工语音语言模型 Moshi 中探索情绪转向,用均值差激活转向覆盖四种情绪,每帧只需几次向量加法、无需重训。情绪可从残差流线性解码,但激活转向仅部分可行且不均衡:happy、angry 与 surprise 共享同一方向,sad 则可独立转向,且三者共享成分无法从所有情绪中等量投影剔除。论文被 NeurIPS 2026 实时会话智能体研讨会(RTCA)接收。

Heat trend

Current heat 9·Comparable peak 10(Oct 8)·Comparable change over 24 hours –

02.557.510Oct8Oct8Oct8Oct8

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.