1
LLM-Powered Interactive Robotic Action Synthesis from Multimodal Speech, Gestures, and Music
利用大模型推理能力，融合语音、手势与音乐多模态信号，让机器人动作表达更自然直观。
arXiv:2606.31158v1 Announce Type: cross Abstract: The quest for intuitive and natural human-robot interaction (HRI) remains a significant challenge in…