Authors

Bosong Ding

Publications 2

Preprint Open access

GestAdapt: Workspace-Conditioned Co-Speech Gesture Generation for Humanoid Robots

Bosong Ding, Xianglin Zhang, Miao Xin et al. · 2026

Co-speech gestures for robots must adapt not only to speech and embodiment, but also to the workspace available for performing the motion. Since the same speech can be accompanied by different gestures, a robot can respond to workspace constraints, e.g., gestures for speech next to a wall. In these scenarios, the robot …

Preprint Open access

Co-Speech with You: Training-Free Personalization of Robot Co-Speech Gestures

Bosong Ding, Selma Ancel, Giacomo Spigler et al. · 2026

Personal robots should adapt their co-speech gesture style to a new user without requiring model retraining. We present a training-free personalization pipeline that combines a frozen audio-conditioned diffusion prior with a gesture style encoder and lightweight conditioning adapters. The encoder is first trained to di …

Co-authors