Yiyang Shao — accepted AI-conference papers

2025

LangWBC: Language-directed Humanoid Whole-Body Control via End-to-end Learning

Yiyang Shao, Bike Zhang, Qiayuan Liao, Xiaoyu Huang, Yuman Gao, Yufeng Chi +3

RSS 2025poster

General-purpose humanoid robots are expected to interact intuitively with humans, enabling seamless integration into daily life. Natural language provides the most accessible medium for this purpose. However, translating languages into humanoid whole-body motions remains a significant challenge, pri…

Cited by 0 PDF ↗Scholar ↗

2025

Learning Optimal Multimodal Information Bottleneck Representations

Qilong Wu, Yiyang Shao, Jun Wang, Xiaobo Sun

ICML 2025poster

Leveraging high-quality joint representations from multimodal data can greatly enhance model performance in various machine-learning based applications. Recent multimodal learning methods, based on the multimodal information bottleneck (MIB) principle, aim to generate optimal MIB with maximal task-r…

Cited by 0 Source ↗PDF ↗Scholar ↗