2 papers
cs.LG2025
Learning Optimal Multimodal Information Bottleneck Representations
Qilong Wu, Yiyang Shao, Jun Wang +1
Leveraging high-quality joint representations from multimodal data can greatly enhance model performance in various machine-learning based applications. Recent multimodal learning…
cs.RO2025
LangWBC: Language-directed Humanoid Whole-Body Control via End-to-end Learning
Yiyang Shao, Xiaoyu Huang, Bike Zhang +6
General-purpose humanoid robots are expected to interact intuitively with humans, enabling seamless integration into daily life. Natural language provides the most accessible mediu…