Jang, Kangwook

2 publications

ICML 2025 MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition Sungnyun Kim, Kangwook Jang, Sangmin Bae, Sungwoo Cho, Se-Young Yun

ICLR 2025 Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation Sungnyun Kim, Sungwoo Cho, Sangmin Bae, Kangwook Jang, Se-Young Yun