Yanghao Zhou

continual learning (1) cross-modal learning (1) test-time adaptation (1) referring expression (1) automatic speech recognition (1) weakly-supervised learning (1) model ensembling (1) multimodal language model (1) domain shift (1) failure diagnosis (1) audio-visual segmentation (1) temporal localization (1) audio-visual event localization (1) semantic propagation (1) signal fidelity (1) object-aware reasoning (1) explicit reasoning chain (1) text-to-audio-video generation (1) multi-talker dialogue (1) multi-speaker dialogue generation (1)