Xinxin Zhang

representation learning (3) multimodal domain adaptation (2) few-shot learning (2) self-supervised learning (2) information bottleneck (2) multimodal learning (2) domain adaptation (2) semi-supervised learning (2) speaker diarization (1) multi-objective optimization (1) generalization bound (1) contextual bandit (1) vision language model (1) variational information bottleneck (1) representation alignment (1) domain shift (1) missing modality (1) cross-modal representation learning (1) correlation alignment (1) multi-speaker recognition (1)