Xiufeng Song

multi-modal learning (2) representation learning (1) multi-task learning (1) imitation learning (1) robotic manipulation (1) domain adaptation (1) anomaly detection (1) multimodal learning (1) deepfake detection (1) spatio-temporal learning (1) foundation model (1) mixture of expert (1) vision-language model (1) embodied agent (1) robotics manipulation (1) feature augmentation (1) multi-agent collaboration (1) temporal module (1) contrastive language-image pre-training (1) forgery detection (1)