Zonglin Di

federated learning (1) adversarial learning (1) vision-language navigation (1) domain adaptation (1) self-supervised learning (1) knowledge distillation (1) test-time adaptation (1) human pose estimation (1) text-to-image generation (1) machine unlearning (1) model forgetting (1) visual recognition (1) backdoor attack (1) generative model (1) multimodal large language model (1) embodied agent (1) image manipulation (1) road extraction (1) bias measurement (1) model personalization (1)