Xianhang Li

foundation model (3) model scaling (2) representation learning (2) vision transformer (2) adversarial robustness (1) transfer learning (1) image segmentation (1) noisy label learning (1) video generation (1) video classification (1) multimodal learning (1) robust classification (1) adversarial training (1) visual representation (1) model interpretability (1) computational efficiency (1) label noise (1) sequential modeling (1) sparse representation (1) robust optimization (1)