Kaiyou Song

self-supervised learning (5) visual representation learning (3) representation learning (3) visual representation (3) vision transformer (2) transfer learning (1) preference learning (1) knowledge distillation (1) semantic consistency (1) collaborative learning (1) multimodal large language model (1) cross attention (1) self-supervised pre-training (1) pretext task (1) positional embedding (1) autoregressive modeling (1) masked image modeling (1) position reconstruction (1) feature search (1) patch permutation (1)