SungHeon Jeong

model compression (1) representation learning (1) zero-shot learning (1) vision transformer (1) few-shot learning (1) transfer learning (1) image retrieval (1) multimodal learning (1) cross-modal learning (1) multi-modal large language model (1) multimodal large language model (1) token pruning (1) image-text alignment (1) event-based camera (1) latent token (1) vision projection (1) geometric probing (1) task-oriented segmentation (1)