Tongkun Guan

document understanding (3) self-supervised learning (2) multi-modal large language model (2) multimodal large language model (2) visual foundation model (1) visual-language alignment (1) mask generation (1) scene text recognition (1) token-level prediction (1) text segmentation (1) visual language model (1) visual-text alignment (1) text recognition (1) visual language alignment (1) glyph structure (1) implicit attention (1) character segmentation (1) text-rich image understanding (1) character-to-character distillation (1) visual question answering (1)