Junfeng Luo

document understanding (3) multi-modal large language model (2) visual question answering (2) multimodal large language model (2) lane detection (1) autonomous driving (1) instruction tuning (1) deep neural network (1) feature fusion (1) vision-language model (1) autonomous vehicle (1) multimodal representation (1) feature aggregation (1) real-time inference (1) visual foundation model (1) visual-language alignment (1) mask generation (1) inference speed (1) token-level prediction (1) spatial information (1)