Can Huang

Reinforcement Learning (1)

multimodal learning (3) multimodal large language model (3) document understanding (2) vision-language model (2) visual question answering (2) image captioning (2) large language model (2) benchmark evaluation (2) scene text recognition (2) domain adaptation (1) few-shot learning (1) reinforcement learning (1) vision-language alignment (1) video understanding (1) document analysis (1) named entity recognition (1) parallel processing (1) visual recognition (1) in-context learning (1) computational efficiency (1)