An-Lan Wang

Reinforcement Learning (1)

multimodal large language model (3) benchmark evaluation (2) image captioning (1) multimodal learning (1) autoregressive model (1) document understanding (1) document analysis (1) vision-language alignment (1) sequence prediction (1) action prediction (1) visual question answering (1) language model (1) quality score prediction (1) reinforcement learning (1) vision encoder (1) mutual learning (1) reasoning capability (1) instructional video (1) scene text recognition (1) sequence modeling (1)