Wenhui Liao

document understanding (2) attention mechanism (1) multimodal learning (1) multi-modal learning (1) efficient computing (1) multi-modal large language model (1) multimodal large language model (1) feed-forward network (1) inference acceleration (1) visual token (1) entity typing (1) optical character recognition (1) decoder-only architecture (1) large language model (1) visually-rich document (1) semantic entity recognition (1) multi-modal pre-trained model (1) computational redundancy (1) text-rich document understanding (1) multimodal document understanding (1)