Yijie Hong

UP TO 36X SPEEDUP: MASK-BASED PARALLEL INFERENCE PARADIGM FOR KEY INFORMATION EXTRACTION IN MLLMS

Key Information Extraction (KIE) from visually-rich documents (VrDs) is a critical task, for which recent Large Language Models (LLMs) and Multi-Modal Large Language Models (MLLMs) have demonstrated strong potential. However, their reliance on autoregressive inference, which generates outputs sequen…