4 papers
Up to 36x Speedup: Mask-based Parallel Inference Paradigm for Key Information Extraction in MLLMs
Xinzhong Wang, Ya Guo, Jing Li +5
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)…
Keep the General, Inject the Specific: Structured Dialogue Fine-Tuning for Knowledge Injection without Catastrophic Forgetting
Yijie Hong, Xiaofei Yin, Xinzhong Wang +7
Large Vision Language Models have demonstrated impressive versatile capabilities through extensive multimodal pre-training, but face significant limitations when incorporating spec…
InsightVision: A Comprehensive, Multi-Level Chinese-based Benchmark for Evaluating Implicit Visual Semantics in Large Vision Language Models
Xiaofei Yin, Yijie Hong, Ya Guo +4
In the evolving landscape of multimodal language models, understanding the nuanced meanings conveyed through visual cues - such as satire, insult, or critique - remains a significa…
Modeling Layout Reading Order as Ordering Relations for Visually-rich Document Understanding
Chong Zhang, Yi Tu, Yixi Zhao +8
Modeling and leveraging layout reading order in visually-rich documents (VrDs) is critical in document intelligence as it captures the rich structure semantics within documents. Pr…