3 papers
cs.CV2025
DocLayLLM: An Efficient Multi-modal Extension of Large Language Models for Text-rich Document Understanding
Wenhui Liao, Jiapeng Wang, Hongliang Li +3
Text-rich document understanding (TDU) requires comprehensive analysis of documents containing substantial textual content and complex layouts. While Multimodal Large Language Mode…
cs.CL2024
PEneo: Unifying Line Extraction, Line Grouping, and Entity Linking for End-to-end Document Pair Extraction
Zening Lin, Jiapeng Wang, Teng Li +4
Document pair extraction aims to identify key and value entities as well as their relationships from visually-rich documents. Most existing methods divide it into two separate task…
cs.CL2024
VideoCLIP-XL: Advancing Long Description Understanding for Video CLIP Models
Jiapeng Wang, Chengyu Wang, Kunzhe Huang +2
Contrastive Language-Image Pre-training (CLIP) has been widely studied and applied in numerous applications. However, the emphasis on brief summary texts during pre-training preven…