AI RESEARCH
InstructTable: Improving Table Structure Recognition Through Instructions
arXiv CS.CV
•
ArXi:2604.02880v1 Announce Type: new Table structure recognition (TSR) holds widespread practical importance by parsing tabular images into structured representations, yet encounters significant challenges when processing complex layouts involving merged or empty cells. Traditional visual-centric models rely exclusively on visual information while lacking crucial semantic, thereby impeding accurate structural recognition in complex scenarios.