Venkata Kesav Venna

M3Grounder: Mask-Based Multi-Span and Multi-Granular Grounding for Document QA

**Document QA** requires not only accurate answers but also identifying where each answer is grounded on the page. Most models treat the task as text-only generation, while existing answer grounding methods generate coarse bounding boxes that fail to capture curved text. We introduce **M3Grounder, a