AI RESEARCH
Making Dialogue Grounding Data Rich: A Three-Tier Data Synthesis Framework for Generalized Referring Expression Comprehension
arXiv CS.CL
•
ArXi:2512.02791v2 Announce Type: replace Dialogue-Based Generalized Referring Expression Comprehension (GREC) requires models to ground the expression and unlimited targets in complex visual scenes while resolving coreference across a long dialogue context. However, existing systems struggle under distribution shift between