CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence
Paper • 2605.12882 • Published • 274
huruo
huruo
·
AI & ML interests
data-centric ai & LLM reasoning (SFT/RL) & computer vision (det/mm)
Recent Activity
upvoted a paper about 1 month ago
CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligence upvoted a paper 3 months ago
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models updated a dataset 3 months ago
OpenDCAI/Infinity-Instruct-Curated-1MOrganizations
upvoted a paper about 1 month ago