作者位次 #4/6CVPR 2026Poster· Computer Vision & Pattern Recognition
M3Grounder: Mask-Based Multi-Span and Multi-Granular Grounding for Document QA
Venkata Kesav Venna · Sai Madhusudan Gunda · Jyothi Swaroopa Jinka · Hrithik Sagar Rachakonda · Anirudh Srinivasan · Ravi Kiran Sarvadevabhatla
多模态OpenReview 项目页