MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding
Paper
•
2505.20298
•
Published
•
9
Jeonghun Baek
ku21fan
AI & ML interests
Computer vision, Text recognition
Recent Activity
liked
a Space
19 days ago
JMMMU/JMMMU-Pro_Leaderboard
liked
a dataset
19 days ago
JMMMU/JMMMU-Pro
updated
a dataset
2 months ago
hal-utokyo/Manga109
Organizations
upvoted
a
paper
7 months ago