Papers by Hikaru Ikuta

1 papers
MangaVQA and MangaLMM: A Benchmark and Specialized Model for Multimodal Manga Understanding (2026.findings-eacl)

Copied to clipboard

Challenge: Manga is a richly multimodal narrative form that blends images and text in complex ways.
Approach: They propose two benchmarks for multimodal manga understanding: mangaOCR and mangaVQA . mangaVQ consists of 526 high-quality, manually constructed question-answer pairs .
Outcome: The proposed model is finetuned from the open-source LMM Qwen2.5-VL . it compares with proprietary models such as GPT-4o and Gemini 2.5 to evaluate its performance .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations