作者位次 #2/6ACL 2026Findings· Findings of ACL
C omic VQA : A Benchmark for Visual Reasoning in Multimodal LLM s
Esther Gan · Hannah Brown · David Herel · Kenji Kawaguchi · Min-Yen Kan · Michael Qizhe Shieh
摘要
We introduce Comic Visual Question Answering ( ComicVQA ), a comics-based benchmark for evaluating MLLMs on visual reasoning. ComicVQA comprises of (i) Missing Panel Prediction , testing fine-grained visual grounding and (ii) Panel Sorting , which evaluates sequential narrative understanding. Pro...