#computer vision
Jan 2026
AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
AVMeme Exam, a human-curated benchmark of over one thousand iconic Internet sounds and videos spanning speech, songs, music, and sound effects, is introduced, showing current models perform poorly on textless music and sound effects, and struggle to think in context and in culture compared to surface content.
Xi-Lin Jiang, Qiao-Lin Wang, Junkai Wu et al.
· arXiv.org · 4 citations