Author name: Che Liu, Lichao Ma, Xiangyu Tony Zhang, Yuxin Zhang, Haoyang Zhang, Xuerui Yang, Fei Tian

arXiv:2605.12034v2 Announce Type: replace-cross
Abstract: Omni-modal language models are intended to jointly understand audio, visual inputs, and language, but benchmark gains can be inflated when visual evidence alone is enough to answer a query. We …

arXiv:2605.12034v1 Announce Type: cross
Abstract: Omni-modal language models are intended to jointly understand audio, visual inputs, and language, but benchmark gains can be inflated when visual evidence alone is enough to answer a query. We study wh…