一作ICLR 2026Poster· Computer Vision / Vision Models & Multimodal
ThinkOmni: Lifting Textual Reasoning to Omni-modal Scenarios via Guidance Decoding
Yiran Guan · Sifan Tu · Dingkang Liang · Linghao Zhu · Jianzhong Ju · Zhenbo Luo · Jian Luan · Yuliang Liu · Xiang Bai