作者位次 #6/8ACL 2026Poster· Natural Language Processing
Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni- LLM s
Hongcheng Liu · Yuhao Wang · Zhe Chen · Pingjie Wang · Zhiyuan Zhu · Yixuan Hou · Yanfeng Wang · Yu Wang
摘要
Omni Large Language Models (Omni-LLMs) have demonstrated impressive capabilities in holistic multi-modal perception, yet they consistently falter in complex scenarios requiring synergistic omni-modal reasoning. Beyond understanding global multimodal context, effective reasoning also hinges on fin...