Task-Specific Information Decomposition for End-to-End Dense Video Captioning ACL

Zhiyue Liu | Xinru Zhang | Jinyuan Liu |

From Complex Word Identification to Substitution: Instruction-Tuned Language Models for Lexical Simplification *SEM

Tonghui Han | Xinru Zhang | Yaxin Bi | Maurice D. Mulvenna | Dongqiang Yang |

Dual-Path Dynamic Fusion with Learnable Query for Multimodal Sentiment Analysis EMNLP

Miao Zhou | Lina Yang | Thomas Wu | Dongnan Yang | Xinru Zhang |