开源成果

(2024). CONSTRUCTURE: Benchmarking CONcept STRUCTUre REasoning for Multimodal Large Language Models. In EMNLP.

PDF Cite Dataset

(2024). M2ConceptBase: The first concept-centric multimodal concept knowledge base. In CIKM.

PDF Cite Dataset

(2024). HOTVCOM: A large-scale Chinese short video comment dataset. In ACL.

PDF Cite Dataset

(2024). ESC-Eval: Evaluate LLMs in Emotion Support Dialogue. In EMNLP.

PDF Cite Dataset

(2024). Flickr30K-CFQ: Compact and Fragmented Query challenge dataset. In DASFAA.

PDF Cite Dataset

(2024). TalkFunny: An explainable humorous context-response dataset. In AAAI.

PDF Cite Dataset

(2023). XMQAs: A complex-modified question-answering dataset. In TKDE.

PDF Cite Dataset

(2023). A comprehensive Chinese humor understanding dataset. In WSDM.

PDF Cite Dataset

(2022). ClidSum: Cross-Lingual Dialogue Summarization dataset. In EMNLP.

PDF Cite Dataset

(2022). WidiDiverse: A Multimodal Entity Linking dataset. In ACL.

PDF Cite Dataset