Xiao Xu 0005, Bei Li, Chenfei Wu, Shao-Yen Tseng, Anahita Bhiwandiwalla, Shachar Rosenman, Vasudev Lal, Wanxiang Che, Nan Duan. ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning. In Anna Rogers, Jordan L. Boyd-Graber, Naoaki Okazaki, editors, Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023. pages 14507-14525, Association for Computational Linguistics, 2023. [doi]
@inproceedings{0005LWTBRLCD23, title = {ManagerTower: Aggregating the Insights of Uni-Modal Experts for Vision-Language Representation Learning}, author = {Xiao Xu 0005 and Bei Li and Chenfei Wu and Shao-Yen Tseng and Anahita Bhiwandiwalla and Shachar Rosenman and Vasudev Lal and Wanxiang Che and Nan Duan}, year = {2023}, url = {https://aclanthology.org/2023.acl-long.811}, researchr = {https://researchr.org/publication/0005LWTBRLCD23}, cites = {0}, citedby = {0}, pages = {14507-14525}, booktitle = {Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2023, Toronto, Canada, July 9-14, 2023}, editor = {Anna Rogers and Jordan L. Boyd-Graber and Naoaki Okazaki}, publisher = {Association for Computational Linguistics}, isbn = {978-1-959429-72-2}, }