Scaling Vison-Language Foundation Model to 12 Billion Parameters in Baidu Dynamic Image Advertising.

Xinyu Zhao|Kang Zhao|Zhipeng Jin|Yi Yang|Wen Tao|Xiaodong Chen|Cong Han|Shuanglong Li|Lin Liu


Anthology ID:DBLP:conf/cikm/ZhaoZJ0TCHLL24
Volume:Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, CIKM 2024, Boise, ID, USA, October 21-25, 2024
Year:2024
Venue:International Conference on Information and Knowledge Management (CIKM)
Publisher:ACM
Pages:5102-5110
URL:https://doi.org/10.1145/3627673.3680014
DOI:https://doi.org/10.1145/3627673.3680014
DBLP:conf/cikm/ZhaoZJ0TCHLL24
BibTeX:
@inproceedings{zhao-2024-scaling, author = {Xinyu Zhao and Kang Zhao and Zhipeng Jin and Yi Yang and Wen Tao and Xiaodong Chen and Cong Han and Shuanglong Li and Lin Liu}, editor = {Edoardo Serra and Francesca Spezzano}, title = {{Scaling Vison-Language Foundation Model to 12 Billion Parameters in Baidu Dynamic Image Advertising}}, booktitle = {{Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, CIKM 2024, Boise, ID, USA, October 21-25, 2024}}, pages = {5102--5110}, publisher = {ACM}, year = {2024}, url = {https://doi.org/10.1145/3627673.3680014}, doi = {https://doi.org/10.1145/3627673.3680014} }