An Integrated Data Processing Framework for Pretraining Foundation Models.

@inproceedings{sun-2024-integrated, author = {Yiding Sun and Feng Wang and Yutao Zhu and Wayne Xin Zhao and Jiaxin Mao}, editor = {Grace Hui Yang and Hongning Wang and Sam Han and Claudia Hauff and Guido Zuccon and Yi Zhang}, title = {{An Integrated Data Processing Framework for Pretraining Foundation Models}}, booktitle = {{Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2024, Washington DC, USA, July 14-18, 2024}}, pages = {2713--2718}, publisher = {ACM}, year = {2024}, url = {https://doi.org/10.1145/3626772.3657671}, doi = {https://doi.org/10.1145/3626772.3657671} }