M2-VLP: Enhancing Multilingual Vision-Language Pre-Training via Multi-Grained Alignment.

@inproceedings{ahmat-2025-m2vlp, author = {Ahtamjan Ahmat and Lei Wang and Yating Yang and Bo Ma and Rui Dong and Kaiwen Lu and Rong Ma and Xinyue Wang}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{M2-VLP: Enhancing Multilingual Vision-Language Pre-Training via Multi-Grained Alignment}}, booktitle = {{Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025- 2 May 2025}}, pages = {3438--3450}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3696410.3714861}, doi = {https://doi.org/10.1145/3696410.3714861} }