@inproceedings{nakamura-etal-2025-aurora, title = "Aurora-{M}: Open Source Continual Pre-training for Multilingual Language and Code", author = "Nakamura, Taishi and Mishra, Mayank and Tedeschi, Simone and Chai, Yekun and Stillerman, Jason T. and Friedrich, Felix and Yadav, Prateek and Laud, Tanmay and Chien, Vu Minh and Zhuo, Terry Yue and Misra, Diganta and Bogin, Ben and Vu, Xuan-Son and Karpinska, Marzena and Dantuluri, Arnav Varma and Kusa, Wojciech and Furlanello, Tommaso and Yokota, Rio and Muennighoff, Niklas and Pai, Suhas and Adewumi, Tosin and Laippala, Veronika and Yao, Xiaozhe and Junior, Adalberto Barbosa and Drozd, Aleksandr and Clive, Jordan and Gupta, Kshitij and Chen, Liangyu and Sun, Qi and Tsui, Ken and Moustafa-Fahmy, Nour and Monti, Nicolo and Dang, Tai and Luo, Ziyang and Bui, Tien-Tung and Navigli, Roberto and Mehta, Virendra and Blumberg, Matthew and May, Victor and Nguyen, Hiep and Pyysalo, Sampo", editor = "Rambow, Owen and Wanner, Leo and Apidianaki, Marianna and Al-Khalifa, Hend and Eugenio, Barbara Di and Schockaert, Steven and Darwish, Kareem and Agarwal, Apoorv", booktitle = "Proceedings of the 31st International Conference on Computational Linguistics: Industry Track", month = jan, year = "2025", address = "Abu Dhabi, UAE", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2025.coling-industry.56/", pages = "656--678" }