Ahmed Mohammad Dabeer, Ahn Jeongmi, Anocha Sutaveephamochanon, Antonyrex Sajeban, Aulia Adila, Chan Hok Teng, Adwin, Cheng Zi Yi, Nicholas Zhuang Ziyi, Choa Hsueh Mei Esther, David Ong Tat-Wee, Evelyn Tan Chor Phin, Heng Cheng Peng, Jonathan, Lee Chwan Ren, Leong Wai Yi, Leong Wei Qi, Leslie Teo Eng Sipp, Liew Rachel, Limkonchotiwat Peerat · arXiv (Cornell University) 2026 · 2026
DOI: 10.48550/arxiv.2609.18310
Counts differ because each database indexes a different set of publications. We treat OpenAlex as the canonical count; Google Scholar is not shown (no API, and crawling it violates its ToS).
We introduce Nemotron-SEA-LION-v4.8, a family of Southeast Asian Languages in One Network (SEA-LION) built upon NVIDIA Nemotron 3. The family includes 30B-A3B and 120B-A12B models, with both continued-pretrained base checkpoints and post-trained variants. We adapt the models using Southeast Asian, reasoning, code, and multilingual parallel datasets, followed by post-training with supervised fine-tuning and online on-policy distillation. On SEA-HELM, the 30B-A3B model improves the overall SEA score from 46.06 to 51.57, while the 120B-A12B model improves from 49.30 to 63.44. The strongest gains are observed in instruction following, natural language reasoning, and natural language understanding across seven Southeast Asian languages.
No comments yet — start the discussion below.