Longxu Dou

A new method improves the selection of data mixtures for language model training.

2025-07-21T18:25:30+00:00 ― 5 min read

Discover how vocabulary size influences the performance of large language models.

2025-07-11T02:04:12+00:00 ― 6 min read

SailCompass evaluates LLM performance for Southeast Asian languages, promoting language technology growth.

2025-04-22T19:27:30+00:00 ― 5 min read

Exploring the rise of AI in decision-making and social interactions.

2025-04-09T10:55:39+00:00 ― 6 min read