Booth 21-25 | AI Data Management Zone | Tokyo Big Sight
If you’ve worked on NLP for low-resource languages — Yoruba, Quechua, Tigrinya, Hmong — you know the math is brutal. Native speakers with domain expertise are scarce. Their time is
Most improvements to AI systems happen before deployment: better training data, better fine-tuning, better RLHF. Once the model is out in the world, you generally get the performance you trained for and nothing better. A paper from early 2026 takes a different approach. Instead of trying to bake everything into
