Advancing Southeast Asian (SEA) NLP Research
https://seacrowd.github.io/
SEACrowd
Loading...
β Extensions to image generation and embedding models for SEA contexts
β Evaluation across translated and region-specific multimodal benchmarks
This work is made possible by the amazing SEACrowd community, bringing together contributors across languages, cultures, and domains.
Weβre happy to share our latest work on SEA-VL Phase 2, continuing our effort to build language systems tailored for Southeast Asian languages and cultures.
β SEA-adapted vision-language models (SEA-VLM) built on strong foundation models
β Multilingual and culturally grounded instructiontuning data