For SEA, by SEA
We are a research community dedicated to advance Southeast Asian-focused AI and empower the next generation of SEA AI researchers. We’re building towards a future in which AI ecosystems in Southeast Asia are mature and competitive with the rest of the world, and the people in SEA can use world-class AI in their own linguistic and cultural context.
To advance Southeast Asian-focused AI and empower the next generation of SEA AI researchers.
Our current efforts are focused on:
Learn more about our projects.
We have an active community of over 400 people on Discord. Please join us if you share our interests! Our datasets and code can be found on Github and HuggingFace.
May 8, 2025
Welcome! SEA-VL is a global community project organized by the SEACrowd community to push the boundaries of vision and language research in Southeast Asia (SEA). We recently completed Phase 1 of this project with the release of high-quality, culturally relevant image datasets and a benchmarking study for SEA languages, as detailed in this paper.
March 14, 2025
We’re excited to announce a major milestone from the SEACrowd team—the launch of SEA-VL, the largest open-source vision-language (VL) dataset specifically designed to represent the cultural diversity of Southeast Asia 🇧🇳🇰🇭🇹🇱🇮🇩🇱🇦🇲🇾🇲🇲🇵🇭🇸🇬🇹🇭🇻🇳.
November 9, 2024
Following the success of our SEACrowd project, we’re excited to announce SEA-VL, a new open-source initiative to create high-quality vision-language datasets specifically for Southeast Asian (SEA) languages! We’re calling on contributors to help us build a SEA-specific vision-language model.
September 23, 2024
🎉 Exciting news! SEACrowd’s very first publication has been accepted at EMNLP 2024! 🚀
August 22, 2024
Today, SEACrowd has formed a legal entity in Indonesia. 🇮🇩
