🚀 SEA-VL Phase 2 (Anthropogenic Regional Adaptation in Multimodal Vision-Language Model) is now available on arXiv!
📄 Paper: arxiv.org/abs/2604.11490
🔗 Project page: seacrowd.org/projects/202...
Reminder: Mentee registration is still OPEN for the second batch!
If you’ve been thinking about doing real AI/ML/NLP research with mentors — this is your sign to apply. (Deadline for application - Dec 17th)
Apply here: seacrowd.org/apprenticesh...
🌏 Applications are now open for the SEACrowd Apprentice Program 2026!
🗓️ Apply between Nov 17 – Dec 17, 2025 (UTC-12)
📅 Program runs Feb – Jun 2026
seacrowd.org/apprenticeship
★ Extensions to image generation and embedding models for SEA contexts
★ 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.
While the field of vision-language (VL) has achieved remarkable success in integrating visual and textual information across multiple languages and domains, there is still no dedicated framework for a...