Liquid AI releases d1-3B, a 3.12B multimodal decision model outperforming 10x larger models
Original article in Korean리퀴드 AI, 10배 큰 체급 제친 멀티모달 의사결정 모델 ‘d1-3B’ 출시
- Outlet
- AI Times
- Published
- Importance
- 4/5
Summary
Liquid AI released d1-3B and d1-Omni-600M, multimodal decision models that compute input states once to return immediate decision scores instead of generating tokens sequentially. The 3.12 billion parameter d1-3B outperforms models 10 times its size.