KAIST develops CONDA, a dynamic vector search technique that maintains accuracy as data changes
Original article in KoreanKAIST, 데이터 변화해도 검색 정확도 유지하는 ‘CONDA’ 기술 개발
- Outlet
- AI Times
- Published
- Importance
- 4/5
Summary
KAIST researchers developed CONDA, a dynamic vector search technology that maintains high retrieval accuracy in environments where data is continuously added and deleted. The technique addresses the challenge of generative AI accessing new information it has not seen during training.
#rag
Read the originalaitimes.com · in Korean