preference optimization 3편

• DT-Guard 가드레일 · 안전 26.10.09
• Demystifying Domain-adaptive Post-training for Financial LLMs LLM 학습 · 효율화 26.05.25
• Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment 멀티모달 임베딩 · 검색 25.11.29

전체 태그 보기