MDPO:Conditional Preference Optimization for Multimodal Large Language Models
MDPO: Conditional Preference Optimization for Multimodal Large Language Models 相关链接:arxiv 关键字:多模态、大型语言模型、偏好优化、条件偏好优化、幻觉减少 摘要 直接偏好优化(DPO)已被证明是大型语言模型(…
2025-10-20