P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization 文章

ArXiv CS.CV2026-06-04NEWSen作者: Ruipeng Zhang, Zhihao Li, Haozhang Yuan, C. L. Philip Chen, Tong Zhang
查看原文 →
关系图谱

P$^2$-DPO: Grounding Hallucination in Perceptual Processing via Calibration Direct Preference Optimization · 相关技术

相关技术

Perceptual Processing Direct Preference Optimization (P^2-DPO)Direct Preference OptimizationLarge vision-language model