AI RESEARCH

YARD: Y-Architecture Register Decoding for Efficient Hallucination Mitigation in Large Vision-Language Models

arXiv CS.CV

ArXi:2605.31429v1 Announce Type: new Contrastive decoding (CD) seeks to mitigate hallucinations in Large Vision-Language Models (LVLMs) by contrasting the output distributions of a standard model and a visually degraded model. However, existing