AI RESEARCH
HanMoVLM: Large Vision-Language Models for Professional Artistic Painting Evaluation
arXiv CS.CV
•
ArXi:2603.10814v1 Announce Type: new While Large Vision-Language Models (VLMs) nstrate impressive general visual capabilities, they remain artistically blind and unable to offer professional evaluation of artworks within specific artistic domains like human experts. To bridge this gap, we transform VLMs into experts capable of professional-grade painting evaluation in the Chinese Artistic Domain, which is abstract and demands extensive artistic