VHELM: A Holistic Evaluation of Vision Language Models Tony Lee 1 Haoqin T u 2 Chi Heem Wong

Neural Information Processing Systems 

Our framework is designed to be lightweight and automatic so that evaluation runs are cheap and fast. Our initial run evaluates 22 VLMs on 21 existing datasets to provide a holistic snapshot of the models. We uncover new key findings, such as the fact that efficiency-focused models (e.g., Claude 3 Haiku or Gemini 1.5 Flash) perform significantly

Similar Docs  Excel Report  more

TitleSimilaritySource
None found