Michele LaurelliBlog

Vision-language model (VLM)

Vision-language model (VLM): A model that jointly processes images and language to understand or generate multimodal content. A visual encoder connects to language components through shared representations or adapters. Capabilities vary across description, answering and generation and require vision-specific evaluation.

In italiano: Vision-Language Model (VLM)Legge II · Probabilità, softmax e modelli generativi

A visual encoder connects to language components through shared representations or adapters. Capabilities vary across description, answering and generation and require vision-specific evaluation.

Examples

  • Visual question answering
  • Image description
  • Scanned document analysis