An Empirical Study of VLM Pipelines for Long-Document QA
Vision-Language Models (VLMs) are increasingly used for long-document processing, where the inputs combine text with charts, tables, figures, and complex layouts. Deploying them means choosing how to feed the document to the model, which retriever to use when only a subset of pages is sent, and whether to run the model...
K. E. Ak, Jay Mohta, Gwang Lee et al.
· 0 citations