CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation
This story is from 2026-09-09. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.05518v1 Announce Type: new Abstract: Despite the strong capabilities of multimodal large language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, motivating multimodal retrieval-augmented generation (RAG) to ground responses in external text and ima…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-09-09 04:00 · arXiv cs.CV
CrossModalQA: A Cross-modal and Multi-hop Benchmark for Multimodal Retrieval-augmented Generation