SlideVQA

SlideVQA SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images 📖 arXiv 🌐 github We introduce a new document VQA dataset, SlideVQA, for tasks wherein given a slide deck composed of multiple slide images and a corresponding question, a system selects a set of evidence images and answers the ques

Papers using SlideVQA (3)

MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A2026Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models2026Quizzard@inova Challenge 2025 -- Track A: Plug-and-play Technique In Interleaved Multi-image Model2025