multimodal-question-answering

Collaborative research exploring multimodal question answering using OCR, RAG, and document/image understanding techniques.

For the work on "MemeMQA: Multimodal Question Answering for Memes via Rationale-Based Inferencing"

Quasar PoC, Multitenant PoC.

(IJCNLP-AACL 2025) MAMMQA: Rethinking Information Synthesis in Multimodal Question Answering from a Multi-Agent Perspective

MMTabReal is a benchmark suite for multimodal table reasoning on real-world tables with mixed text, images, charts, maps, and visual encodings. It includes curated QA pairs, baseline implementations, and evaluation scripts for multimodal table understanding research.