Research map / Vision-language and multimodal / Visual question answering
MultiModalQA: complex question answering over text, tables and images
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use implicit two-hop decomposition with intermediate answers instead of single-hop modality routing | MMQA QA · MMQA test, Multi Modality | F1: 38.2 -> 51.7 | Helped |
| Use implicit two-hop decomposition with intermediate answers instead of single-hop modality routing | MMQA QA · MMQA test, Single Modality | F1: 57.1 -> 58.8 | Helped |
| Use implicit two-hop decomposition with intermediate answers instead of single-hop modality routing | MMQA QA · MMQA test, All | F1: 49.5 -> 55.9 | Helped |
| Require the first-hop answer to be correct | ImplicitDecomp · MMQA test, compositional multimodal questions | F1: 37.4 -> 63.9 | Helped |
Closest papers by meaning
- SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers (NeurIPS 2024 · similarity 0.90)
- Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering (NeurIPS 2025 · similarity 0.89)
- SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs (ICML 2025 · similarity 0.89)
- Benchmarking Multimodal Retrieval Augmented Generation with Dynamic VQA Dataset and Self-adaptive Planning Agent (ICLR 2025 · similarity 0.89)
- VTQA: Visual Text Question Answering via Entity Alignment and Cross-Media Reasoning (CVPR 2024 · similarity 0.89)
- Evaluating Cross-Modal Reasoning Ability and Problem Charactaristics with Multimodal Item Response Theory (ICLR 2026 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.