Research map / Vision-language and multimodal / Multimodal LLMs
Understanding Museum Exhibits using Vision-Language Reasoning
Ada-Astrid Balauca, Sanjana Garai, Stefan Balauca, Rasesh Udayakumar Shetty, Naitik Agrawal, Dhwanil Subhashbhai Shah, Yuqian Fu, Xi Wang, Kristina Toutanova, Danda Pani Paudel, Luc Van Gool
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| fine-tune LLaVA on Museum-65 | LLaVA · Museum-65 title attribute | accuracy: 10.13 -> 57.00 | Improved |
| fine-tune LLaVA on Museum-65 | LLaVA · Museum-65 place attribute | accuracy: 23.42 -> 70.00 | Improved |
| fine-tune BLIP on Museum-65 | BLIP · Museum-65 title attribute | accuracy: 3.00 -> 52.00 | Improved |
| fine-tune LLaVA on Museum-65 vs zero-shot GPT-4o | GPT-4o · Museum-65 place attribute | accuracy: 33.33 -> 70.00 | Improved |
| fine-tune LLaVA on Museum-65 | LLaVA · Museum-65 semantic eval | METEOR: 2.96 -> 58.85 | Improved |
| fine-tune BLIP on Museum-65 | BLIP · Museum-65 semantic eval | WMD top-1 accuracy: 35.54 -> 74.02 | Improved |
| use alternative viewpoint images instead of original | LLaVA20mn-1ep · MultiAngle | partial precision: 58.09 -> 56.14 | No clear effect |
| fine-tune LLaVA on Museum-65 | LLaVA · Visually Unanswerable Questions (test) | complete precision: 1.55 -> 25.83 | Improved |
| fine-tune BLIP on Museum-65 | BLIP · Visually Unanswerable Questions (test) | partial precision: 5.44 -> 3.3 | Hurt |
| fine-tune LLaVA on English-only Museum-65 | LLaVA · Multi-language (French) | partial precision: 41.81 -> 10.37 | Hurt |
| fine-tune LLaVA on Museum-65 | LLaVA · Continent-wise (Asia) | partial precision: 23.4 -> 67.4 | Improved |
| fine-tune LLaVA on Museum-65 | LLaVA · Continent-wise (Oceania) | partial precision: 52.4 -> 99.2 | Improved |
Closest papers by meaning
- VaseVQA-3D: Benchmarking 3D VLMs on Ancient Greek Pottery (ICLR 2026 · similarity 0.86)
- ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models (NeurIPS 2025 · similarity 0.85)
- Beyond Aesthetics: Cultural Competence in Text-to-Image Models (NeurIPS 2024 · similarity 0.84)
- Seeking and Updating with Live Visual Knowledge (NeurIPS 2025 · similarity 0.84)
- Same or Not? Enhancing Visual Perception in Vision-Language Models (CVPR 2026 · similarity 0.84)
- World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Models (CVPR 2026 · similarity 0.84)
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.
