AI Paper Atlas

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

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Multimodal LLM benchmarks · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
fine-tune LLaVA on Museum-65LLaVA · Museum-65 title attributeaccuracy: 10.13 -> 57.00Improved
fine-tune LLaVA on Museum-65LLaVA · Museum-65 place attributeaccuracy: 23.42 -> 70.00Improved
fine-tune BLIP on Museum-65BLIP · Museum-65 title attributeaccuracy: 3.00 -> 52.00Improved
fine-tune LLaVA on Museum-65 vs zero-shot GPT-4oGPT-4o · Museum-65 place attributeaccuracy: 33.33 -> 70.00Improved
fine-tune LLaVA on Museum-65LLaVA · Museum-65 semantic evalMETEOR: 2.96 -> 58.85Improved
fine-tune BLIP on Museum-65BLIP · Museum-65 semantic evalWMD top-1 accuracy: 35.54 -> 74.02Improved
use alternative viewpoint images instead of originalLLaVA20mn-1ep · MultiAnglepartial precision: 58.09 -> 56.14No clear effect
fine-tune LLaVA on Museum-65LLaVA · Visually Unanswerable Questions (test)complete precision: 1.55 -> 25.83Improved
fine-tune BLIP on Museum-65BLIP · Visually Unanswerable Questions (test)partial precision: 5.44 -> 3.3Hurt
fine-tune LLaVA on English-only Museum-65LLaVA · Multi-language (French)partial precision: 41.81 -> 10.37Hurt
fine-tune LLaVA on Museum-65LLaVA · Continent-wise (Asia)partial precision: 23.4 -> 67.4Improved
fine-tune LLaVA on Museum-65LLaVA · Continent-wise (Oceania)partial precision: 52.4 -> 99.2Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy