AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MultiVerse: A Multi-Turn Conversation Benchmark for Evaluating Large Vision and Language Models

Young-Jun Lee, Byung-Kwan Lee, Jianshu Zhang, Yechan Hwang, Byungsoo Ko, Han-Gyu Kim, Dongyu Yao, Xuankun Rong, Eojin Joo, Seung-Ho Han, Bowon Ko, Ho-Jin Choi

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 10 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
use ground-truth (Oracle) dialogue history instead of self-generated historyQwen2.5-VL-72B · MultiVersegap vs Self-Prediction: -44.64Improved
use ground-truth (Oracle) dialogue history instead of self-generated historyQwen2.5-VL-7B · MultiVersegap vs Self-Prediction: -30.44Improved
provide more interaction turns of golden historyInternVL2.5-2B · MultiVerse (Oracle)checklist x quality score: 17.79 -> 34.32Improved
provide more interaction turns of golden historyLLaVA-1.5-7B · MultiVerse (Oracle)checklist x quality score: 9.10 -> 31.81Improved
provide more interaction turns of golden historyQwen2.5-VL-72B · MultiVerse (Oracle)checklist x quality score: 52.05 -> 46.19Hurt
provide more interaction turns of golden historyClaude-3.5-Sonnet · MultiVerse (Oracle)checklist x quality score: 46.60 -> 45.00No clear effect
provide more interaction turns of golden historyGPT-4o · MultiVerse (Oracle)checklist x quality score: 48.56 -> 49.12No clear effect
scale Qwen2.5-VL from 7B to 72BQwen2.5-VL · MultiVerse (Oracle)checklist x quality score: 48.15 -> 47.95No clear effect
scale Qwen2.5-VL from 7B to 72BQwen2.5-VL · MultiVerse (Oracle, goal: calculation)checklist x quality score: 44.86 -> 47.15Improved
scale Qwen2.5-VL from 7B to 72BQwen2.5-VL · MultiVerse (Oracle, goal: creation)checklist x quality score: 44.45 -> 39.82Hurt
scale InternVL2.5 from 1B to 4BInternVL2.5 · MultiVerse (Oracle)checklist x quality score: 21.22 -> 35.66Improved
scale LLaMA-3.2-Vision from 11B to 90BLLaMA-3.2-Vision · MultiVerse (Oracle)checklist x quality score: 21.61 -> 35.78Improved

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