AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

OURO: A Self-Bootstrapped Framework for Enhancing Multimodal Scene Understanding

Tianrun Xu, Guanyu Chen, Ye Li, Yuxin Xi, Zeyu Mu, Ruichen Wang, Tianren Zhang, Haichuan Gao, Feng Chen

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 0 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
add 5 training sub-regions instead of none (ablation)OURO-7B · Average over 10 VQA benchmarksaverage accuracy: 77.3 -> 80.0Improved
add 1 random sub-region instead of none (ablation)OURO-7B · Average over 10 VQA benchmarksaverage accuracy: 77.3 -> 74.0Hurt
add 2 sub-regions instead of none (ablation)OURO-7B · Average over 10 VQA benchmarksaverage accuracy: 77.3 -> 78.8Improved
add 3 sub-regions instead of none (ablation)OURO-7B · Average over 10 VQA benchmarksaverage accuracy: 77.3 -> 78.7Improved
increase sub-regions from 5 to 7 (ablation)OURO-7B · Average over 10 VQA benchmarksaverage accuracy: 80.0 -> 75.6Hurt
use enhanced self-bootstrapped annotations instead of original (k=3) (ablation)OURO-7B · VQAv2accuracy: 72.3 -> 79.9Improved
use enhanced annotations instead of original (k=3) (ablation)OURO-7B · AI2Daccuracy: 66.0 -> 86.5Improved
use enhanced annotations instead of original (k=3) (ablation)OURO-7B · OKVQAaccuracy: 58.4 -> 65.9Improved
use enhanced annotations instead of original (k=5) (ablation)OURO-7B · ChartQAaccuracy: 80.2 -> 84.1Improved
use enhanced annotations instead of original (k=5) (ablation)OURO-7B · STVQAaccuracy: 72.8 -> 77.0Improved
use enhanced annotations instead of original (k=5) (ablation)OURO-7B · AI2Daccuracy: 85.9 -> 80.2Hurt
use enhanced annotations instead of original (k=5) (ablation)OURO-7B · OKVQAaccuracy: 66.2 -> 66.2No clear effect

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