AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

MoAI: Mixture of All Intelligence for Large Language and Vision Models

Byung-Kwan Lee, Beomchan Park, Chae Won Kim, Yong Man Ro

ECCV 2024 · Vision-language and multimodal › Multimodal LLMs · approach: Instruction-tuned multimodal assistants · 32 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 panoptic segmentation and open-world detection outputs (ablation)MoAI · MME Existencescore: 187 -> 200Improved
add scene graph generation outputs (ablation)MoAI · MME Positionscore: 145 -> 165Improved
add OCR model outputs (ablation)MoAI · MM-Bench OCRaccuracy: 80.1 -> 93.5Improved
combine both training steps instead of the first only (ablation)MoAI · MME-Pscore: 1542 -> 1714Improved
use top-3 experts instead of top-1 (ablation)MoAI-Mixer · MME-Pscore: 1588 -> 1714Improved
train gating network instead of uniform weights (ablation)MoAI-Mixer · MME-Pscore: 1617 -> 1714Improved
add bounding boxes and segmentation map together (ablation)MoAI · MM-Bench Localizationaccuracy: 55.2 -> 71.1Improved
add auxiliary CV information to other LLVMsLLaVA1.5-7B · MM-Benchaccuracy: 64.3 -> 79.1Improved
add auxiliary CV information to other LLVMsQwen-VL-Chat-7B · TextVQAaccuracy: 63.8 -> 69.2Improved
increase number of detection categories from 0 to 1847 (ablation)MoAI · MM-Benchaccuracy: 65.9 -> 79.3Improved
MoAI versus larger CogVLM-17BMoAI-7B · MM-Vetscore: 43.7 vs 54.5Hurt

Later papers that compared with this method

1 later accepted paper reports MoAI-7B as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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