AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

Uni-MoE: Scaling Unified Multimodal LLMs With Mixture of Experts

Yunxin Li, Shenyuan Jiang, Baotian Hu, Longyue Wang, Wanqi Zhong, Wenhan Luo, Lin Ma, Min Zhang

TPAMI 2025 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 136 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
activate top-2 experts instead of top-1 (ablation)Uni-MoE · RACE-Audio middleaccuracy: 45.13% -> 46.31%Improved
use 4 experts instead of 1 (ablation)Uni-MoE · OK-VQAaccuracy: 56.12% -> 63.02%Improved
use 4 experts instead of 2 (ablation)Uni-MoE · RACE-Audio middleaccuracy: 44.64% -> 46.31%Improved
add more identical experts (6 instead of 1) to pure MoE (ablation)Pure MoE · ActivityNet-QAaccuracy: 42.5% -> 43.2%No clear effect
apply MoE to all layers instead of interval layout (ablation)Uni-MoE · ActivityNet-QAaccuracy: 43.3% -> 42.8%Hurt
apply MoE only to second half of layers instead of all layers (ablation)Uni-MoE · RACE-Audio highaccuracy: 43.71% -> 52.69%Improved
pre-tune modality-specific experts (tri-phase training) instead of identical LLaVA experts (ablation)Uni-MoE · avg of 5 benchmarksaverage accuracy: 47.5% -> 49.2%Improved
add auxiliary balancing loss to mixture(4) experts (ablation)Uni-MoE · avg of 5 benchmarksaverage accuracy: 49.2% -> 48.5%Hurt
add auxiliary balancing loss to pure(4) experts (ablation)Pure MoE · avg of 5 benchmarksaverage accuracy: 47.5% -> 48.4%Improved
use pure(4) MoE instead of single dense expert (LLaVA experts) (ablation)Pure MoE · avg of 5 benchmarksaverage accuracy: 48.2% -> 47.5%No clear effect
use pure(4) MoE instead of single dense expert (LLaMA experts) (ablation)Pure MoE · avg of 5 benchmarksaverage accuracy: 46.5% -> 47.3%Improved
expand image-text data from LLaVA-150k to LLaVA-v1.5-665kUni-MoE (4E) · MMBenchaccuracy: 69.82% -> 73.2%Improved

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