AI Paper Atlas

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

MLLM Enriched Explainable Multiple Clustering

Shan Zhang, Liangrui Ren, Qiaoyu Tan, Carlotta Domeniconi, Wei Du, Jun Wang, Guoxian Yu

AAAI 2026 · Vision-language and multimodal › Cross-modal learning · approach: Medical multimodal fusion · 1 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
fuse text and image features via cross-attention instead of image-only features (ablation)MLLMMC · COIL colorNMI: 0.025 -> 0.990Improved
fuse text and image features instead of image-only features (ablation)MLLMMC · CIFAR typeNMI: 0.008 -> 0.764Improved
fuse image features with text instead of text-only features (ablation)MLLMMC · Cards numberNMI: 0.359 -> 0.575Improved
fuse image features with text instead of text-only features (ablation)MLLMMC · CMUFace poseNMI: 0.097 -> 0.120Improved
use text-only features instead of image-only features (ablation)unimodal clustering · COIL colorNMI: 0.025 -> 0.951Improved
use text-only features instead of image-only features (ablation)unimodal clustering · Fruit speciesNMI: 0.559 -> 0.455Hurt
add contrastive loss (ablation)MLLMMC · six benchmark datasetsNMIImproved
add cross-attention (ablation)MLLMMC · six benchmark datasetsNMIImproved
add residual connection (ablation)MLLMMC · six benchmark datasetsNMIImproved
add candidate tag matching (ablation)MLLMMC · six benchmark datasetsNMIImproved
use MLLMMC instead of Multi-Sub/Multi-MaP with direct LLM-generated referencesMLLMMC vs Multi-Sub · CIFAR environmentNMI: 0.483 -> 0.220Hurt
use MLLMMC instead of Multi-SubMLLMMC vs Multi-Sub · Fruit colorNMI: 0.660 -> 0.694Improved

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