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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| fuse text and image features via cross-attention instead of image-only features (ablation) | MLLMMC · COIL color | NMI: 0.025 -> 0.990 | Improved |
| fuse text and image features instead of image-only features (ablation) | MLLMMC · CIFAR type | NMI: 0.008 -> 0.764 | Improved |
| fuse image features with text instead of text-only features (ablation) | MLLMMC · Cards number | NMI: 0.359 -> 0.575 | Improved |
| fuse image features with text instead of text-only features (ablation) | MLLMMC · CMUFace pose | NMI: 0.097 -> 0.120 | Improved |
| use text-only features instead of image-only features (ablation) | unimodal clustering · COIL color | NMI: 0.025 -> 0.951 | Improved |
| use text-only features instead of image-only features (ablation) | unimodal clustering · Fruit species | NMI: 0.559 -> 0.455 | Hurt |
| add contrastive loss (ablation) | MLLMMC · six benchmark datasets | NMI | Improved |
| add cross-attention (ablation) | MLLMMC · six benchmark datasets | NMI | Improved |
| add residual connection (ablation) | MLLMMC · six benchmark datasets | NMI | Improved |
| add candidate tag matching (ablation) | MLLMMC · six benchmark datasets | NMI | Improved |
| use MLLMMC instead of Multi-Sub/Multi-MaP with direct LLM-generated references | MLLMMC vs Multi-Sub · CIFAR environment | NMI: 0.483 -> 0.220 | Hurt |
| use MLLMMC instead of Multi-Sub | MLLMMC vs Multi-Sub · Fruit color | NMI: 0.660 -> 0.694 | Improved |
Closest papers by meaning
- ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering (AAAI 2026 · similarity 0.92)
- Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering (CVPR 2024 · similarity 0.86)
- SpEx: A Spectral Approach to Explainable Clustering (NeurIPS 2025 · similarity 0.86)
- Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning (NeurIPS 2024 · similarity 0.86)
- Medusa: A Multi-Scale High-order Contrastive Dual-Diffusion Approach for Multi-View Clustering (CVPR 2025 · similarity 0.86)
- A Peer-review Look on Multi-modal Clustering: An Information Bottleneck Realization Method (ICML 2025 · similarity 0.86)
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.
