ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (31) · 26588-26596
DOI: 10.1609/aaai.v40i31.39867 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xinyue Wang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Typical deep clustering methods, while achieving notable progress, can only provide one clustering result per dataset. This limitation arises from their assumption of a fixed underlying data distribution, which may fail to meet user needs and provide unsatisfactory clustering outcomes. Our work investigates how multi-modal large language models (MLLMs) can be leveraged to achieve user-driven clustering, emphasizing their adaptability to user-specified semantic requirements. However, directly using MLLM output for clustering has risks for producing unstructured and generic image descriptions instead of feature-specific and concrete ones. To address these issues, our method first discovers that MLLMs' hidden states of text tokens are strongly related to the corresponding features, and leverages these embeddings to perform clusterings from any user-defined criteria. We also employ a lightweight clustering head augmented with pseudo-label learning, significantly enhancing clustering accuracy. Extensive experiments demonstrate its competitive performance on diverse datasets and metrics.
Zitieren
APA
Wang, X., Jia, Y., Liu, H., & Hou, J. (2026). ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering. Proceedings of the AAAI Conference on Artificial Intelligence, 40(31), 26588-26596. https://doi.org/10.1609/aaai.v40i31.39867
Vancouver
Wang X, Jia Y, Liu H, Hou J. ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(31):26588-26596. doi:10.1609/aaai.v40i31.39867
BibTeX
@article{Wang2026,
author = {Wang, Xinyue and Jia, Yuheng and Liu, Hui and Hou, Junhui},
title = {ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {31},
pages = {26588--26596},
doi = {10.1609/aaai.v40i31.39867}
}
EUVIMED