AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

ESMC: MLLM-Based Embedding Selection for Explainable Multiple Clustering

Xinyue Wang, Yuheng Jia, Hui Liu, Junhui Hou

AAAI 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Multilingual language representation pretraining · 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
add MLP clustering head with pseudo-labels (ablation)ESMC · CMU_face PoseNMI: 0.5498 -> 0.6271Improved
add MLP clustering head with pseudo-labels (ablation)ESMC · Fruit360 SpeciesNMI: 0.3806 -> 0.5036Improved
add MLP clustering head with pseudo-labels (ablation)ESMC · CIFAR-10 TypeNMI: 0.7149 -> 0.8293Improved
add MLP clustering head with pseudo-labels (ablation)ESMC · Fruit ColorNMI: 0.9308 -> 0.9308No clear effect
use hidden-state token embeddings instead of MLLM text output (ablation)ESMC w/o MLP · CIFAR-10 EnvironmentNMI: 0.0443 -> 0.5484Improved
use hidden-state token embeddings instead of MLLM text output (ablation)ESMC w/o MLP · CMU_face PoseNMI: 0.0913 -> 0.5498Improved
use hidden-state token embeddings instead of MLLM text output (ablation)ESMC w/o MLP · CIFAR-10 TypeNMI: 0.7505 -> 0.7149Hurt
use ESMC instead of Multi-SubESMC · CIFAR-10 TypeNMI: 0.5271 -> 0.8293Improved
use ESMC instead of Multi-SubESMC · Fruit360 SpeciesNMI: 0.6123 -> 0.5036Hurt
use ESMC instead of Multi-SubESMC · CMU_face EmotionRI: 0.8527 -> 0.6697Hurt
rephrase the prompt (ablation)ESMC · Stanford_Cars ColorNMI: 0.8138 vs 0.8016 / 0.8143 / 0.8113No clear effect
change keyword-generating LLM (GPT-4, DeepSeek-R1, Gemini-2.5) (ablation)ESMC · Stanford_CarsNMI: 0.8138 and 0.8817 for allNo clear effect

Later papers that compared with this method

1 later accepted paper reports ESM-C 300M as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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