AI Paper Atlas

Research map / Large language models / Agents, code and math

Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent

Wenliang Zhong, Rob Barton, Lucas Goncalves, Kushal Kumar, Feng Jiang, Hehuan Ma, Yuzhi Guo, Vidit Bansal, Karim Bouyarmane, Junzhou Huang

CVPR 2026 · Large language models › Agents, code and math · approach: LLMs for optimization and heuristics · 0 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 MST-based LLM Traversal merging after HDBSCAN (ablation)GCPM-G · ImageNet-10ARI: 0.3 -> 72.1Improved
add MST Traversal after HDBSCAN on long-tail e-commerce (ablation)GCPM-E · ABO-LCARI: 28.2 -> 51.5Improved
add MST Traversal on fine-grained clustering (ablation)GCPM · fine-grained datasetsNMI: 1.0 to 3.2 NMI gainImproved
add MST Traversal: recall vs precision (ablation)HDBSCAN · ImageNet-10BCubed recall: 19.9 -> 62.3 recall, 99.7 -> 93.5 precisionMixed
use GCPM guideline captions instead of image only (ablation)GME-Qwen embedder · Card-NumberNMI: 71.9 -> 82.0Improved
use GCPM guideline captions instead of image only (ablation)GME-Qwen embedder · Stanford CarsNMI: 61.5 -> 86.2Improved
use GCPM guideline captions instead of standard captions (ablation)GME-Qwen embedder · ImageNet-10NMI: 93.7 -> 96.7Improved
use MLLM embedder (GCPM-G) instead of text instruction encoder (GCPM-I)GCPM · CIFAR-10ACC: 75.6 -> 94.1Improved
use LLM embedder E5-Mistral instead of GME on CardGCPM · Card-NumberNMI: 82.0 -> 91.1Mixed
K-Means with known cluster count instead of HDBSCAN aloneGCPM-G · CIFAR-10ACC/NMI: 42.0 -> 94.1Improved
prompt optimization of merge guideline with PromptAgent (ablation)MST Traversal · Oxford FlowersB-Prec.: 90.1 -> 95.7Improved

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