← 研踪 PaperTrailCVF · CVPR 2026:cvf:43bf4af73eda479c00baabf1a2a81970 · 记录 #1
Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent
Zhong, WenliangBarton, RobGoncalves, LucasKumar, KushalJiang, FengMa, HehuanGuo, YuzhiBansal, ViditBouyarmane, KarimHuang, Junzhou 来源日期(仅到年份) 2026
来源记录日期 2026
雷达观测 2026-11-05 01:48
摘要
Unifying image clustering across different clustering scenarios remains challenging due to fundamental gaps among tasks. We introduce a Guideline-Driven Image Clustering Agent, the first universal framework that bridges these gaps through textual guidelines. To incorporate complex guidelines without task-specific training, we propose Generative Concept Proxy Modeling, which generates guideline-aware embeddings via concept proxy extraction. For scenarios requiring automatic cluster discovery, we introduce LLM Traversal based on Minimum Spanning Tree that selectively applies LLM reasoning for complex semantic judgments. Our method generalizes across diverse clustering scenarios spanning from general to fine-grained categorization, from global to local criteria, and from balanced to long-tail distributions. Our framework consistently outperforms specialized methods across diverse clustering tasks.
论文发现出处
这些页面提供论文线索,不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化,不是作者修订号。来源日期仅到月份或年份时,按该月或该年首日存档。
记录 #1 · 2026 · 最新观测版本
Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent
Unifying image clustering across different clustering scenarios remains challenging due to fundamental gaps among tasks. We introduce a Guideline-Driven Image Clustering Agent, the first universal framework that bridges these gaps through textual guidelines. To incorporate complex guidelines without task-specific training, we propose Generative Concept Proxy Modeling, which generates guideline-aware embeddings via concept proxy extraction. For scenarios requiring automatic cluster discovery, we introduce LLM Traversal based on Minimum Spanning Tree that selectively applies LLM reasoning for complex semantic judgments. Our method generalizes across diverse clustering scenarios spanning from general to fine-grained categorization, from global to local criteria, and from balanced to long-tail distributions. Our framework consistently outperforms specialized methods across diverse clustering tasks.
查看此版本解读 →查看此版本原文 ↗