7 papers
Mixture-of-Translators: Translating KV Caches Across Heterogeneous Large Language Models
Jin-woo Lee, Minkyung Song, Junghyun Oh +4
Heterogeneous Large Language Model (LLM) systems increasingly rely on shared contexts, retrieved evidence, and multi-agent dialogue histories, yet their internal key-value (KV) cac…
MPR-CiteG: Enhancing RAG with Multi-Portfolio Retrieval and Citation-Grounded Generation
Hyewon Lee, Minkyung Song, Junghyun Oh +2
This paper presents the MPR-CiteG framework, which achieved second place in the ScienceON AI Challenge by addressing two fundamental challenges in generative AI: inefficient retrie…
Hyperbolic Heterogeneous Graph Transformer
Jongmin Park, Seunghoon Han, Hyewon Lee +2
In heterogeneous graphs, we can observe complex structures such as tree-like or hierarchical structures. Recently, the hyperbolic space has been widely adopted in many studies to e…
Alibaba International E-commerce Product Search Competition DILAB Team Technical Report
Hyewon Lee, Junghyun Oh, Minkyung Song +2
This study presents the multilingual e-commerce search system developed by the DILAB team, which achieved 5th place on the final leaderboard with a competitive overall score of 0.8…
Metapath-based Hyperbolic Contrastive Learning for Heterogeneous Graph Embedding
Jongmin Park, Seunghoon Han, Won-Yong Shin +1
The hyperbolic space, characterized by a constant negative curvature and exponentially expanding space, aligns well with the structural properties of heterogeneous graphs. However,…
Zero-Shot Industrial Anomaly Segmentation with Image-Aware Prompt Generation
SoYoung Park, Hyewon Lee, Mingyu Choi +4
Anomaly segmentation is essential for industrial quality, maintenance, and stability. Existing text-guided zero-shot anomaly segmentation models are effective but rely on fixed pro…