Výsledky vyhledávání

Report

OG-RAG: Ontology-Grounded Retrieval-Augmented Generation For Large Language Models

Autor: Sharma, Kartik, Kumar, Peeyush, Li, Yunqing

This paper presents OG-RAG, an Ontology-Grounded Retrieval Augmented Generation method designed to enhance LLM-generated responses by anchoring retrieval processes in domain-specific ontologies. While LLMs are widely used for tasks like question answ

Externí odkaz: http://arxiv.org/abs/2412.15235

Zobrazit plný text záznamu

Report

Building A Knowledge Graph to Enrich ChatGPT Responses in Manufacturing Service Discovery

Autor: Li, Yunqing, Starly, Binil

Sourcing and identification of new manufacturing partners is crucial for manufacturing system integrators to enhance agility and reduce risk through supply chain diversification in the global economy. The advent of advanced large language models has

Externí odkaz: http://arxiv.org/abs/2404.06571

Zobrazit plný text záznamu

Report

Manufacturing Service Capability Prediction with Graph Neural Networks

Autor: Li, Yunqing, Liu, Xiaorui, Starly, Binil

In the current landscape, the predominant methods for identifying manufacturing capabilities from manufacturers rely heavily on keyword matching and semantic matching. However, these methods often fall short by either overlooking valuable hidden info

Externí odkaz: http://arxiv.org/abs/2403.17239

Zobrazit plný text záznamu

Akademický článek

Tracking astrocyte polarization in the retina in retinopathy of prematurity

Autor: Feng, Xiaoxiao, Zhang, Liwei, Jiao, Kangwei, Li, Yunqing, Wu, Min, Xie, Yu, Xiao, Libo

Publikováno v: In Experimental Eye Research January 2025 250

Zobrazit plný text záznamu

Report

A study on joint modeling and data augmentation of multi-modalities for audio-visual scene classification

Autor: Wang, Qing, Du, Jun, Zheng, Siyuan, Li, Yunqing, Wang, Yajian, Wu, Yuzhong, Hu, Hu, Yang, Chao-Han Huck, Siniscalchi, Sabato Marco, Wang, Yannan, Lee, Chin-Hui

In this paper, we propose two techniques, namely joint modeling and data augmentation, to improve system performances for audio-visual scene classification (AVSC). We employ pre-trained networks trained only on image data sets to extract video embedd

Externí odkaz: http://arxiv.org/abs/2203.04114

Zobrazit plný text záznamu