Fine-Tuned Llama Model Turns Unstructured Farm Data Into a Searchable Knowledge Graph
Researchers fine-tuned a Llama model with LoRA to extract agronomic triplets and build a GraphRAG-powered knowledge graph that outperforms standard ...
Researchers fine-tuned a Llama model with LoRA to extract agronomic triplets and build a GraphRAG-powered knowledge graph that outperforms standard ...
Researchers at Shanghai Jiao Tong University have built a multimodal knowledge graph that aligns historical Chinese architectural texts, field photographs ...
Chinese researchers have built an ontology-guided LightRAG framework that converts fragmented precarious rock hazard records into a knowledge graph, achieving ...
Researchers at a Chinese power grid enterprise have built a recommendation system that combines knowledge graphs with dynamic employee personas ...
A new hybrid recommender called Meta KG-NCF combines a frozen knowledge graph prior, neural collaborative filtering, and first-order meta-learning to ...
A 2025 study in Frontiers of Digital Education details how data-driven student portraits, built from knowledge graphs, clustering, and natural ...
Researchers at the Vellore Institute of Technology have built NEXUS-Rec, a five-signal neural recommender that outperforms strong baselines on MovieLens ...
Researchers in China have developed MKMed, a cross-modal AI framework that aligns five types of drug knowledge to overcome the ...
Researchers have built an ontology-driven GraphRAG framework that unifies fragmented levee data into a queryable knowledge graph, achieving 95.16 percent ...
Researchers in China have developed a detection method that combines temporal knowledge graphs, time-series tensors, and a variational autoencoder paired ...
© 2025 Scienmag - Science Magazine
© 2025 Scienmag - Science Magazine