Results 111 to 120 of about 36,775 (295)
Clustered Retrieved Augmented Generation (CRAG)
Providing external knowledge to Large Language Models (LLMs) is a key point for using these models in real-world applications for several reasons, such as incorporating up-to-date content in a real-time manner, providing access to domain-specific knowledge, and contributing to hallucination prevention.
Simon Akesson, Frances Albert Santos
openaire +2 more sources
Generative AI‐Driven Accelerated Discovery of Passivation Molecules for Perovskite Solar Cells
A generative artificial intelligence (AI) framework combining a discriminative machine learning model (SMILES‐X) and a generative language model (GPT‐2) autonomously discovers new molecular passivators for perovskite solar cells (PSCs). Through an iterative design loop, over 100 000 candidates are generated and screened, and randomly selected molecules
Adroit T. N. Fajar +7 more
wiley +1 more source
Document Retrieval Augmented Fine-Tuning (DRAFT) for Safety-Critical Software Assessment
The evaluation of safety critical software requires a robust evaluation against complex regulatory frameworks, a process traditionally limited by manual evaluation.
Regan Bolton +6 more
doaj +1 more source
Retrieval Augmented Comic Image Generation
We present RaCig, a novel system for generating comic-style image sequences with consistent characters and expressive gestures. RaCig addresses two key challenges: (1) maintaining character identity and costume consistency across frames, and (2) producing diverse and vivid character gestures.
Yunhao Shui +10 more
openaire +2 more sources
Bone cancer pain and depression share a common origin: astrocytic A2‐to‐A1 transition in the posterior piriform cortex. This phenotypic shift disrupts the ATP–adenosine–A2AR–norepinephrine axis, simultaneously driving nociceptive and affective dysfunction.
Jiang‐Ping Liu +14 more
wiley +1 more source
Case Study on Understanding the Power of Retrieval Augmented Generation (RAG) [PDF]
This paper explores how Generative AI is changing with the use of Retrieval-Augmented Generation (RAG). RAG helps improve Artificial Intelligence (AI) systems by making them more capable, efficient and accurate.
Venkata Jaipal Reddy Batthula +2 more
doaj
GRAG: Graph Retrieval-Augmented Generation
Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and, as a result, falls short in handling networked documents which are very popular in many applications such as citation graphs, social media, and knowledge graphs.
Yuntong Hu +5 more
openaire +2 more sources
Multi‐omic profiling of T1 high‐grade bladder cancer identifies a high‐risk subtype (T1HG1) driven by NQO1, which couples anoikis resistance with immune evasion. NQO1 orchestrates macrophage–T cell crosstalk suppression via CXCL9 modulation. Pharmacological NQO1 inhibition with skullcapflavone II enhances cisplatin efficacy, representing a promising ...
Bin Guo +20 more
wiley +1 more source
Development of a Retrieval-Augmented Generation (RAG) Chatbot [PDF]
Our research presents a Retrieval-Augmented Generation (RAG) chatbot designed for intelligent document-based question answering. Built with Streamlit as the front-end, the application integrates LLaMA2 models hosted on Replicate, alongside a document ...
Simona-Vasilica Oprea , Adela Bâra
doaj
Medical question answering (QA) systems and conversational agents have attracted growing interest as tools that can assist clinicians, support medical students, and help patients navigate complex information sources.
Richard Coric +2 more
doaj +1 more source

