+++ digiS-Workshops +++ #OERcamp +++ Public Domain Day +++ Science Tracking +++ Social Media für Kultureinrichtungen +++ PID-Workshop +++ Ausgewählte Veranstaltungen im Berliner Raum und online zu Open Research in Wissenschaft und Kulturerbe
An Introduction to RA-CM3, MuRAG and RACE Author Xuzeng He (ORCID: 0009-0005-7317-7426) Generative Artificial Intelligence (GAI) has demonstrated impressive performances in tasks such as text generation and text-to-image generation.
Refining AI Vision: How Retrieval-Augmented Generation Transforms Image Captioning in Large Language Models Leveraging External Knowledge to Enhance the Descriptive Capabilities of AI Systems Author Vaibhav Khobragade (ORCID: 0009–0009–8807–5982) Introduction Large Language Models (LLMs) are artificial intelligence models that are trained on massive amounts of text data in order to generate human-like language and produce coherent
An Introduction to Retrieval Augmented Generation (RAG) and Knowledge Graph Author Qingqin Fang (ORCID: 0009–0003–5348–4264) Introduction Large Language Models (LLMs) have transformed the landscape of natural language processing, demonstrating exceptional proficiency in generating text that closely resembles human language.
Improving the performance of Large Language Models Author Dhruv Gupta (ORCID: 0009-0004-7109-5403) ChatGPT, which first came out in late 2022, took the world by storm. Since then, various LLM models and LLM based products such as Meta’s Llama and Google’s Gemini have emerged, demonstrating the power of LLMs.
Improving the performance and application of Large Language Models Author Amanda Kau (ORCID: 0009-0004-4949-9284) Large language models (LLMs) like GPT-4, the engine of products like ChatGPT, have taken centre stage in recent years due to their astonishing capabilities. Yet, they are far from perfect.
How to efficiently retrieve information for different applications Author Wenyi Pi (ORCID: 0009-0002-2884-2771) This article aims to explore various ways in which Retrieval-Augmented Generation (RAG) can be utilised to retrieve information and generate responses effectively within the dialogue system. The rationale behind utilising RAG as well as potential ways in which it can be employed effectively will be covered.
The package assertr maintained by Tony Fischetti, provides functionality to assert conditions that have to be met so that errors in data used in analysis pipelines can fail quickly.The provided functionality is similar to stopifnot() but more powerful, friendly, and easier for use in pipelines.Contributed to assertr!
por Benjamín Marín Meneses Miguel Fernández Ubiría en su libro Fútbol y anarquismo (2020) menciona la existencia de dos agrupaciones futbolísticas en México que podrían enmarcarse en el ideal anarquista: la Selección del Ejército Zapatista de Liberación Nacional y el UD Sinaia (en el que juegan, esporádicamente, Gael García y Diego Luna). Las suposiciones de […]
The Rogue Scholar science blog archive today has launched a new free Personal Plan : similar to the Starter Plan launched last year, but only for personal (single-author) blogs, and with no limitations on the number of blog posts that can be archived and registered with a DOI per year.