Agentic AI

Understanding Stable Diffusion Through 35 Illustrations

by
Understanding Stable Diffusion Through 35 Illustrations

Source | OSCHINA Community – OneFlow Deep Learning Framework Original link: https://my.oschina.net/oneflow/blog/6087116 Author｜Jay Alammar Translated by｜Yang Ting, Xu Jiayu Recently, AI image generation has attracted attention for its ability to create stunning images based on textual descriptions, greatly changing the way people create images.Stable Diffusion, as a high-performance model, produces higher quality images, operates faster, … Read more

Is the Diffusion Model Outpacing GANs?

by
Is the Diffusion Model Outpacing GANs?

Jin Lei Alex from Aofeisi Quantum Bit | WeChat Official Account QbitAI The once-popular GAN is outdated. Tom Goldstein, an associate professor at the University of Maryland, recently published a tweet that stirred up a lot of discussion. Even big names in the tech world have come to pay attention: The keyword that the topic … Read more

Mathematics and Working Principles of Diffusion and Stable Diffusion

by
Mathematics and Working Principles of Diffusion and Stable Diffusion

Author：Deephub Imba This article is approximately 2800 words, recommended reading time 5minutes This article introduces how the diffusion model works. The rise of diffusion models can be seen as a major factor in the recent breakthroughs in the field of AI-generated art. The development of the stable diffusion model allows us to easily create wonderful … Read more

RAG-Check: A Novel AI Framework for Multimodal Retrieval-Augmented Generation

by
RAG-Check: A Novel AI Framework for Multimodal Retrieval-Augmented Generation

Large Language Models (LLMs) have made significant progress in the field of generative artificial intelligence, but they face the “hallucination” problem, which is the tendency to generate inaccurate or irrelevant information. This issue is particularly severe in high-risk applications such as medical assessments and insurance claims processing. To address this challenge, researchers from the University … Read more

Introduction to RAG Technology: A New Journey in Large Model Application Development

by
Introduction to RAG Technology: A New Journey in Large Model Application Development

What is RAG Technology RAG, or Retrieval-Augmented Generation technology, is an AI architecture that combines retrieval and generation. It enhances the output quality of language models by retrieving external knowledge. This is akin to equipping large language models with an intelligent knowledge base, enabling them to retrieve and reference relevant information in real-time while generating … Read more

Roaming RAG Technology: Features and Advantages

by
Roaming RAG Technology: Features and Advantages

Roaming RAG, as an innovative RAG technology, can be elaborated on in detail regarding its characteristics and advantages from the following aspects: Working Principle and Process The core of Roaming RAG lies in utilizing the hierarchical structure of documents to enhance the information retrieval capabilities of large language models (LLMs). The specific process includes: Document … Read more

RAG Architecture Explained: 7 Patterns from Basic to Advanced

by
RAG Architecture Explained: 7 Patterns from Basic to Advanced

The RAG technology introduces external knowledge retrieval in the AI generation process, evolving from basic document queries to intelligent architectures with multi-modal and Multi-Agent collaborations, allowing AI to provide more accurate and comprehensive answers. Core Components: Embedding Model: Converts text into vector representations. Generation Model: Responsible for the final content generation. Re-ranking Model: Optimizes the … Read more

Overview of 15 Classic RAG Frameworks (Part 2)

by
Overview of 15 Classic RAG Frameworks (Part 2)

Source: Deep Learning and Large Models (LLM) This article is approximately 3500 words long and is recommended for a 9-minute read. This article delves into the development of Retrieval-Augmented Generation (RAG), from basic concepts to the latest technologies. 4. Overview of Existing RAG Frameworks Agent-Based RAG A new agent-based Retrieval-Augmented Generation (RAG) framework adopts a … Read more

RAG vs Fine-Tuning: A Guide for Domain-Specific AI Models

by
RAG vs Fine-Tuning: A Guide for Domain-Specific AI Models

Machine Heart Report Editor: Rome Retrieval-Augmented Generation (RAG) and Fine-tuning are two common methods to enhance the performance of large language models. So, which method is better? Which is more efficient when building applications in specific domains? This paper from Microsoft serves as a reference for your choice. When constructing large language model applications, there … Read more

Microsoft’s ‘Little Cannon’: Phi-4 – A Model for Complex Inference Driven by Synthetic Data

by
Microsoft's 'Little Cannon': Phi-4 - A Model for Complex Inference Driven by Synthetic Data

Follow us to stay updated! Recently, the LLM community has been immersed in the shock brought by DeepSeek-V3. This model is not only open-source but also performs well. However, such a large-scale LLM is beyond our reach (the GPU memory can’t handle it). If we can’t afford that, let’s take a look at Microsoft’s open-source … Read more