Reading articles about LLMs, you often see phrases like “we use the standard Transformer architecture.” But what does “standard” mean, and has it changed since the original paper? Interestingly, despite the rapid growth in the NLP field over the past five years, the Vanilla Transformer still adheres to the Lindy Effect, which suggests that the … Read more
1. Universal Magic Spells Description of Magic Commands: Theme + Detailed Description + Style Type + Command Parameters Spell Analysis Theme—— What type of scene to create, including time, characters, location, and activities in the scene Detailed Description—— Composition ratio, texture, light source, color tone, the type of scene, character dynamics and expressions (if the … Read more
Source: Deep Learning Enthusiasts This article is about 3000 words long and is recommended to be read in 10 minutes. This article introduces the basic components of CNN and classic network structures. The full name of CNN is “Convolutional Neural Network”. A neural network is a mathematical model or computational model that mimics the structure … Read more
While Wall Street’s tech stocks experienced a dramatic plunge on January 28, a new star in China’s AI sector was illuminating the entire industry with its disruptive brilliance—the DeepSeek team’s officially open-sourced Janus-Pro series model not only redefined the performance boundaries of multimodal large models but also showcased China’s hardcore strength in AI to the … Read more
Hello, I am the Fisherman. Today, I am sharing a 35-page overview of the latest Agentic RAG. The core problem this paper aims to address is the outdated, inaccurate outputs, and hallucinations that arise when today’s large language models (LLMs) rely on static training data to handle dynamic, real-time queries. It starts from the fundamental … Read more
If we talk about which AI software is the best for architectural design, it must be Stable Diffusion! Previously, we also introduced the basic usage of Midjourney in architectural workflows (click the blue text beside to jump if interested), but although the images generated by MJ are beautiful, the control is too poor, and the … Read more
On January 24, at the “New Architecture, New Model Power” large model launch conference held by Shanghai Yanxin Intelligent AI Technology Co., Ltd., Yanxin officially released the first general-purpose natural language large model in China that does not use the Attention mechanism—Yan model. As one of the few non-Transformer large models in the industry, the … Read more
Windsurf Editor: The Future Programming Assistant for Architecture Introduction In the architecture industry, designers and engineers rely on various software tools, such as CAD (Computer-Aided Design) and document processing software (like Word), to realize their ideas and designs. With the advancement of technology, enhancing efficiency and collaboration in design work has become a major challenge … Read more
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
How to build an effective operating AI Agent system? And how to identify potential issues during development that could lead to significant trouble after deployment? To answer these questions, you need to break the Agent system down into three parts: tools, reasoning, and action. Each layer has its own challenges. An error in one layer … Read more