Articles by Yang Fan

Comprehensive Introduction HealthGPT is a state-of-the-art medical grand visual language model designed to enable unified medical visual understanding and generation capabilities through heterogeneous knowledge adaptation. The goal of the project is to integrate medical vision understanding and generation capabilities into a unified autoregressive framework, significantly enhancing the medical image processing...

General Introduction MatAnyone is an open source project focusing on video keying, developed by a research team at S-Lab, Nanyang Technological University, Singapore and released on GitHub. It provides users with stable and efficient video processing capabilities through consistent memory propagation techniques , especially good at dealing with complex backgrounds...

General Introduction HiveChat is an AI chatbot for small to medium sized teams that allows administrators to configure multiple AI models (such as Deepseek, OpenAI, Claude, and Gemini) at once for easy use by team members. It features LaTeX and Markdown rendering, DeepS...

Whether you are a new user of Microsoft 365 Copilot or a skilled veteran, whether you use copilot chat, or use copilot in office365, copilot prompts thesaurus will help you make full use of this epoch-making product of copilot. It will not only help you memorize everyday...

General Omnitool.ai is an open source "AI lab" designed to provide an extensible browser-based desktop environment for learners, hobbyists, and anyone interested in current AI innovations. It allows users to collaborate with other AI labs from OpenAI, replicate.com, Stable Diffusio...

General Description Bardeen AI is an automated workflow platform designed to boost team productivity. Through seamless integration with popular tools, Bardeen AI automates repetitive tasks, simplifies data management, and enhances team collaboration. Users don't need to write code, just simple actions to create...

General Introduction Step-Video-T2V is an advanced text-to-video conversion model by StepFun AI (StepFun Star). The model has 3 billion parameters and is capable of generating videos up to 204 fps. With a deep compression Variable Auto-Encoder (VAE), the model achieves a spatial compression of 16x16 and a temporal compression of 8x...

General Introduction OmniParser is a tool developed by Microsoft to parse user interface screenshots into structured and easy-to-understand elements. This tool significantly improves the ability of GPT-4V to generate accurate actions in the corresponding interface area.OmniParser not only supports a wide range of large language models, but also...

This document is a PPT of a talk given at Stanford University by Barret Zoph and John Schulman (also OpenAI co-founders), OpenAI's pre- and post-training leads, sharing their experience in developing ChatGPT post-training at OpenAI. Since the talk was not videotaped, this PPT is a great way to learn more about this...

This is a reprint of the article, according to the previously written: "Using intelligent programming tools Trae to create an all-powerful writing platform", the next episode will be about how to use Trae to empower the local knowledge base, by the server crash restrained for two days, happened to read this article on the loan of flowers to the Buddha, as a sister article of the original article, included in the...

Introduction Welcome to the course on Metacognition in AI Agent! This chapter is designed for beginners interested in how AI Agents think about their own thought processes. By the end of this course, you will understand key concepts and have practical examples of applying metacognition to AI Agent design. Learning Objectives...

When you start working on a project that involves multiple intelligences, you need to consider the Multi-Intelligence Design Pattern. However, it may not be obvious when to move to multi-intelligentsia and what the advantages are. Introduction In this course, Microsoft attempts to answer the following questions: What scenarios are suitable for multi-intelligentsia? What scenarios are suitable for multi-intelligence?

INTRODUCTION This paper will cover the following: Define clear overarching goals and break down complex tasks into manageable subtasks. Leverage structured output for more reliable and machine-readable responses. Applying an event-driven approach to dynamic tasks and unexpected inputs. Learning Objectives At the completion of this article...

Introduction This course will cover: How to build and deploy secure and effective AI Agents Important security considerations when developing AI Agents. How to maintain data and user privacy when developing AI Agents. Learning Objectives After completing this course, you will understand how to: Create AI Agents ...

This course provides a comprehensive overview of Agentic Retrieval-Augmented Generation (Agentic RAG), an emerging AI paradigm in which Large Language Models (LLMs) autonomously plan their next actions while acquiring information from external sources. Instead of the static "retrieve-then-read" model...

Tools are interesting because they allow AI intelligences to have a wider range of capabilities. By adding tools, the intelligence is no longer limited to the limited set of operations it can perform, but can perform a wide variety of operations. In this chapter, we will explore the Tool Usage Design Pattern, which describes the AI ...

INTRODUCTION There are many ways to build AI Agentic systems. Given that ambiguity is a feature, not a flaw, of generative AI design, it is sometimes difficult for engineers to determine where to start. We have created a set of human-centered user experience design principles that enable developers to build customer-centric Agentic...