OpenAI

2299 Articles
From Fine-Tuning to Prompt Engineering: Theory and Practice for Efficient Transformer Adaptation
OpenAI

From Fine-Tuning to Prompt Engineering: Theory and Practice for Efficient Transformer Adaptation

The Challenge of Fine-Tuning Large Transformer Models Self-attention enables transformer models to capture long-range dependencies in text, which is crucial for comprehending complex...

How to Use python-A2A to Create and Connect Financial Agents with Google’s Agent-to-Agent (A2A) Protocol
OpenAI

How to Use python-A2A to Create and Connect Financial Agents with Google’s Agent-to-Agent (A2A) Protocol

Python A2A is an implementation of Google’s Agent-to-Agent (A2A) protocol, which enables AI agents to communicate with each other using a shared, standardized...

EPFL Researchers Introduce MEMOIR: A Scalable Framework for Lifelong Model Editing in LLMs
OpenAI

EPFL Researchers Introduce MEMOIR: A Scalable Framework for Lifelong Model Editing in LLMs

The Challenge of Updating LLM Knowledge LLMs have shown outstanding performance for various tasks through extensive pre-training on vast datasets. However, these models...

OpenBMB Releases MiniCPM4: Ultra-Efficient Language Models for Edge Devices with Sparse Attention and Fast Inference
OpenAI

OpenBMB Releases MiniCPM4: Ultra-Efficient Language Models for Edge Devices with Sparse Attention and Fast Inference

The Need for Efficient On-Device Language Models Large language models have become integral to AI systems, enabling tasks like multilingual translation, virtual assistance,...

StepFun Introduces Step-Audio-AQAA: A Fully End-to-End Audio Language Model for Natural Voice Interaction
OpenAI

StepFun Introduces Step-Audio-AQAA: A Fully End-to-End Audio Language Model for Natural Voice Interaction

Rethinking Audio-Based Human-Computer Interaction Machines that can respond to human speech with equally expressive and natural audio have become a major goal in...

EPFL Researchers Unveil FG2 at CVPR: A New AI Model That Slashes Localization Errors by 28% for Autonomous Vehicles in GPS-Denied Environments
OpenAI

EPFL Researchers Unveil FG2 at CVPR: A New AI Model That Slashes Localization Errors by 28% for Autonomous Vehicles in GPS-Denied Environments

Navigating the dense urban canyons of cities like San Francisco or New York can be a nightmare for GPS systems. The towering skyscrapers...

Microsoft AI Introduces Code Researcher: A Deep Research Agent for Large Systems Code and Commit History
OpenAI

Microsoft AI Introduces Code Researcher: A Deep Research Agent for Large Systems Code and Commit History

Rise of Autonomous Coding Agents in System Software Debugging The use of AI in software development has gained traction with the emergence of...

Building AI-Powered Applications Using the Plan → Files → Code Workflow in TinyDev
OpenAI

Building AI-Powered Applications Using the Plan → Files → Code Workflow in TinyDev

In this tutorial, we introduce TinyDev class implementation, a minimal yet powerful AI code generation tool that utilizes the Gemini API to transform...