Large Language Models

Comprehensive Survey on the Development and Application of AI Agents in 2023: Concepts, Principles, Development, Applications, Challenges, and Prospects

by
Comprehensive Survey on the Development and Application of AI Agents in 2023: Concepts, Principles, Development, Applications, Challenges, and Prospects

The field of Artificial Intelligence (AI) is rapidly evolving.Today’s AI agents are capable of perceiving, making decisions, and taking actions independently. With the rise of AI agents driven by large language models (LLMs), we are on the brink of a new era: AI agents may form their own societies and coexist harmoniously with humans. Newton … Read more

What is an AI Agent?

by
What is an AI Agent?

ChatGPT has released GPTs, and DingTalk has launched AI assistants. In the AI era, AI agents are the mainstream form of implementing large models in business scenarios. So, what is an AI Agent? 01 — What is an AI Agent? An AI Agent, or Artificial Intelligence Agent, is an entity capable of perceiving its environment, … Read more

Why the Next Stop for Artificial Intelligence is AI Agents?

by
Why the Next Stop for Artificial Intelligence is AI Agents?

Introduction: J.A.R.V.I.S from Iron Man In the movie Iron Man, J.A.R.V.I.S is an impressive AI assistant. As Tony’s capable aide, he is both reliable and intelligent, capable of connecting to any computer terminal, controlling Tony’s Iron Man suit, and discussing action plans with Tony. The success of J.A.R.V.I.S lies in his highly intelligent AI system, … Read more

In-Depth Analysis of AI Agents

by
In-Depth Analysis of AI Agents

1. Definition and Core Features An AI Agent is an intelligent system capable of perceiving its environment through sensors, making autonomous decisions, and utilizing tools to perform tasks. Its core features include: Autonomy: Operates without continuous human intervention. Goal-Oriented: Breaks down tasks and plans around predefined objectives. Adaptability: Dynamically adjusts strategies through feedback mechanisms. Interactivity: … Read more

Solving Composite Problems in One Inference: The MeteoRA Architecture for Scalable Integration of Knowledge Modules in Large Language Models Based on MoE

by
Solving Composite Problems in One Inference: The MeteoRA Architecture for Scalable Integration of Knowledge Modules in Large Language Models Based on MoE

In the field of large language models, the pre-training + fine-tuning paradigm has become an important foundation for deploying various downstream applications. Within this framework, the use of low-rank adaptation (LoRA) methods for efficient fine-tuning of large model parameters (PEFT) has resulted in a large number of reusable LoRA adapters tailored for specific tasks. However, … Read more

Solving Composite Problems in One Inference: The MeteoRA Architecture for Scalable Integration of Knowledge Modules in MoE-based Large Language Models

by
Solving Composite Problems in One Inference: The MeteoRA Architecture for Scalable Integration of Knowledge Modules in MoE-based Large Language Models

The AIxiv column is a section published by Machine Heart that features academic and technical content. Over the past few years, the AIxiv column has reported on more than 2000 pieces of content, covering top laboratories from major universities and companies worldwide, effectively promoting academic exchange and dissemination. If you have excellent work to share, … Read more

A Comprehensive Guide to Running Large Model Applications on NVIDIA Jetson

by
A Comprehensive Guide to Running Large Model Applications on NVIDIA Jetson

We are very excited to share some amazing advancements in bringing the latest generative AI and large language models (LLMs) to edge computing. Since the introduction of Transformers and NVIDIA’s launch of the Ampere GPU in 2020, we have witnessed a rapid increase in the scale and intelligence of models, approaching human levels. This has … Read more

Efficient Deep Learning Computation: From TinyML to LargeLM

by
Efficient Deep Learning Computation: From TinyML to LargeLM

Deep learning dominates various fields and fundamentally changes human society. Efficiency is a key factor in democratizing deep learning and expanding its application scope. This has become increasingly important as Moore’s Law slows down and the pace of model size expansion accelerates. We need efficient algorithms and systems to help bridge this gap. In this … Read more

Modular Design and X1 Framework Enhance Reasoning Model Development

by
Modular Design and X1 Framework Enhance Reasoning Model Development

Click Follow us by clicking the blue text above This paper introduces a modular blueprint and the X1 framework aimed at advancing the development of accessible and scalable Reasoning Language Models (RLMs) by combining reinforcement learning and hierarchical reasoning strategies, simplifying the design and deployment of RLMs, enhancing efficiency, and reducing costs. Paper Introduction By … Read more

What Can Trainers Do in the Era of AI Large Models?

by
What Can Trainers Do in the Era of AI Large Models?

By | Li Dongshuo, Founder, Chairman, and President of UMU Source | Training Magazine July Issue It is not easy to elaborate on the definition of Artificial Intelligence (AI). The reason is that AI has the characteristic of phased development, forming new shapes and connotations over time. Three years ago, when people talked about AI, … Read more