RLHF Programming Tutorials & Engineering Articles

This article explores how to train an AI agent to operate a new Command Line Interface (CLI) using synthetic data generation and reinforcement learning.

The article discusses the NVIDIA Rubin platform, which introduces six new chips designed to create a powerful AI supercomputer.

The article discusses the development of scientific AI agents using reinforcement learning (RL) techniques, specifically through the NVIDIA NeMo framework.

The article discusses the innovative use of AI co-scientists in scientific research, specifically focusing on fusion research and cancer treatment.

Netflix introduces Advantage-Weighted Supervised Fine-Tuning (A-SFT), a novel post-training algorithm for generative recommender systems that addresses the unique challenges of applying reinforceme...

The article introduces Tunix, a new open-source, JAX-native library designed for post-training of large language models (LLMs).

The article discusses the use of synthetic data in post-training procedures for large language models (LLMs) and highlights NVIDIA's open-sourcing of the Llama-Nemotron post-training dataset, which...

The article discusses the development and capabilities of NVIDIA's Llama Nemotron reasoning models, which enhance AI agents' reasoning abilities for complex problem-solving in various industries.

Gemma 3 is the latest version of the Gemma open-model family, boasting enhanced capabilities such as multimodality, longer context windows, and improved reasoning.

The article introduces GPT-4. 5, OpenAI's latest and most advanced model for chat, highlighting its improvements in unsupervised learning, emotional intelligence, and practical applications.

The OpenAI GPT-4. 5 System Card provides insights into the latest advancements in OpenAI's language model, highlighting its capabilities, safety evaluations, and preparedness framework.

The article discusses the Llama Nemotron models, which enhance Agentic AI workflows by integrating large language models with advanced reasoning and planning capabilities.

The article discusses a new alignment strategy called deliberative alignment, which teaches reasoning to language models to enhance their safety.

The article discusses the development of domain-adapted foundation GenAI models at LinkedIn, focusing on their application within the Economic Opportunity Network (EON) project.

The article discusses the development of a new reward model, Llama 3.

The article discusses the deployment of the Llama 3.

The article discusses how NVIDIA optimizes data center performance using AI agents and the OODA loop strategy.

The article discusses the Mistral NeMo 12B model, a next-generation language model developed by NVIDIA and Mistral, designed for high performance on a single GPU.

The article discusses the launch of Meta's Llama 3.

The article discusses the Llama 3. 1 collection of large language models (LLMs) and their applications in enterprise settings.

The article discusses the development and application of Rule-Based Rewards (RBRs) to enhance the safety behavior of AI models, reducing reliance on extensive human data collection.

The article introduces GPT-4o mini, OpenAI's most cost-efficient small model, designed to make AI intelligence more accessible and affordable.

The article discusses CriticGPT, a model based on GPT-4, designed to identify errors in ChatGPT responses.

NVIDIA has achieved new generative AI performance records in MLPerf Training v4. 0, showcasing significant advancements in training large language models (LLMs) and graph neural networks (GNNs).

The article introduces DRaFT+, an enhanced algorithm for fine-tuning text-to-image diffusion models, which aims to improve the alignment between input prompts and generated images.

The article discusses NVIDIA NeMo Customizer, a microservice designed to simplify the fine-tuning and alignment of large language models (LLMs) for enterprise AI applications.

The article discusses the NVIDIA NeMo microservices, which simplify the development of custom generative AI models for enterprises.

The article discusses StarCoder2, an advanced large language model (LLM) designed to enhance coding efficiency for developers.

NVIDIA collaborates with Google to enhance inference performance for the Gemma models using TensorRT-LLM, facilitating easier development with large language models (LLMs) on NVIDIA RTX GPUs.

The article discusses the collaboration between H2O. ai and NVIDIA to enhance AI applications in financial services through generative AI and predictive analytics.

The article discusses the latest features of the NVIDIA NeMo framework and the performance enhancements brought by the NVIDIA H200 GPUs, which significantly improve the training of large language m...

Dell Technologies and NVIDIA have collaborated to set new records in financial risk calculations using the NVIDIA H100 system for high-performance computing (HPC) and AI.

The article discusses how to leverage Palantir AIP to build a semantic search application that uncovers insights from unstructured data within enterprises.

The article discusses the evolution of machine learning operations (MLOps) into specialized areas such as GenAIOps and LLMOps, focusing on the development and management of generative AI and large ...

The article discusses NVIDIA's AI Foundation Models, specifically the Nemotron-3 8B family, which enables the creation of custom enterprise chatbots and co-pilots with production-ready capabilities.

The article discusses how to build custom enterprise-grade generative AI applications using NVIDIA's AI Foundation Models.

The article discusses the application of Large Language Models (LLMs) in enterprise solutions, highlighting their capabilities in enhancing productivity across various industries.

NVIDIA has introduced the Jetson Generative AI Lab, enabling developers to leverage generative AI capabilities on Jetson edge devices.

NVIDIA SteerLM is a novel technique designed to simplify the customization of large language models (LLMs) during inference.

The article discusses various techniques for customizing Large Language Models (LLMs) to better fit enterprise needs, emphasizing the importance of tailoring language processing capabilities for sp...

The article discusses NVIDIA NeMo, an end-to-end platform designed to facilitate the development and deployment of enterprise-ready large language models (LLMs).

Generative AI technologies are transforming the creation and interaction of non-playable characters (NPCs) in games, enabling developers to create more intelligent and dynamic gaming experiences.

NVIDIA introduces NeMo Guardrails, an open-source toolkit designed to create safe and trustworthy large language model (LLM) conversational systems.

NVIDIA has introduced generative AI services aimed at enhancing language, visual content, and biology applications.

GPT-4 is the latest milestone in OpenAI's deep learning efforts, showcasing a large multimodal model that accepts both image and text inputs.

The article discusses advancements in training language models to better follow user instructions, specifically focusing on the InstructGPT models developed by OpenAI.