Community Blog & Articles

Community Articles

The Open Source Community is backing OpenEnv for Agentic RL

Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI

EVA-Bench Data 2.0: 3 Domains, 121 Tools, 213 Scenarios

Designing the hf CLI as an agent-optimized way to work with the Hub

Direct Preference Optimization Beyond Chatbots

Adding MCP Tools to Reachy Mini

Holo3.1: Fast & Local Computer Use Agents

Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains

Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic

Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler

Reachy Mini goes fully local

Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL

Harness, Scaffold, and the AI Agent Terms Worth Getting Right

OlmoEarth v1.1: A more efficient family of Earth observation models

NEW Articles from Team or Enterprise organizations will get promoted to the main section.

Community Blog & Articles

How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

Fine-tune FLUX.2 [klein] with a LoRA under 60 minutes

Task-Seeded Synthetic Q&A Generation for Nemotron Pretraining

Taking Alpamayo to New Heights with Driving Foundation Models and Closed-Loop Training

Her · हेर — a detective for your Claude Code sessions

Introduction to Trimming ✂

MiniMax Goes Sparse: Decoding M3's Attention from a Single Diagram

A Deep Neural Network that turns Any Image into a Playable Game! All on consumer GPUs, NOT DATACENTER

Code a simple RAG from scratch

LeRobot Humanoid: An Open, Low-Cost, 3D-Printed Humanoid for Robot Learning

Thousand Token Wood: shipping a multi-agent economy on a 3B model

Job Searcher

Norm-Preserving Biprojected Abliteration

ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM

Agentic RL: Token-In, Token-Out Done Right

Build Small Hackathon With Cohere Models

AutoResearch on Diffusers' Pipeline for 10 Rounds on JarvisLabs

Run Claude Code, OpenCode & Frontier Coding Models on Your Own AI Infrastructure with DEH

Five labs, five minds: building a multi-model finance drama on small models

The Open Source Community is backing OpenEnv for Agentic RL

Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI

EVA-Bench Data 2.0: 3 Domains, 121 Tools, 213 Scenarios

Designing the hf CLI as an agent-optimized way to work with the Hub

Direct Preference Optimization Beyond Chatbots

Adding MCP Tools to Reachy Mini

Holo3.1: Fast & Local Computer Use Agents

Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains

Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic

Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler

Reachy Mini goes fully local

Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL

Harness, Scaffold, and the AI Agent Terms Worth Getting Right

OlmoEarth v1.1: A more efficient family of Earth observation models

How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent

Welcome NVIDIA Cosmos 3: The First Open Omni-model for Physical AI Reasoning and Action

Fine-tune FLUX.2 [klein] with a LoRA under 60 minutes

Task-Seeded Synthetic Q&A Generation for Nemotron Pretraining

Taking Alpamayo to New Heights with Driving Foundation Models and Closed-Loop Training

Her · हेर — a detective for your Claude Code sessions

Introduction to Trimming ✂

MiniMax Goes Sparse: Decoding M3's Attention from a Single Diagram

A Deep Neural Network that turns Any Image into a Playable Game! All on consumer GPUs, NOT DATACENTER

Code a simple RAG from scratch

LeRobot Humanoid: An Open, Low-Cost, 3D-Printed Humanoid for Robot Learning

Thousand Token Wood: shipping a multi-agent economy on a 3B model

Job Searcher

Norm-Preserving Biprojected Abliteration

ITBench-AA: Frontier Models Score Below 50% on the First Benchmark for Agentic Enterprise IT Tasks — by Artificial Analysis and IBM

Agentic RL: Token-In, Token-Out Done Right

Build Small Hackathon With Cohere Models

AutoResearch on Diffusers' Pipeline for 10 Rounds on JarvisLabs

Run Claude Code, OpenCode & Frontier Coding Models on Your Own AI Infrastructure with DEH

Five labs, five minds: building a multi-model finance drama on small models