Blog, Articles, and discussions

Community Articles

Granite 4.0 Nano: Just how small can you go?

and 1 other •

LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR

and 2 others •

The World’s First and Best Speed Painting Software

Why Did MiniMax M2 End Up as a Full Attention Model?

On the Shifting Global Compute Landscape

and 1 other •

🛡️ Nemotron PII: Synthesized Data for Privacy-Preserving AI

What makes good reasoning data

Cosmos Predict 2.5 & Transfer 2.5: Evolving the World Foundation Models for Physical AI

Code a simple RAG from scratch

NVIDIA Releases 8 Million Sample Open Dataset and Tooling for OCR, Image Reasoning, Image and Video QA Tasks

and 6 others •

Can Your LLM Think Like a Professional? Introducing ProfBench

and 7 others •

Aligning to What? Rethinking Agent Generalization in MiniMax M2

NVIDIA Isaac GR00T in LeRobot

and 4 others •

How to Build a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac for Healthcare

3+ Years of ML & Society at Hugging Face 🤗🤝🧑‍🤝‍🧑

and 3 others •

Projected Abliteration

Advancing Predictive ADMET Modeling Through Community-Driven Science: The ExpansionRx-OpenADMET Blind Challenge

and 1 other •

KV Caching Explained: Optimizing Transformer Inference Efficiency

Uncensor any LLM with abliteration

Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm

and 5 others •

videodatasetsmultimodal

TimeScope: How Long Can Your Video Large Multimodal Model Go?

loradiffusionguide

Fast LoRA inference for Flux with Diffusers and PEFT

collaborationguide

Arc Virtual Cell Challenge: A Primer

multi-agentshackathongradio

Consilium: When Multiple LLMs Collaborate

researchevaluationai

Back to The Future: Evaluating AI Agents on Predicting Future Events

+3

gradiomcpcommunity

Five Big Improvements to Gradio MCP Servers

llmnlpcommunity

Seq vs Seq: the Ettin Suite of Paired Encoders and Decoders

+2

storageinfrastructurecontent addressed store

Migrating the Hub from Git LFS to Xet

lerobotroboticsmodels

Asynchronous Robot Inference: Decoupling Action Prediction and Execution

+3

agentsguicommunity

ScreenEnv: Deploy your full stack Desktop Agent

communityopen-sourcemcp

Building the Hugging Face MCP Server

roboticscommunityopen-source

Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders

Creating custom kernels for the AMD MI300

Upskill your LLMs with Gradio MCP Servers

Community Articles

Granite 4.0 Nano: Just how small can you go?

and 1 other •

LightOnOCR-1B: The Case for End-to-End and Efficient Domain-Specific Vision-Language Models for OCR

and 2 others •

The World’s First and Best Speed Painting Software

Why Did MiniMax M2 End Up as a Full Attention Model?

On the Shifting Global Compute Landscape

and 1 other •

🛡️ Nemotron PII: Synthesized Data for Privacy-Preserving AI

What makes good reasoning data

Cosmos Predict 2.5 & Transfer 2.5: Evolving the World Foundation Models for Physical AI

Code a simple RAG from scratch

NVIDIA Releases 8 Million Sample Open Dataset and Tooling for OCR, Image Reasoning, Image and Video QA Tasks

and 6 others •

Can Your LLM Think Like a Professional? Introducing ProfBench

and 7 others •

Aligning to What? Rethinking Agent Generalization in MiniMax M2

NVIDIA Isaac GR00T in LeRobot

and 4 others •

How to Build a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac for Healthcare

3+ Years of ML & Society at Hugging Face 🤗🤝🧑‍🤝‍🧑

and 3 others •

Projected Abliteration

Advancing Predictive ADMET Modeling Through Community-Driven Science: The ExpansionRx-OpenADMET Blind Challenge

and 1 other •

KV Caching Explained: Optimizing Transformer Inference Efficiency

Uncensor any LLM with abliteration

Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm

and 5 others •

View all