Community Blog & Articles

Community Articles

Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI

Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding

SynthVision: Building a 110K Synthetic Medical VQA Dataset with Cross-Model Validation

ATE-2: State-of-the-Art Armenian Text Embeddings and the ArmBench-TextEmbed Benchmark

Raw Robot Video to VLA-Ready Training Data: Annotating LeRobot Datasets with Nomadic and HuggingFace Buckets

KV Caching Explained: Optimizing Transformer Inference Efficiency

LoRA Fine-Tuning BitNet b1.58 LLMs on Heterogeneous Edge GPUs via QVAC Fabric

Expanding the Alpamayo Open Platform for Developing Reasoning AVs Across Models, Data, and Simulation

Introducing AI chunking to semchunk

The First Healthcare Robotics Dataset and Foundational Physical AI Models for Healthcare Robotics

Uncensor any LLM with abliteration

NEO-unify: Building Native Multimodal Unified Models End to End

Beyond Semantic Similarity: Introducing NVIDIA NeMo Retriever’s Generalizable Agentic Retrieval Pipeline

Build an Agent That Thinks Like a Data Scientist: How We Hit #1 on DABStep with Reusable Tool Generation

Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face

Small Language Models (SLM): A Comprehensive Overview

Everything You Need to Know about Knowledge Distillation

From GRPO to DAPO and GSPO: What, Why, and How

How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons

How We Use Claude Code Skills to Run 1,000+ ML Experiments a Day

A New Framework for Evaluating Voice Agents (EVA)

Build a Domain-Specific Embedding Model in Under a Day

What's New in Mellea 0.4.0 + Granite Libraries Release

State of Open Source on Hugging Face: Spring 2026

Holotron-12B - High Throughput Computer Use Agent

hubstorageannouncement

Introducing Storage Buckets on the Hugging Face Hub

+8

Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries

+5

guidedistributed-trainingaccelerate

Ulysses Sequence Parallelism: Training with Million-Token Contexts

lerobotrobotics

LeRobot v0.5.0: Scaling Every Dimension

+6

Bringing Robotics AI to Embedded Platforms: Dataset Recording, VLA Fine‑Tuning, and On‑Device Optimizations

open-sourcediffusersgenerative

Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines

PRX Part 3 — Training a Text-to-Image Model in 24h!

mixture-of-expertsoptimizationtransformers

Mixture of Experts (MoEs) in Transformers

+3

February 26, 2026

communityopen-sourcellm

GGML and llama.cpp join HF to ensure the long-term progress of Local AI

+2

February 20, 2026

Community Articles

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

Nemotron 3 Nano 4B: A Compact Hybrid Model for Efficient Local AI

Introducing SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding

SynthVision: Building a 110K Synthetic Medical VQA Dataset with Cross-Model Validation

ATE-2: State-of-the-Art Armenian Text Embeddings and the ArmBench-TextEmbed Benchmark

Raw Robot Video to VLA-Ready Training Data: Annotating LeRobot Datasets with Nomadic and HuggingFace Buckets

KV Caching Explained: Optimizing Transformer Inference Efficiency

LoRA Fine-Tuning BitNet b1.58 LLMs on Heterogeneous Edge GPUs via QVAC Fabric

Expanding the Alpamayo Open Platform for Developing Reasoning AVs Across Models, Data, and Simulation

Introducing AI chunking to semchunk

The First Healthcare Robotics Dataset and Foundational Physical AI Models for Healthcare Robotics

Uncensor any LLM with abliteration

NEO-unify: Building Native Multimodal Unified Models End to End

Beyond Semantic Similarity: Introducing NVIDIA NeMo Retriever’s Generalizable Agentic Retrieval Pipeline

Build an Agent That Thinks Like a Data Scientist: How We Hit #1 on DABStep with Reusable Tool Generation

Fine-Tuning Your First Large Language Model (LLM) with PyTorch and Hugging Face

Small Language Models (SLM): A Comprehensive Overview

Everything You Need to Know about Knowledge Distillation

From GRPO to DAPO and GSPO: What, Why, and How

How I Trained Action Chunking Transformer (ACT) on SO-101: My Journey, Gotchas, and Lessons

How We Use Claude Code Skills to Run 1,000+ ML Experiments a Day

View all articles