Community Blog & Articles

Community Articles

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

🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do

How NVIDIA AI-Q Reached \#1 on DeepResearch Bench I and II

MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning

How NVIDIA Builds Open Data for AI

Structural Problems in AI Benchmarking and the Case for a Unified Evaluation Framework

Uncensor any LLM with abliteration

The ML Engineer's Guide to Protein AI

KV Caching Explained: Optimizing Transformer Inference Efficiency

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

Konkani LLM: Bringing a Multi-Script Low-Resource Language to the AI Era

Building Tucano 2: Open-Source Language Models That Actually _Think_ in Portuguese

Kanon 2 Reranker: the most powerful reranker for legal RAG

Arabic TTS Arena: Ranking Voice Models the Way Chess Ranks Grandmasters

about 23 hours ago

Code a simple RAG from scratch

OpenMed: Six Months of Open-Source Medical AI and the Road Ahead

We’re open-sourcing our text-to-image model and the process behind it

Forge: Scalable Agent RL Framework and Algorithm

Deploying Open Source Vision Language Models (VLM) on Jetson

Scaling Pedagogical Pre-training: From Optimal Mixing to 10 Billion Tokens

leaderboardresearchcollaboration

Bringing the Artificial Analysis LLM Performance Leaderboard to Hugging Face

audioasrinference

Powerful ASR + diarization + speculative decoding with Hugging Face Inference Endpoints

evaluationcollaborationresearch

Improving Prompt Consistency with Structured Generations

nlpcommunityresearch

StarCoder2-Instruct: Fully Transparent and Permissive Self-Alignment for Code Generation

+5

leaderboardresearchcollaboration

Introducing the Open Chain of Thought Leaderboard

imitationrltransformers

Jack of All Trades, Master of Some, a Multi-Purpose Transformer Agent

leaderboardcollaborationresearch

The Open Medical-LLM Leaderboard: Benchmarking Large Language Models in Healthcare

nlpcommunityresearch

Welcome Llama 3 - Meta's new open LLM

+1

gradioopen-sourceguide

AI Apps in a Flash with Gradio's Reload Mode

leaderboardresearchcollaboration

Introducing the LiveCodeBench Leaderboard - Holistic and Contamination-Free Evaluation of Code LLMs

+3

guideprivacyresearch

Running Privacy-Preserving Inferences on Hugging Face Endpoints

Ryght’s Journey to Empower Healthcare and Life Sciences with Expert Support from Hugging Face

Introducing Idefics2: A Powerful 8B Vision-Language Model for the community

visionvlmmultimodal

Vision Language Models Explained

Community Articles

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

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

🏟️ Smol AI WorldCup: A 5-Axis Benchmark That Reveals What Small Language Models Can Really Do

How NVIDIA AI-Q Reached \#1 on DeepResearch Bench I and II

MARL: Runtime Middleware That Reduces LLM Hallucination Without Fine-Tuning

How NVIDIA Builds Open Data for AI

Structural Problems in AI Benchmarking and the Case for a Unified Evaluation Framework

Uncensor any LLM with abliteration

The ML Engineer's Guide to Protein AI

KV Caching Explained: Optimizing Transformer Inference Efficiency

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

Konkani LLM: Bringing a Multi-Script Low-Resource Language to the AI Era

Building Tucano 2: Open-Source Language Models That Actually _Think_ in Portuguese

Kanon 2 Reranker: the most powerful reranker for legal RAG

Arabic TTS Arena: Ranking Voice Models the Way Chess Ranks Grandmasters

about 23 hours ago

Code a simple RAG from scratch

OpenMed: Six Months of Open-Source Medical AI and the Road Ahead

We’re open-sourcing our text-to-image model and the process behind it

Forge: Scalable Agent RL Framework and Algorithm

Deploying Open Source Vision Language Models (VLM) on Jetson

Scaling Pedagogical Pre-training: From Optimal Mixing to 10 Billion Tokens

View all articles