Community Blog & Articles

Community Articles

Build a Robot Pick-and-Place Simulation with SimReady Assets

XYBench: Helping with the problem behind the question

llama.cpp v1.0.0 : A stronger foundation for the local AI ecosystem

LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B

The Definitive Fine-Tuning Guide for 3D Generation Models

BotPsy: On-Device Personal Assistant with a Sub-Billion-Parameter Agentic Language Model

Token Pooling-Aware Training for Multi-Vector Embedding Models

Pay for Hugging Face Hub with your Google Cloud Account

Decision Models in Hugging Face

Your Experts Have Partners. There's HOPE for Keeping Them Together

Egyptian and Nigerian English join the Open ASR Leaderboard

A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.

Dharma Field Extractor: Any Document In, Structured Fields in JSON Out

Palette: teaching a small model to build decks in your design language

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

Community Blog & Articles

Introducing Salesforce SOV-Transcribe-1: #1 Open-Weight Model Built for Real-World Speech

Harness adapters: Safe RL for efficient agentic development

New NVIDIA Cosmos 3 Open Models for Interactive World Simulation

ToyBlocks: A controlled world for robot learning and evaluation

Nemotron-Personas-Finance-Japan: A Synthetic Dataset Capturing Japan's Demographics and Financial Context

MotionGraphicsBench: Evaluating Motion Graphics Generation with Programmatic Verification

Yang-Mills, OpenAI proof, and the mass gap problem

Nemotron-Personas-Finance-Japan: 日本の人口分布と金融コンテキストを捉える合成ペルソナデータセット

Bring Your Own Expert! Extending MoE Models with New Domain Expertise

Uncensor any LLM with abliteration

On-Device Speech Recognition and Text-to-Speech in Google AI Edge Gallery

ZONOS3-Mini: Open-Source Real-Time Voice Cloning & Steerable TTS in 100M Active Parameters

Which Weather Model Is Most Accurate? We Score Them Every Day, in the Open

SafetyPulse: Catching Safety Drift During Fine-Tuning by Reading the Model's Refusal Circuit

MOSS-Live: A Full-Duplex Real-Time Interaction System

KV Caching Explained: Optimizing Transformer Inference Efficiency

Qai x Hugging Face Hackathon

*Evaluating Privacy Protection and Practical AI Applications with 100,000 Synthetic Business Documents Across Eight Domains*

NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction

Stop Paying the Embedding Tax: Why Simple BM25 + Seb Beats 8B Vector RAG on Quality, Speed, and Cost

Build a Robot Pick-and-Place Simulation with SimReady Assets

XYBench: Helping with the problem behind the question

llama.cpp v1.0.0 : A stronger foundation for the local AI ecosystem

LLMON: An LLM-Native Markup Language, now in Granite 4.1 3B and 8B

The Definitive Fine-Tuning Guide for 3D Generation Models

BotPsy: On-Device Personal Assistant with a Sub-Billion-Parameter Agentic Language Model

Token Pooling-Aware Training for Multi-Vector Embedding Models

Pay for Hugging Face Hub with your Google Cloud Account

Decision Models in Hugging Face

Your Experts Have Partners. There's HOPE for Keeping Them Together

Egyptian and Nigerian English join the Open ASR Leaderboard

A Closer Look at Phonon TTS. Launching High-Quality On-Device Speech That Tops the Benchmarks.

Dharma Field Extractor: Any Document In, Structured Fields in JSON Out

Palette: teaching a small model to build decks in your design language

Introducing Salesforce SOV-Transcribe-1: #1 Open-Weight Model Built for Real-World Speech

Harness adapters: Safe RL for efficient agentic development

New NVIDIA Cosmos 3 Open Models for Interactive World Simulation

ToyBlocks: A controlled world for robot learning and evaluation

Nemotron-Personas-Finance-Japan: A Synthetic Dataset Capturing Japan's Demographics and Financial Context

MotionGraphicsBench: Evaluating Motion Graphics Generation with Programmatic Verification

Yang-Mills, OpenAI proof, and the mass gap problem

Nemotron-Personas-Finance-Japan: 日本の人口分布と金融コンテキストを捉える合成ペルソナデータセット

Bring Your Own Expert! Extending MoE Models with New Domain Expertise

Uncensor any LLM with abliteration

On-Device Speech Recognition and Text-to-Speech in Google AI Edge Gallery

ZONOS3-Mini: Open-Source Real-Time Voice Cloning & Steerable TTS in 100M Active Parameters

Which Weather Model Is Most Accurate? We Score Them Every Day, in the Open

SafetyPulse: Catching Safety Drift During Fine-Tuning by Reading the Model's Refusal Circuit

MOSS-Live: A Full-Duplex Real-Time Interaction System

KV Caching Explained: Optimizing Transformer Inference Efficiency

Qai x Hugging Face Hackathon

*Evaluating Privacy Protection and Practical AI Applications with 100,000 Synthetic Business Documents Across Eight Domains*

NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular Prediction

Stop Paying the Embedding Tax: Why Simple BM25 + Seb Beats 8B Vector RAG on Quality, Speed, and Cost

Evaluating Privacy Protection and Practical AI Applications with 100,000 Synthetic Business Documents Across Eight Domains

Evaluating Privacy Protection and Practical AI Applications with 100,000 Synthetic Business Documents Across Eight Domains