Community Blog & Articles

Community Articles

Introducing the agentic robotics appstore for 10,000 Reachy Minis

QVAC MedPsy: State-of-the-Art Medical and Healthcare Language Models for Edge Devices

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

Improving Depth Anything V2 Robustness to Video Compression

KV Caching Explained: Optimizing Transformer Inference Efficiency

AI evals are becoming the new compute bottleneck

Learning Maths for the Last Time

Uncensor any LLM with abliteration

🧠 I trained my own French LLM from scratch — alone, with a 1080 Ti, and the power went out ⚡🇫🇷

CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models

Code a simple RAG from scratch

Mastering Tensor Dimensions in Transformers

Small Language Models (SLM): A Comprehensive Overview

There is no such thing as a tokenizer-free lunch

Running AI agents to automate outreach at scale

Build a legal RAG app that won't be held in contempt

Unbelievable! Run 70B LLM Inference on a Single 4GB GPU with This NEW Technique

BM25 for Python: Achieving high performance while simplifying dependencies with BM25S⚡

Understanding Vector Quantization in VQ-VAE

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

"OncoAgent: A Dual-Tier Multi-Agent Framework for Privacy-Preserving Oncology Clinical Decision Support"

EMO: Pretraining mixture of experts for emergent modularity

vLLM V0 to V1: Correctness Before Corrections in RL

audiospeechleaderboard

Adding Benchmaxxer Repellant to the Open ASR Leaderboard

+7

Granite 4.1 LLMs: How They’re Built

llmsinference-providersdeepinfra

DeepInfra on Hugging Face Inference Providers 🔥

+4

Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents

openaiprivacy-filterweb-apps

How to build scalable web apps with OpenAI's Privacy Filter

llmmoelong-context

DeepSeek-V4: a million-token context that agents can actually use

guidetransformers.jsjavascript

How to Use Transformers.js in a Chrome Extension

QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard

cybersecurityopen-sourcecommunity

AI and the Future of Cybersecurity: Why Openness Matters

reinforcement-learningrlvre-commerce

Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents

announcementmlxllm

The PR you would have opened yourself

Community Articles

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

Introducing the agentic robotics appstore for 10,000 Reachy Minis

QVAC MedPsy: State-of-the-Art Medical and Healthcare Language Models for Edge Devices

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

Improving Depth Anything V2 Robustness to Video Compression

KV Caching Explained: Optimizing Transformer Inference Efficiency

AI evals are becoming the new compute bottleneck

Learning Maths for the Last Time

Uncensor any LLM with abliteration

🧠 I trained my own French LLM from scratch — alone, with a 1080 Ti, and the power went out ⚡🇫🇷

CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models

Code a simple RAG from scratch

Mastering Tensor Dimensions in Transformers

Small Language Models (SLM): A Comprehensive Overview

There is no such thing as a tokenizer-free lunch

Running AI agents to automate outreach at scale

Build a legal RAG app that won't be held in contempt

Unbelievable! Run 70B LLM Inference on a Single 4GB GPU with This NEW Technique

BM25 for Python: Achieving high performance while simplifying dependencies with BM25S⚡

Understanding Vector Quantization in VQ-VAE

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

View all articles