Community Blog & Articles

Community Articles

OlmoEarth v1.1: A more efficient family of Earth observation models

Introducing the Ettin Reranker Family

Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation

PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend

The Open Agent Leaderboard

Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality

Unlocking asynchronicity in continuous batching

Building Blocks for Foundation Model Training and Inference on AWS

vLLM V0 to V1: Correctness Before Corrections in RL

Adding Benchmaxxer Repellant to the Open ASR Leaderboard

Granite 4.1 LLMs: How They’re Built

DeepInfra on Hugging Face Inference Providers 🔥

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

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

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

Community Blog & Articles

Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step

Vividh-ASR: Diagnosing and Fixing Studio-Bias in Whisper for Indic Languages

EMO: Pretraining mixture of experts for emergent modularity

Two Years of Local AI on a Laptop: When Open Models Outpaced Moore's Law

KV Caching Explained: Optimizing Transformer Inference Efficiency

Uncensor any LLM with abliteration

How to Comply with SOC 2 and ISO 27001 with Hugging Face: A Practical Guide to AI Model Supply Chain Governance

Software Forgets: Agent Traces Are the Memory

Code a simple RAG from scratch

Small Language Models (SLM): A Comprehensive Overview

A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond

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

Mastering Tensor Dimensions in Transformers

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

Norm-Preserving Biprojected Abliteration

Forge: Scalable Agent RL Framework and Algorithm

LLM Architectures Explained: What Powers Today’s Top Models

NVIDIA Isaac GR00T N1.7: Open Reasoning VLA Model for Humanoid Robots

Talking to a 4-Year-Old: A Multilingual Benchmark for Children's AI Companions

SSE Retrieval MRL v2: Regularization of Representation Space and Performance Improvement via Hyperparameter Optimization

OlmoEarth v1.1: A more efficient family of Earth observation models

Introducing the Ettin Reranker Family

Fine-Tuning NVIDIA Cosmos Predict 2.5 with LoRA/DoRA for Robot Video Generation

PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend

The Open Agent Leaderboard

Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality

Unlocking asynchronicity in continuous batching

Building Blocks for Foundation Model Training and Inference on AWS

vLLM V0 to V1: Correctness Before Corrections in RL

Adding Benchmaxxer Repellant to the Open ASR Leaderboard

Granite 4.1 LLMs: How They’re Built

DeepInfra on Hugging Face Inference Providers 🔥

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

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

Training-Free Reasoning at 88.89% on GPQA Diamond: How Darwin Family Hit Frontier Scores Without a Single Gradient Step

Vividh-ASR: Diagnosing and Fixing Studio-Bias in Whisper for Indic Languages

EMO: Pretraining mixture of experts for emergent modularity

Two Years of Local AI on a Laptop: When Open Models Outpaced Moore's Law

KV Caching Explained: Optimizing Transformer Inference Efficiency

Uncensor any LLM with abliteration

How to Comply with SOC 2 and ISO 27001 with Hugging Face: A Practical Guide to AI Model Supply Chain Governance

Software Forgets: Agent Traces Are the Memory

Code a simple RAG from scratch

Small Language Models (SLM): A Comprehensive Overview

A Guide to Reinforcement Learning Post-Training for LLMs: PPO, DPO, GRPO, and Beyond

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

Mastering Tensor Dimensions in Transformers

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

Norm-Preserving Biprojected Abliteration

Forge: Scalable Agent RL Framework and Algorithm

LLM Architectures Explained: What Powers Today’s Top Models

NVIDIA Isaac GR00T N1.7: Open Reasoning VLA Model for Humanoid Robots

Talking to a 4-Year-Old: A Multilingual Benchmark for Children's AI Companions

SSE Retrieval MRL v2: Regularization of Representation Space and Performance Improvement via Hyperparameter Optimization