Hugging Face Blog

@hugging-face-blog

huggingface.co/blog

Articles (110)

Hugging Face Blog1d ago7 min

Towards Speed-of-Light Text Generation with Nemotron-Labs Diffusion Language Models

0

Hugging Face Blog1d ago13 min

Specialization Beats Scale: A Strategic Variable Most AI Procurement Decisions Overlook

0

Hugging Face Blog4d ago5 min

OlmoEarth v1.1: A more efficient family of models

0

Hugging Face Blog5d ago29 min

Introducing the Ettin Reranker Family

0

Hugging Face Blog5d ago13 min

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

0

Hugging Face Blog5d ago5 min

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

0

Hugging Face Blog5d ago9 min

The Open Agent Leaderboard

0

Hugging Face BlogMay 1417 min

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

0

Hugging Face BlogMay 1419 min

Unlocking asynchronicity in continuous batching

0

Hugging Face BlogMay 1120 min

Building Blocks for Foundation Model Training and Inference on AWS

0

Hugging Face BlogMay 106 min

MachinaCheck: Building a Multi-Agent CNC Manufacturability System on AMD MI300X

0

Hugging Face BlogMay 914 min

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

0

Hugging Face BlogMay 89 min

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

0

Hugging Face BlogMay 89 min

EMO: Pretraining mixture of experts for emergent modularity

0

Hugging Face BlogMay 88 min

MedQA: Fine-Tuning a Clinical AI on AMD ROCm — No CUDA Required

0

Hugging Face BlogMay 68 min

vLLM V0 to V1: Correctness Before Corrections in RL

0

Hugging Face BlogMay 67 min

Adding Benchmaxxer Repellant to the Open ASR Leaderboard

0

Hugging Face BlogApr 2918 min

AI evals are becoming the new compute bottleneck

0

Hugging Face BlogApr 2914 min

Granite 4.1 LLMs: How They’re Built

0

Hugging Face BlogApr 295 min

DeepInfra on Hugging Face Inference Providers 🔥

0

Hugging Face BlogApr 2816 min

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

0

Hugging Face BlogApr 285 min

Adaptive Ultrasound Imaging with Physics-Informed NV-Raw2Insights-US AI

0

Hugging Face BlogApr 278 min

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

0

Hugging Face BlogApr 248 min

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

0

Hugging Face BlogApr 239 min

How to Use Transformers.js in a Chrome Extension

0

Hugging Face BlogApr 228 min

Gemma 4 VLA Demo on Jetson Orin Nano Super

0

Hugging Face BlogApr 219 min

QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard

0

Hugging Face BlogApr 218 min

How to Ground a Korean AI Agent in Real Demographics with Synthetic Personas

0

Hugging Face BlogApr 216 min

AI and the Future of Cybersecurity: Why Openness Matters

0

Hugging Face BlogApr 1712 min

Building a Fast Multilingual OCR Model with Synthetic Data

0

Hugging Face BlogApr 1618 min

Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers

0

Hugging Face BlogApr 1612 min

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

0

Hugging Face BlogApr 1612 min

The PR you would have opened yourself

0

Hugging Face BlogApr 1515 min

Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents

0

Hugging Face BlogApr 153 min

Meet HoloTab by HCompany. Your AI browser companion.

0

Hugging Face BlogApr 915 min

Multimodal Embedding & Reranker Models with Sentence Transformers

0

Hugging Face BlogApr 95 min

Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs

0

Hugging Face BlogApr 86 min

ALTK‑Evolve: On‑the‑Job Learning for AI Agents

0

Hugging Face BlogApr 84 min

Safetensors is Joining the PyTorch Foundation

0

Hugging Face BlogApr 226 min

Welcome Gemma 4: Frontier multimodal intelligence on device

0

Hugging Face BlogApr 14 min

Holo3: Breaking the Computer Use Frontier

0

Hugging Face BlogApr 115 min

Falcon Perception

0

Hugging Face BlogApr 16 min

Any Custom Frontend with Gradio's Backend

0

Hugging Face BlogMar 317 min

Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents

0

Hugging Face BlogMar 3130 min

Training mRNA Language Models Across 25 Species for $165

0

Hugging Face BlogMar 3116 min

TRL v1.0: Post-Training Library That Holds When the Field Invalidates Its Own Assumptions

0

Hugging Face BlogMar 273 min

Liberate your OpenClaw

0

Hugging Face BlogMar 2410 min

A New Framework for Evaluating Voice Agents (EVA)

0

Hugging Face BlogMar 2013 min

Build a Domain-Specific Embedding Model in Under a Day

0

Hugging Face BlogMar 203 min

What's New in Mellea 0.4.0 + Granite Libraries Release

0

Hugging Face BlogMar 1911 min

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

0

Hugging Face BlogMar 178 min

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

0

Hugging Face BlogMar 1713 min

State of Open Source on Hugging Face: Spring 2026

0

Hugging Face BlogMar 175 min

Holotron-12B - High Throughput Computer Use Agent

0

Hugging Face BlogMar 165 min

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

0

Hugging Face BlogMar 138 min

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

0

Hugging Face BlogMar 1310 min

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

0

Hugging Face BlogMar 129 min

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

0

Hugging Face BlogMar 114 min

Code Concepts: A Large-Scale Synthetic Dataset Generated from Programming Concept Seeds

0

Hugging Face BlogMar 108 min

How NVIDIA Builds Open Data for AI

0

Hugging Face BlogMar 1030 min

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

0

Hugging Face BlogMar 107 min

Introducing Storage Buckets on the Hugging Face Hub

0

Hugging Face BlogMar 92 min

Granite 4.0 1B Speech: Compact, Multilingual, and Built for the Edge

0

Hugging Face BlogMar 915 min

Ulysses Sequence Parallelism: Training with Million-Token Contexts

0

Hugging Face BlogMar 910 min

LeRobot v0.5.0: Scaling Every Dimension

0

Hugging Face BlogMar 67 min

Conversational LLM Evaluations in Minutes with NVIDIA NeMo Evaluator Agent Skills

0

Hugging Face BlogMar 59 min

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

0

Hugging Face BlogMar 59 min

Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines

0

Hugging Face BlogMar 38 min

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

0

Hugging Face BlogFeb 2610 min

Mixture of Experts (MoEs) in Transformers

0

Hugging Face BlogFeb 248 min

Deploying Open Source Vision Language Models (VLM) on Jetson

0

Hugging Face BlogFeb 205 min

Train AI models with Unsloth and Hugging Face Jobs for FREE

0

Hugging Face BlogFeb 204 min

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

0

Hugging Face BlogFeb 192 min

「データ不足」の壁を越える：合成ペルソナが日本のAI開発を加速

0

Hugging Face BlogFeb 1811 min

IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST

0

Hugging Face BlogFeb 184 min

One-Shot Any Web App with Gradio's gr.HTML

0

Hugging Face BlogFeb 172 min

NVIDIA Nemotron 2 Nano 9B Japanese: 日本のソブリンAIを支える最先端小規模言語モデル

0

Hugging Face BlogFeb 139 min

Custom Kernels for All from Codex and Claude

0

Hugging Face BlogFeb 128 min

OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World Environments

0

Hugging Face BlogFeb 96 min

Transformers.js v4 Preview: Now Available on NPM!

0

Hugging Face BlogFeb 54 min

Introducing SyGra Studio

0

Hugging Face BlogFeb 45 min

Nemotron ColEmbed V2: Raising the Bar for Multimodal Retrieval with ViDoRe V3’s Top Model

0

Hugging Face BlogFeb 44 min

Community Evals: Because we're done trusting black-box leaderboards over the community

0

Hugging Face BlogFeb 32 min

H Company's new Holo2 model takes the lead in UI Localization

0

Hugging Face BlogFeb 38 min

The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+

0

Hugging Face BlogFeb 330 min

Training Design for Text-to-Image Models: Lessons from Ablations

0

Hugging Face BlogJan 297 min

Introducing NVIDIA Cosmos Policy for Advanced Robot Control

0

Hugging Face BlogJan 298 min

Introducing Daggr: Chain apps programmatically, inspect visually

0

Hugging Face BlogJan 285 min

Nemotron-Personas-Brazil: Co-Designed Data for Sovereign AI

0

Hugging Face BlogJan 2810 min

We Got Claude to Build CUDA Kernels and teach open models!

0

Hugging Face BlogJan 276 min

Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek

0

Hugging Face BlogJan 278 min

Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMs

0

Hugging Face BlogJan 2716 min

Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective

0

Hugging Face BlogJan 264 min

NVIDIA Earth-2 Open Models Span the Whole Weather Stack

0

Hugging Face BlogJan 216 min

AssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial Reality

0

Hugging Face BlogJan 208 min

One Year Since the “DeepSeek Moment”

0

Hugging Face BlogJan 2014 min

Differential Transformer V2

0

Hugging Face BlogJan 204 min

Introducing Waypoint-1: Real-time interactive video diffusion from Overworld

0

Hugging Face BlogJan 152 min

Introducing OptiMind, a research model designed for optimization

0

Hugging Face BlogJan 156 min

Open Responses: What you need to know

0

Hugging Face BlogJan 67 min

Small Yet Mighty: Improve Accuracy In Multimodal Search and Visual Document Retrieval with Llama Nemotron RAG Models

0

Hugging Face BlogJan 56 min

NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI

0

Hugging Face BlogJan 59 min

Introducing Falcon-H1-Arabic: Pushing the Boundaries of Arabic Language AI with Hybrid Architecture

0

Hugging Face BlogJan 511 min

NVIDIA brings agents to life with DGX Spark and Reachy Mini

0

Hugging Face BlogDec 2310 min

AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems

0

Hugging Face BlogDec 1815 min

Tokenization in Transformers v5: Simpler, Clearer, and More Modular

0

Hugging Face BlogDec 1712 min

The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator

0

Hugging Face BlogDec 155 min

CUGA on Hugging Face: Democratizing Configurable AI Agents

0

Hugging Face BlogDec 119 min

New in llama.cpp: Model Management

0

Hugging Face BlogDec 1113 min

Codex is Open Sourcing AI models

0