corpus.blog
41554 blogs · [ { "id": "01a07d5d-72e7-7112-bd07-c154e74cbe96", "title": "Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents", "url": "https://huggingface.co/blog/nvidia/nemotron-3-nano-omni-multimodal-intelligence", "published_at": "2026-04-28T15:58:57+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e7cb9163", "title": "How to build scalable web apps with OpenAI's Privacy Filter", "url": "https://huggingface.co/blog/openai-privacy-filter-web-apps", "published_at": "2026-04-27T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e83101e1", "title": "DeepSeek-V4: a million-token context that agents can actually use", "url": "https://huggingface.co/blog/deepseekv4", "published_at": "2026-04-24T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e83464c3", "title": "How to Use Transformers.js in a Chrome Extension", "url": "https://huggingface.co/blog/transformersjs-chrome-extension", "published_at": "2026-04-23T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e8552c24", "title": "QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboard", "url": "https://huggingface.co/blog/tiiuae/qimma-arabic-leaderboard", "published_at": "2026-04-21T10:09:58+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e8c38ef5", "title": "AI and the Future of Cybersecurity: Why Openness Matters", "url": "https://huggingface.co/blog/cybersecurity-openness", "published_at": "2026-04-21T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e99ba078", "title": "Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agents", "url": "https://huggingface.co/blog/ecom-rlve", "published_at": "2026-04-16T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ea583b2d", "title": "The PR you would have opened yourself", "url": "https://huggingface.co/blog/transformers-to-mlx", "published_at": "2026-04-16T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ea65e5e0", "title": "Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformers", "url": "https://huggingface.co/blog/train-multimodal-sentence-transformers", "published_at": "2026-04-16T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ea6a6637", "title": "Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agents", "url": "https://huggingface.co/blog/ibm-research/vakra-benchmark-analysis", "published_at": "2026-04-15T12:07:25+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154eb44dabf", "title": "Meet HoloTab by HCompany. Your AI browser companion.", "url": "https://huggingface.co/blog/Hcompany/holotab", "published_at": "2026-04-15T09:25:20+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ec004c14", "title": "Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUs", "url": "https://huggingface.co/blog/waypoint-1-5", "published_at": "2026-04-09T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ec2af198", "title": "Multimodal Embedding & Reranker Models with Sentence Transformers", "url": "https://huggingface.co/blog/multimodal-sentence-transformers", "published_at": "2026-04-09T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154eca05e5b", "title": "Safetensors is Joining the PyTorch Foundation", "url": "https://huggingface.co/blog/safetensors-joins-pytorch-foundation", "published_at": "2026-04-08T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ecc9a77a", "title": "Welcome Gemma 4: Frontier multimodal intelligence on device", "url": "https://huggingface.co/blog/gemma4", "published_at": "2026-04-02T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ed74c0e7", "title": "Falcon Perception", "url": "https://huggingface.co/blog/tiiuae/falcon-perception", "published_at": "2026-04-01T07:13:20+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154edbaaf1e", "title": "Any Custom Frontend with Gradio's Backend", "url": "https://huggingface.co/blog/introducing-gradio-server", "published_at": "2026-04-01T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ee784af8", "title": "Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documents", "url": "https://huggingface.co/blog/ibm-granite/granite-4-vision", "published_at": "2026-03-31T15:10:41+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154eea9a3c9", "title": "Training mRNA Language Models Across 25 Species for $165", "url": "https://huggingface.co/blog/OpenMed/training-mrna-models-25-species", "published_at": "2026-03-31T08:23:44+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ef1ecb6c", "title": "TRL v1.0: Post-Training Library Built to Move with the Field", "url": "https://huggingface.co/blog/trl-v1", "published_at": "2026-03-31T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154efe4e397", "title": "Liberate your OpenClaw", "url": "https://huggingface.co/blog/liberate-your-openclaw", "published_at": "2026-03-27T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154effe90de", "title": "A New Framework for Evaluating Voice Agents (EVA)", "url": "https://huggingface.co/blog/ServiceNow-AI/eva", "published_at": "2026-03-24T02:01:52+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f01f2660", "title": "Build a Domain-Specific Embedding Model in Under a Day", "url": "https://huggingface.co/blog/nvidia/domain-specific-embedding-finetune", "published_at": "2026-03-20T19:38:16+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f04e994f", "title": "State of Open Source on Hugging Face: Spring 2026", "url": "https://huggingface.co/blog/huggingface/state-of-os-hf-spring-2026", "published_at": "2026-03-17T16:37:55+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f146f623", "title": "Holotron-12B - High Throughput Computer Use Agent", "url": "https://huggingface.co/blog/Hcompany/holotron-12b", "published_at": "2026-03-17T12:33:39+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f20e79e7", "title": "Introducing Storage Buckets on the Hugging Face Hub", "url": "https://huggingface.co/blog/storage-buckets", "published_at": "2026-03-10T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f28b93a6", "title": "Keep the Tokens Flowing: Lessons from 16 Open-Source RL Libraries", "url": "https://huggingface.co/blog/async-rl-training-landscape", "published_at": "2026-03-10T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f2a6029a", "title": "Ulysses Sequence Parallelism: Training with Million-Token Contexts", "url": "https://huggingface.co/blog/ulysses-sp", "published_at": "2026-03-09T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f3006407", "title": "LeRobot v0.5.0: Scaling Every Dimension", "url": "https://huggingface.co/blog/lerobot-release-v050", "published_at": "2026-03-09T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f3b9e32f", "title": "Bringing Robotics AI to Embedded Platforms: Dataset Recording, VLA Fine‑Tuning, and On‑Device Optimizations", "url": "https://huggingface.co/blog/nxp/bringing-robotics-ai-to-embedded-platforms", "published_at": "2026-03-05T14:16:49+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f3bfe0f0", "title": "Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelines", "url": "https://huggingface.co/blog/modular-diffusers", "published_at": "2026-03-05T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f4909476", "title": "PRX Part 3 — Training a Text-to-Image Model in 24h!", "url": "https://huggingface.co/blog/Photoroom/prx-part3", "published_at": "2026-03-03T16:50:49+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f4b1f1f9", "title": "Mixture of Experts (MoEs) in Transformers", "url": "https://huggingface.co/blog/moe-transformers", "published_at": "2026-02-26T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f599deea", "title": "GGML and llama.cpp join HF to ensure the long-term progress of Local AI", "url": "https://huggingface.co/blog/ggml-joins-hf", "published_at": "2026-02-20T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f66f2cc7", "title": "Train AI models with Unsloth and Hugging Face Jobs for FREE", "url": "https://huggingface.co/blog/unsloth-jobs", "published_at": "2026-02-20T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f6f22256", "title": "IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MAST", "url": "https://huggingface.co/blog/ibm-research/itbenchandmast", "published_at": "2026-02-18T16:15:45+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f7aa24ee", "title": "One-Shot Any Web App with Gradio's gr.HTML", "url": "https://huggingface.co/blog/gradio-html-one-shot-apps", "published_at": "2026-02-18T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f7d54944", "title": "Custom Kernels for All from Codex and Claude", "url": "https://huggingface.co/blog/custom-cuda-kernels-agent-skills", "published_at": "2026-02-13T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f7e55daf", "title": "OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World Environments", "url": "https://huggingface.co/blog/openenv-turing", "published_at": "2026-02-12T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f7fcb827", "title": "Transformers.js v4: Now Available on NPM!", "url": "https://huggingface.co/blog/transformersjs-v4", "published_at": "2026-02-09T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f862e471", "title": "Introducing SyGra Studio", "url": "https://huggingface.co/blog/ServiceNow-AI/sygra-studio", "published_at": "2026-02-05T16:52:28+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f8ae79b1", "title": "Community Evals: Because we're done trusting black-box leaderboards over the community", "url": "https://huggingface.co/blog/community-evals", "published_at": "2026-02-04T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f8af6138", "title": "H Company's new Holo2 model takes the lead in UI Localization", "url": "https://huggingface.co/blog/Hcompany/introducing-holo2-235b-a22b", "published_at": "2026-02-03T17:40:14+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f9890131", "title": "The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+", "url": "https://huggingface.co/blog/huggingface/one-year-since-the-deepseek-moment-blog-3", "published_at": "2026-02-03T15:03:19+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154f9ae84c0", "title": "Training Design for Text-to-Image Models: Lessons from Ablations", "url": "https://huggingface.co/blog/Photoroom/prx-part2", "published_at": "2026-02-03T11:25:53+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154faab5502", "title": "Introducing Daggr: Chain apps programmatically, inspect visually", "url": "https://huggingface.co/blog/daggr", "published_at": "2026-01-29T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154fb25600c", "title": "We Got Claude to Build CUDA Kernels and teach open models!", "url": "https://huggingface.co/blog/upskill", "published_at": "2026-01-28T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154fbd438c1", "title": "Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek ", "url": "https://huggingface.co/blog/huggingface/one-year-since-the-deepseek-moment-blog-2", "published_at": "2026-01-27T15:01:45+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154fcab1cc2", "title": "Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMs", "url": "https://huggingface.co/blog/tiiuae/emirati-benchmarks", "published_at": "2026-01-27T10:26:42+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154fcb04199", "title": "Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospective", "url": "https://huggingface.co/blog/LinkedIn/gpt-oss-agentic-rl", "published_at": "2026-01-27T01:53:15+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154fd6d892d", "title": "AssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial Reality", "url": "https://huggingface.co/blog/ibm-research/assetopsbench-playground-on-hugging-face", "published_at": "2026-01-21T06:25:31+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154fdadea54", "title": "One Year Since the “DeepSeek Moment”", "url": "https://huggingface.co/blog/huggingface/one-year-since-the-deepseek-moment", "published_at": "2026-01-20T15:02:10+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154fe101398", "title": "Differential Transformer V2", "url": "https://huggingface.co/blog/microsoft/diff-attn-v2", "published_at": "2026-01-20T03:20:57+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154fe2808be", "title": "Introducing Waypoint-1: Real-time interactive video diffusion from Overworld", "url": "https://huggingface.co/blog/waypoint-1", "published_at": "2026-01-20T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154fe735e3f", "title": "Open Responses: What you need to know", "url": "https://huggingface.co/blog/open-responses", "published_at": "2026-01-15T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ff1c23d7", "title": "NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AI", "url": "https://huggingface.co/blog/nvidia/nvidia-cosmos-reason-2-brings-advanced-reasoning", "published_at": "2026-01-05T22:56:51+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ff8cb6d7", "title": "Introducing Falcon-H1-Arabic: Pushing the Boundaries of Arabic Language AI with Hybrid Architecture", "url": "https://huggingface.co/blog/tiiuae/falcon-h1-arabic", "published_at": "2026-01-05T09:16:51+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155003792f7", "title": "NVIDIA brings agents to life with DGX Spark and Reachy Mini", "url": "https://huggingface.co/blog/nvidia-reachy-mini", "published_at": "2026-01-05T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155011543ad", "title": "AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systems", "url": "https://huggingface.co/blog/ServiceNow-AI/aprielguard", "published_at": "2025-12-23T14:07:35+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15501fcc034", "title": "Tokenization in Transformers v5: Simpler, Clearer, and More Modular", "url": "https://huggingface.co/blog/tokenizers", "published_at": "2025-12-18T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15502777bdd", "title": "The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluator", "url": "https://huggingface.co/blog/nvidia/nemotron-3-nano-evaluation-recipe", "published_at": "2025-12-17T13:22:18+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15502a67ef7", "title": "CUGA on Hugging Face: Democratizing Configurable AI Agents", "url": "https://huggingface.co/blog/ibm-research/cuga-on-hugging-face", "published_at": "2025-12-15T16:01:04+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15503750a5c", "title": "New in llama.cpp: Model Management", "url": "https://huggingface.co/blog/ggml-org/model-management-in-llamacpp", "published_at": "2025-12-11T15:47:44+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155037d5861", "title": "Codex is Open Sourcing AI models", "url": "https://huggingface.co/blog/hf-skills-training-codex", "published_at": "2025-12-11T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15503afd789", "title": "Introducing swift-huggingface: The Complete Swift Client for Hugging Face", "url": "https://huggingface.co/blog/swift-huggingface", "published_at": "2025-12-05T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155042cd726", "title": "DeepMath: A lightweight math reasoning Agent with smolagents", "url": "https://huggingface.co/blog/intel-deepmath", "published_at": "2025-12-04T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15504bf4cc5", "title": "We Got Claude to Fine-Tune an Open Source LLM", "url": "https://huggingface.co/blog/hf-skills-training", "published_at": "2025-12-04T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155058b046a", "title": "Transformers v5: Simple model definitions powering the AI ecosystem", "url": "https://huggingface.co/blog/transformers-v5", "published_at": "2025-12-01T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155064845fb", "title": "Diffusers welcomes FLUX-2", "url": "https://huggingface.co/blog/flux-2", "published_at": "2025-11-25T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155064eb936", "title": "Continuous batching from first principles", "url": "https://huggingface.co/blog/continuous_batching", "published_at": "2025-11-25T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15506b985b9", "title": "Building Deep Research: How we Achieved State of the Art", "url": "https://huggingface.co/blog/Tavily/tavily-deep-research", "published_at": "2025-11-24T17:40:14+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15506e2986f", "title": "OVHcloud on Hugging Face Inference Providers 🔥", "url": "https://huggingface.co/blog/OVHcloud/inference-providers-ovhcloud", "published_at": "2025-11-24T16:08:47+00:00" }, { "id": "01a0b653-445a-739b-8462-fde4b70cccf8", "title": "WildChat-2k: The Manually Curated Edition", "url": "https://huggingface.co/datasets/dpaleka/WildChat-2k-TypeTopic", "published_at": "2025-11-24T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550786f6aa", "title": "20x Faster TRL Fine-tuning with RapidFire AI", "url": "https://huggingface.co/blog/rapidfireai", "published_at": "2025-11-21T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15507a5954f", "title": "Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracks", "url": "https://huggingface.co/blog/open-asr-leaderboard", "published_at": "2025-11-21T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155088ca4d1", "title": "Introducing AnyLanguageModel: One API for Local and Remote LLMs on Apple Platforms", "url": "https://huggingface.co/blog/anylanguagemodel", "published_at": "2025-11-20T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15509381e6e", "title": "Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Models", "url": "https://huggingface.co/blog/ServiceNow-AI/apriel-h1", "published_at": "2025-11-19T05:19:07+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155094a362f", "title": "Easily Build and Share ROCm Kernels with Hugging Face", "url": "https://huggingface.co/blog/build-rocm-kernels", "published_at": "2025-11-17T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15509f36460", "title": "Join the AMD Open Robotics Hackathon", "url": "https://huggingface.co/blog/amd/openroboticshackathon", "published_at": "2025-11-13T21:37:26+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550a280d74", "title": "Building for an Open Future - our new partnership with Google Cloud", "url": "https://huggingface.co/blog/google-cloud", "published_at": "2025-11-13T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550a872dd7", "title": "Aligning to What? Rethinking Agent Generalization in MiniMax M2", "url": "https://huggingface.co/blog/MiniMax-AI/aligning-to-what", "published_at": "2025-10-30T10:03:45+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550b1496bb", "title": "On the Shifting Global Compute Landscape", "url": "https://huggingface.co/blog/huggingface/shifting-compute-landscape", "published_at": "2025-10-29T13:56:45+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550b51864a", "title": "Building a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac", "url": "https://huggingface.co/blog/lerobotxnvidia-healthcare", "published_at": "2025-10-29T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550bba03c1", "title": "How to Build a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac for Healthcare", "url": "https://huggingface.co/blog/nvidia/nvidia-isaac-for-healthcare", "published_at": "2025-10-28T20:42:35+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550c9d8bb3", "title": "Granite 4.0 Nano: Just how small can you go?", "url": "https://huggingface.co/blog/ibm-granite/granite-4-nano", "published_at": "2025-10-28T14:59:38+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550cd7176b", "title": "Voice Cloning with Consent", "url": "https://huggingface.co/blog/voice-consent-gate", "published_at": "2025-10-28T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550d03e95a", "title": "Streaming datasets: 100x More Efficient", "url": "https://huggingface.co/blog/streaming-datasets", "published_at": "2025-10-27T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550e016fe1", "title": "huggingface_hub v1.0: Five Years of Building the Foundation of Open Machine Learning", "url": "https://huggingface.co/blog/huggingface-hub-v1", "published_at": "2025-10-27T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550e4c3f78", "title": "LeRobot v0.4.0: Supercharging OSS Robot Learning", "url": "https://huggingface.co/blog/lerobot-release-v040", "published_at": "2025-10-24T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550ea2dbd4", "title": "Building the Open Agent Ecosystem Together: Introducing OpenEnv", "url": "https://huggingface.co/blog/openenv", "published_at": "2025-10-23T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1550f6242e4", "title": "Hugging Face and VirusTotal collaborate to strengthen AI security", "url": "https://huggingface.co/blog/virustotal", "published_at": "2025-10-22T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551010b85f", "title": "Sentence Transformers is joining Hugging Face!", "url": "https://huggingface.co/blog/sentence-transformers-joins-hf", "published_at": "2025-10-22T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15510ec817a", "title": "Supercharge your OCR Pipelines with Open Models", "url": "https://huggingface.co/blog/ocr-open-models", "published_at": "2025-10-21T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155113ab00b", "title": "Unlock the power of images with AI Sheets", "url": "https://huggingface.co/blog/aisheets-unlock-images", "published_at": "2025-10-21T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15511d982a5", "title": "AI for Food Allergies", "url": "https://huggingface.co/blog/hugging-science/ai-for-food-allergies", "published_at": "2025-10-16T22:38:11+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15512113d12", "title": "Google Cloud C4 Brings a 70% TCO improvement on GPT OSS with Intel and Hugging Face", "url": "https://huggingface.co/blog/gpt-oss-on-intel-xeon", "published_at": "2025-10-16T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551244dba1", "title": "Get your VLM running in 3 simple steps on Intel CPUs", "url": "https://huggingface.co/blog/openvino-vlm", "published_at": "2025-10-15T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15512b67633", "title": "Nemotron-Personas-India: Synthesized Data for Sovereign AI", "url": "https://huggingface.co/blog/nvidia/nemotron-personas-india", "published_at": "2025-10-13T23:00:42+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15512da93a1", "title": "Arm will be @ PyTorch Conference, Join Us!", "url": "https://huggingface.co/blog/Arm/arm-at-pytorch-conference", "published_at": "2025-10-10T17:35:04+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155132b4de8", "title": "BigCodeArena: Judging code generations end to end with code executions", "url": "https://huggingface.co/blog/bigcode/arena", "published_at": "2025-10-07T09:37:25+00:00" } ] posts Claim your blog
Back to Hugging Face
Blog · corpus.blog/blogs/huggingface.co/posts

Hugging Face

huggingface.co

2026

Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agentsoriginal ↗
28 Apr 2026
How to build scalable web apps with OpenAI's Privacy Filteroriginal ↗
27 Apr 2026
DeepSeek-V4: a million-token context that agents can actually useoriginal ↗
24 Apr 2026
How to Use Transformers.js in a Chrome Extensionoriginal ↗
23 Apr 2026
QIMMA قِمّة ⛰: A Quality-First Arabic LLM Leaderboardoriginal ↗
21 Apr 2026
AI and the Future of Cybersecurity: Why Openness Mattersoriginal ↗
21 Apr 2026
Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational Agentsoriginal ↗
16 Apr 2026
The PR you would have opened yourselforiginal ↗
16 Apr 2026
Training and Finetuning Multimodal Embedding & Reranker Models with Sentence Transformersoriginal ↗
16 Apr 2026
Inside VAKRA: Reasoning, Tool Use, and Failure Modes of Agentsoriginal ↗
15 Apr 2026
Meet HoloTab by HCompany. Your AI browser companion.original ↗
15 Apr 2026
Waypoint-1.5: Higher-Fidelity Interactive Worlds for Everyday GPUsoriginal ↗
9 Apr 2026
Multimodal Embedding & Reranker Models with Sentence Transformersoriginal ↗
9 Apr 2026
Safetensors is Joining the PyTorch Foundationoriginal ↗
8 Apr 2026
Welcome Gemma 4: Frontier multimodal intelligence on deviceoriginal ↗
2 Apr 2026
Falcon Perceptionoriginal ↗
1 Apr 2026
Any Custom Frontend with Gradio's Backendoriginal ↗
1 Apr 2026
Granite 4.0 3B Vision: Compact Multimodal Intelligence for Enterprise Documentsoriginal ↗
31 Mar 2026
Training mRNA Language Models Across 25 Species for $165original ↗
31 Mar 2026
TRL v1.0: Post-Training Library Built to Move with the Fieldoriginal ↗
31 Mar 2026
Liberate your OpenClaworiginal ↗
27 Mar 2026
A New Framework for Evaluating Voice Agents (EVA)original ↗
24 Mar 2026
Build a Domain-Specific Embedding Model in Under a Dayoriginal ↗
20 Mar 2026
State of Open Source on Hugging Face: Spring 2026original ↗
17 Mar 2026
Holotron-12B - High Throughput Computer Use Agentoriginal ↗
17 Mar 2026
Introducing Storage Buckets on the Hugging Face Huboriginal ↗
10 Mar 2026
Keep the Tokens Flowing: Lessons from 16 Open-Source RL Librariesoriginal ↗
10 Mar 2026
Ulysses Sequence Parallelism: Training with Million-Token Contextsoriginal ↗
9 Mar 2026
LeRobot v0.5.0: Scaling Every Dimensionoriginal ↗
9 Mar 2026
Bringing Robotics AI to Embedded Platforms: Dataset Recording, VLA Fine‑Tuning, and On‑Device Optimizationsoriginal ↗
5 Mar 2026
Introducing Modular Diffusers - Composable Building Blocks for Diffusion Pipelinesoriginal ↗
5 Mar 2026
PRX Part 3 — Training a Text-to-Image Model in 24h!original ↗
3 Mar 2026
Mixture of Experts (MoEs) in Transformersoriginal ↗
26 Feb 2026
GGML and llama.cpp join HF to ensure the long-term progress of Local AIoriginal ↗
20 Feb 2026
Train AI models with Unsloth and Hugging Face Jobs for FREEoriginal ↗
20 Feb 2026
IBM and UC Berkeley Diagnose Why Enterprise Agents Fail Using IT-Bench and MASToriginal ↗
18 Feb 2026
One-Shot Any Web App with Gradio's gr.HTMLoriginal ↗
18 Feb 2026
Custom Kernels for All from Codex and Claudeoriginal ↗
13 Feb 2026
OpenEnv in Practice: Evaluating Tool-Using Agents in Real-World Environmentsoriginal ↗
12 Feb 2026
Transformers.js v4: Now Available on NPM!original ↗
9 Feb 2026
Introducing SyGra Studiooriginal ↗
5 Feb 2026
Community Evals: Because we're done trusting black-box leaderboards over the communityoriginal ↗
4 Feb 2026
H Company's new Holo2 model takes the lead in UI Localizationoriginal ↗
3 Feb 2026
The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+original ↗
3 Feb 2026
Training Design for Text-to-Image Models: Lessons from Ablationsoriginal ↗
3 Feb 2026
Introducing Daggr: Chain apps programmatically, inspect visuallyoriginal ↗
29 Jan 2026
We Got Claude to Build CUDA Kernels and teach open models!original ↗
28 Jan 2026
Architectural Choices in China's Open-Source AI Ecosystem: Building Beyond DeepSeek original ↗
27 Jan 2026
Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMsoriginal ↗
27 Jan 2026
Unlocking Agentic RL Training for GPT-OSS: A Practical Retrospectiveoriginal ↗
27 Jan 2026
AssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial Realityoriginal ↗
21 Jan 2026
One Year Since the “DeepSeek Moment”original ↗
20 Jan 2026
Differential Transformer V2original ↗
20 Jan 2026
Introducing Waypoint-1: Real-time interactive video diffusion from Overworldoriginal ↗
20 Jan 2026
Open Responses: What you need to knoworiginal ↗
15 Jan 2026
NVIDIA Cosmos Reason 2 Brings Advanced Reasoning To Physical AIoriginal ↗
5 Jan 2026
Introducing Falcon-H1-Arabic: Pushing the Boundaries of Arabic Language AI with Hybrid Architectureoriginal ↗
5 Jan 2026
NVIDIA brings agents to life with DGX Spark and Reachy Minioriginal ↗
5 Jan 2026

2025

AprielGuard: A Guardrail for Safety and Adversarial Robustness in Modern LLM Systemsoriginal ↗
23 Dec 2025
Tokenization in Transformers v5: Simpler, Clearer, and More Modularoriginal ↗
18 Dec 2025
The Open Evaluation Standard: Benchmarking NVIDIA Nemotron 3 Nano with NeMo Evaluatororiginal ↗
17 Dec 2025
CUGA on Hugging Face: Democratizing Configurable AI Agentsoriginal ↗
15 Dec 2025
New in llama.cpp: Model Managementoriginal ↗
11 Dec 2025
Codex is Open Sourcing AI modelsoriginal ↗
11 Dec 2025
Introducing swift-huggingface: The Complete Swift Client for Hugging Faceoriginal ↗
5 Dec 2025
DeepMath: A lightweight math reasoning Agent with smolagentsoriginal ↗
4 Dec 2025
We Got Claude to Fine-Tune an Open Source LLMoriginal ↗
4 Dec 2025
Transformers v5: Simple model definitions powering the AI ecosystemoriginal ↗
1 Dec 2025
Diffusers welcomes FLUX-2original ↗
25 Nov 2025
Continuous batching from first principlesoriginal ↗
25 Nov 2025
Building Deep Research: How we Achieved State of the Artoriginal ↗
24 Nov 2025
OVHcloud on Hugging Face Inference Providers 🔥original ↗
24 Nov 2025
WildChat-2k: The Manually Curated Editionoriginal ↗
24 Nov 2025
20x Faster TRL Fine-tuning with RapidFire AIoriginal ↗
21 Nov 2025
Open ASR Leaderboard: Trends and Insights with New Multilingual & Long-Form Tracksoriginal ↗
21 Nov 2025
Introducing AnyLanguageModel: One API for Local and Remote LLMs on Apple Platformsoriginal ↗
20 Nov 2025
Apriel-H1: The Surprising Key to Distilling Efficient Reasoning Modelsoriginal ↗
19 Nov 2025
Easily Build and Share ROCm Kernels with Hugging Faceoriginal ↗
17 Nov 2025
Join the AMD Open Robotics Hackathonoriginal ↗
13 Nov 2025
Building for an Open Future - our new partnership with Google Cloudoriginal ↗
13 Nov 2025
Aligning to What? Rethinking Agent Generalization in MiniMax M2original ↗
30 Oct 2025
On the Shifting Global Compute Landscapeoriginal ↗
29 Oct 2025
Building a Healthcare Robot from Simulation to Deployment with NVIDIA Isaacoriginal ↗
29 Oct 2025
How to Build a Healthcare Robot from Simulation to Deployment with NVIDIA Isaac for Healthcareoriginal ↗
28 Oct 2025
Granite 4.0 Nano: Just how small can you go?original ↗
28 Oct 2025
Voice Cloning with Consentoriginal ↗
28 Oct 2025
Streaming datasets: 100x More Efficientoriginal ↗
27 Oct 2025
huggingface_hub v1.0: Five Years of Building the Foundation of Open Machine Learningoriginal ↗
27 Oct 2025
LeRobot v0.4.0: Supercharging OSS Robot Learningoriginal ↗
24 Oct 2025
Building the Open Agent Ecosystem Together: Introducing OpenEnvoriginal ↗
23 Oct 2025
Hugging Face and VirusTotal collaborate to strengthen AI securityoriginal ↗
22 Oct 2025
Sentence Transformers is joining Hugging Face!original ↗
22 Oct 2025
Supercharge your OCR Pipelines with Open Modelsoriginal ↗
21 Oct 2025
Unlock the power of images with AI Sheetsoriginal ↗
21 Oct 2025
AI for Food Allergiesoriginal ↗
16 Oct 2025
Google Cloud C4 Brings a 70% TCO improvement on GPT OSS with Intel and Hugging Faceoriginal ↗
16 Oct 2025
Get your VLM running in 3 simple steps on Intel CPUsoriginal ↗
15 Oct 2025
Nemotron-Personas-India: Synthesized Data for Sovereign AIoriginal ↗
13 Oct 2025
Arm will be @ PyTorch Conference, Join Us!original ↗
10 Oct 2025
BigCodeArena: Judging code generations end to end with code executionsoriginal ↗
7 Oct 2025
Previous Next