corpus.blog
41554 blogs · [ { "id": "01a07d5d-72e7-7112-bd07-c15513b23bcd", "title": "SOTA OCR with Core ML and dots.ocr", "url": "https://huggingface.co/blog/dots-ocr-ne", "published_at": "2025-10-02T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15514721795", "title": "Introducing RTEB: A New Standard for Retrieval Evaluation", "url": "https://huggingface.co/blog/rteb", "published_at": "2025-10-01T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15514afa660", "title": "Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Models", "url": "https://huggingface.co/blog/intel-qwen3-agent", "published_at": "2025-09-29T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551543a3de", "title": "VibeGame: Exploring Vibe Coding Games", "url": "https://huggingface.co/blog/vibegame", "published_at": "2025-09-29T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15515ceb88c", "title": "Nemotron-Personas-Japan: ソブリン AI のための合成データセット", "url": "https://huggingface.co/blog/nvidia/nemotron-personas-japan-ja", "published_at": "2025-09-26T06:25:50+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15516a226de", "title": "Swift Transformers Reaches 1.0 – and Looks to the Future", "url": "https://huggingface.co/blog/swift-transformers", "published_at": "2025-09-26T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155172778d8", "title": "Smol2Operator: Post-Training GUI Agents for Computer Use", "url": "https://huggingface.co/blog/smol2operator", "published_at": "2025-09-23T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551739cb9e", "title": "SyGra: The One-Stop Framework for Building Data for LLMs and SLMs", "url": "https://huggingface.co/blog/ServiceNow-AI/sygra-data-gen-framework", "published_at": "2025-09-22T06:45:05+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155173c037c", "title": "Gaia2 and ARE: Empowering the community to study agents", "url": "https://huggingface.co/blog/gaia2", "published_at": "2025-09-22T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15517dec9c5", "title": "Scaleway on Hugging Face Inference Providers 🔥", "url": "https://huggingface.co/blog/inference-providers-scaleway", "published_at": "2025-09-19T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15518977455", "title": "Democratizing AI Safety with RiskRubric.ai", "url": "https://huggingface.co/blog/riskrubric", "published_at": "2025-09-18T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155197a8d4f", "title": "Public AI on Hugging Face Inference Providers 🔥", "url": "https://huggingface.co/blog/inference-providers-publicai", "published_at": "2025-09-17T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551a769042", "title": "`LeRobotDataset:v3.0`: Bringing large-scale datasets to `lerobot`", "url": "https://huggingface.co/blog/lerobot-datasets-v3", "published_at": "2025-09-16T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551b37a781", "title": "Visible Watermarking with Gradio", "url": "https://huggingface.co/blog/watermarking-with-gradio", "published_at": "2025-09-15T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551c2d61e8", "title": "Introducing the Palmyra-mini family: Powerful, lightweight, and ready to reason!", "url": "https://huggingface.co/blog/Writer/announcing-palmyra-mini", "published_at": "2025-09-11T20:04:44+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551c9d8577", "title": "Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers", "url": "https://huggingface.co/blog/faster-transformers", "published_at": "2025-09-11T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551d73fc67", "title": "Fine-tune Any LLM from the Hugging Face Hub with Together AI", "url": "https://huggingface.co/blog/togethercomputer/together-ft", "published_at": "2025-09-10T17:04:36+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551dfbcc96", "title": "Jupyter Agents: training LLMs to reason with notebooks", "url": "https://huggingface.co/blog/jupyter-agent-2", "published_at": "2025-09-10T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551edb23b9", "title": "mmBERT: ModernBERT goes Multilingual", "url": "https://huggingface.co/blog/mmbert", "published_at": "2025-09-09T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551f8c3fc1", "title": "Welcome EmbeddingGemma, Google's new efficient embedding model", "url": "https://huggingface.co/blog/embeddinggemma", "published_at": "2025-09-04T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551f9c3fea", "title": "SAIR: Accelerating Pharma R&D with AI-Powered Structural Intelligence", "url": "https://huggingface.co/blog/SandboxAQ/sair-data-accelerating-drug-discovery-with-ai", "published_at": "2025-09-02T16:54:29+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551fa0e3ef", "title": "Make your ZeroGPU Spaces go brrr with ahead-of-time compilation", "url": "https://huggingface.co/blog/zerogpu-aoti", "published_at": "2025-09-02T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1551ffbe2c2", "title": "NVIDIA Releases 6 Million Multi-Lingual Reasoning Dataset", "url": "https://huggingface.co/blog/nvidia/multilingual-reasoning-v1", "published_at": "2025-08-20T22:13:18+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15520cc68ae", "title": "Generate Images with Claude and Hugging Face", "url": "https://huggingface.co/blog/claude-and-mcp", "published_at": "2025-08-19T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155211546be", "title": "From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels", "url": "https://huggingface.co/blog/kernel-builder", "published_at": "2025-08-18T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15521f74fb6", "title": "MCP for Research: How to Connect AI to Research Tools", "url": "https://huggingface.co/blog/mcp-for-research", "published_at": "2025-08-18T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1552235dd75", "title": "Kimina-Prover-RL", "url": "https://huggingface.co/blog/AI-MO/kimina-prover-rl", "published_at": "2025-08-14T12:13:01+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1552271f57c", "title": "Arm & ExecuTorch 0.7: Bringing Generative AI to the masses", "url": "https://huggingface.co/blog/Arm/executorch-0-dot-7", "published_at": "2025-08-13T14:55:10+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15523115b79", "title": "Neural Super Sampling is here!", "url": "https://huggingface.co/blog/Arm/neural-super-sampling", "published_at": "2025-08-12T14:52:08+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155235e1c52", "title": "TextQuests: How Good are LLMs at Text-Based Video Games?", "url": "https://huggingface.co/blog/textquests", "published_at": "2025-08-12T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155240e53d2", "title": "🇵🇭 FilBench - Can LLMs Understand and Generate Filipino?", "url": "https://huggingface.co/blog/filbench", "published_at": "2025-08-12T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155241edfcc", "title": "Introducing AI Sheets: a tool to work with datasets using open AI models!", "url": "https://huggingface.co/blog/aisheets", "published_at": "2025-08-08T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15524c4bd0b", "title": "Accelerate ND-Parallel: A guide to Efficient Multi-GPU Training", "url": "https://huggingface.co/blog/accelerate-nd-parallel", "published_at": "2025-08-08T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155251f95c6", "title": "Vision Language Model Alignment in TRL ⚡️", "url": "https://huggingface.co/blog/trl-vlm-alignment", "published_at": "2025-08-07T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1552520b98c", "title": "Welcome GPT OSS, the new open-source model family from OpenAI!", "url": "https://huggingface.co/blog/welcome-openai-gpt-oss", "published_at": "2025-08-05T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1552606ec00", "title": "Measuring Open-Source Llama Nemotron Models on DeepResearch Bench", "url": "https://huggingface.co/blog/nvidia/ai-q-top-ranking-open-portable-deep-research-agent", "published_at": "2025-08-04T19:51:50+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c1552695f838", "title": "📚 3LM: A Benchmark for Arabic LLMs in STEM and Code", "url": "https://huggingface.co/blog/tiiuae/3lm-benchmark", "published_at": "2025-08-01T14:25:21+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155274de20b", "title": "Implementing MCP Servers in Python: An AI Shopping Assistant with Gradio", "url": "https://huggingface.co/blog/gradio-vton-mcp", "published_at": "2025-07-31T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c15527defc82", "title": "Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face", "url": "https://huggingface.co/blog/trackio", "published_at": "2025-07-29T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155286aa8af", "title": "Say hello to `hf`: a faster, friendlier Hugging Face CLI ✨", "url": "https://huggingface.co/blog/hf-cli", "published_at": "2025-07-25T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c155293768af", "title": "Parquet Content-Defined Chunking", "url": "https://huggingface.co/blog/parquet-cdc", "published_at": "2025-07-25T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92317e6ce8", "title": "TimeScope: How Long Can Your Video Large Multimodal Model Go?", "url": "https://huggingface.co/blog/timescope-video-lmm-benchmark", "published_at": "2025-07-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9232693bf3", "title": "Fast LoRA inference for Flux with Diffusers and PEFT", "url": "https://huggingface.co/blog/lora-fast", "published_at": "2025-07-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9232e21ed3", "title": "Accelerate a World of LLMs on Hugging Face with NVIDIA NIM", "url": "https://huggingface.co/blog/nvidia/multi-llm-nim", "published_at": "2025-07-21T18:01:30+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923391cf4a", "title": "Arc Virtual Cell Challenge: A Primer", "url": "https://huggingface.co/blog/virtual-cell-challenge", "published_at": "2025-07-18T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9233e4214b", "title": "Consilium: When Multiple LLMs Collaborate", "url": "https://huggingface.co/blog/consilium-multi-llm", "published_at": "2025-07-17T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9234db98d1", "title": "Back to The Future: Evaluating AI Agents on Predicting Future Events", "url": "https://huggingface.co/blog/futurebench", "published_at": "2025-07-17T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9235962094", "title": "Five Big Improvements to Gradio MCP Servers", "url": "https://huggingface.co/blog/gradio-mcp-updates", "published_at": "2025-07-17T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9235997c7b", "title": "Ettin Suite: SoTA Paired Encoders and Decoders", "url": "https://huggingface.co/blog/ettin", "published_at": "2025-07-16T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92359d34fd", "title": "Migrating the Hub from Git LFS to Xet", "url": "https://huggingface.co/blog/migrating-the-hub-to-xet", "published_at": "2025-07-15T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9235c98c01", "title": "Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models", "url": "https://huggingface.co/blog/AI-MO/kimina-prover", "published_at": "2025-07-10T12:54:19+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923628e943", "title": "Asynchronous Robot Inference: Decoupling Action Prediction and Execution", "url": "https://huggingface.co/blog/async-robot-inference", "published_at": "2025-07-10T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92362bd1b7", "title": "ScreenEnv: Deploy your full stack Desktop Agent", "url": "https://huggingface.co/blog/screenenv", "published_at": "2025-07-10T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923642da23", "title": "Building the Hugging Face MCP Server", "url": "https://huggingface.co/blog/building-hf-mcp", "published_at": "2025-07-10T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9236e407c4", "title": "Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Builders", "url": "https://huggingface.co/blog/reachy-mini", "published_at": "2025-07-09T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9237967faa", "title": "Creating custom kernels for the AMD MI300", "url": "https://huggingface.co/blog/mi300kernels", "published_at": "2025-07-09T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923808f2d2", "title": "Upskill your LLMs With Gradio MCP Servers", "url": "https://huggingface.co/blog/gradio-mcp-servers", "published_at": "2025-07-09T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92380de709", "title": "SmolLM3: smol, multilingual, long-context reasoner", "url": "https://huggingface.co/blog/smollm3", "published_at": "2025-07-08T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92389ae72a", "title": "Three Mighty Alerts Supporting Hugging Face’s Production Infrastructure", "url": "https://huggingface.co/blog/infrastructure-alerting", "published_at": "2025-07-08T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9238eb4813", "title": "Efficient MultiModal Data Pipeline", "url": "https://huggingface.co/blog/mmdp", "published_at": "2025-07-08T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9239875c6d", "title": "Announcing NeurIPS 2025 E2LM Competition: Early Training Evaluation of Language Models", "url": "https://huggingface.co/blog/tiiuae/e2lm-competition", "published_at": "2025-07-04T12:25:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923997e347", "title": "Training and Finetuning Sparse Embedding Models with Sentence Transformers", "url": "https://huggingface.co/blog/train-sparse-encoder", "published_at": "2025-07-01T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923a08258c", "title": "Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Hub", "url": "https://huggingface.co/blog/nvidia/llama-nemotron-nano-vl", "published_at": "2025-06-27T21:09:27+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923abfe0a8", "title": "Gemma 3n fully available in the open-source ecosystem!", "url": "https://huggingface.co/blog/gemma3n", "published_at": "2025-06-26T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923b2912b6", "title": "Transformers backend integration in SGLang", "url": "https://huggingface.co/blog/transformers-backend-sglang", "published_at": "2025-06-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923b62ca07", "title": "(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardware", "url": "https://huggingface.co/blog/flux-qlora", "published_at": "2025-06-19T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923bbe345d", "title": "Groq on Hugging Face Inference Providers 🔥", "url": "https://huggingface.co/blog/inference-providers-groq", "published_at": "2025-06-16T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923c4de3d5", "title": "How Long Prompts Block Other Requests - Optimizing LLM Performance", "url": "https://huggingface.co/blog/tngtech/llm-performance-blocked-by-long-prompts", "published_at": "2025-06-12T08:00:13+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923d0ca4c7", "title": "Learn the Hugging Face Kernel Hub in 5 Minutes", "url": "https://huggingface.co/blog/hello-hf-kernels", "published_at": "2025-06-12T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923d8524ea", "title": "Featherless AI on Hugging Face Inference Providers 🔥", "url": "https://huggingface.co/blog/inference-providers-featherless", "published_at": "2025-06-12T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923dad505c", "title": "Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Arm", "url": "https://huggingface.co/blog/nvidia/gr00t-n1-5-so101-tuning", "published_at": "2025-06-11T18:27:22+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923e2d08df", "title": "Introducing Training Cluster as a Service - a new collaboration with NVIDIA", "url": "https://huggingface.co/blog/nvidia-training-cluster", "published_at": "2025-06-11T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923ef76dca", "title": "ScreenSuite - The most comprehensive evaluation suite for GUI Agents!", "url": "https://huggingface.co/blog/screensuite", "published_at": "2025-06-06T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd923f899bb3", "title": "KV Cache from scratch in nanoVLM", "url": "https://huggingface.co/blog/kv-cache", "published_at": "2025-06-04T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92404cef3e", "title": "Real-Time AI Sound Generation on Arm: A Personal Tool for Creative Freedom", "url": "https://huggingface.co/blog/Arm/ai-sound-gen-on-arm", "published_at": "2025-06-03T15:04:36+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9240bc5eee", "title": "Holo1: New family of GUI automation VLMs powering GUI agent Surfer-H", "url": "https://huggingface.co/blog/Hcompany/holo1", "published_at": "2025-06-03T13:27:59+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9240e00d86", "title": "SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Data", "url": "https://huggingface.co/blog/smolvla", "published_at": "2025-06-03T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924102e368", "title": "No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRL", "url": "https://huggingface.co/blog/vllm-colocate", "published_at": "2025-06-03T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9241b43379", "title": "CodeAgents + Structure: A Better Way to Execute Actions", "url": "https://huggingface.co/blog/structured-codeagent", "published_at": "2025-05-28T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9241de69c7", "title": "🐯 Liger GRPO meets TRL", "url": "https://huggingface.co/blog/liger-grpo", "published_at": "2025-05-25T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92421d0aa5", "title": "Dell Enterprise Hub is all you need to build AI on premises", "url": "https://huggingface.co/blog/dell-ai-applications", "published_at": "2025-05-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92428011d4", "title": "Tiny Agents in Python: a MCP-powered agent in ~70 lines of code", "url": "https://huggingface.co/blog/python-tiny-agents", "published_at": "2025-05-23T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924294e73e", "title": "Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performance", "url": "https://huggingface.co/blog/tiiuae/falcon-h1", "published_at": "2025-05-21T06:52:13+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9242bc45ce", "title": "Falcon-Arabic: A Breakthrough in Arabic Language Models", "url": "https://huggingface.co/blog/tiiuae/falcon-arabic", "published_at": "2025-05-21T06:35:36+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924336773c", "title": "Exploring Quantization Backends in Diffusers", "url": "https://huggingface.co/blog/diffusers-quantization", "published_at": "2025-05-21T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9243bd2433", "title": "nanoVLM: The simplest repository to train your VLM in pure PyTorch", "url": "https://huggingface.co/blog/nanovlm", "published_at": "2025-05-21T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924427aff8", "title": "Microsoft and Hugging Face expand collaboration", "url": "https://huggingface.co/blog/azure-ai-foundry", "published_at": "2025-05-19T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92443211a2", "title": "Falcon-Edge: A series of powerful, universal, fine-tunable 1.58bit language models.", "url": "https://huggingface.co/blog/tiiuae/falcon-edge", "published_at": "2025-05-15T13:13:45+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924466841d", "title": "The Transformers Library: standardizing model definitions", "url": "https://huggingface.co/blog/transformers-model-definition", "published_at": "2025-05-15T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92451bc28b", "title": "Improving Hugging Face Model Access for Kaggle Users", "url": "https://huggingface.co/blog/kaggle-integration", "published_at": "2025-05-14T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92456a08ca", "title": "Blazingly fast whisper transcriptions with Inference Endpoints", "url": "https://huggingface.co/blog/fast-whisper-endpoints", "published_at": "2025-05-13T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92460d2f39", "title": "Vision Language Models (Better, faster, stronger)", "url": "https://huggingface.co/blog/vlms-2025", "published_at": "2025-05-12T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92469a6087", "title": "LeRobot Community Datasets: The “ImageNet” of Robotics — When and How?", "url": "https://huggingface.co/blog/lerobot-datasets", "published_at": "2025-05-11T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9246b919df", "title": "How to Build an MCP Server with Gradio", "url": "https://huggingface.co/blog/gradio-mcp", "published_at": "2025-04-30T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924791fb60", "title": "The 4 Things Qwen-3’s Chat Template Teaches Us", "url": "https://huggingface.co/blog/qwen-3-chat-template-deep-dive", "published_at": "2025-04-30T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd924832cbfd", "title": "Welcoming Llama Guard 4 on Hugging Face Hub", "url": "https://huggingface.co/blog/llama-guard-4", "published_at": "2025-04-29T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9248e58b00", "title": "Introducing AutoRound: Intel’s Advanced Quantization for LLMs and VLMs", "url": "https://huggingface.co/blog/autoround", "published_at": "2025-04-29T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92494f4e9a", "title": "PipelineRL", "url": "https://huggingface.co/blog/ServiceNow/pipelinerl", "published_at": "2025-04-25T22:37:16+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd92497c576f", "title": "Tiny Agents: an MCP-powered agent in 50 lines of code", "url": "https://huggingface.co/blog/tiny-agents", "published_at": "2025-04-25T00:00:00+00:00" }, { "id": "01a07d5d-72e8-7140-82cd-cd9249900bb0", "title": "Finetuning olmOCR to be a faithful OCR-Engine", "url": "https://huggingface.co/blog/tngtech/finetuning-olmocr-to-be-a-faithful-ocr-engine", "published_at": "2025-04-22T18:33:09+00:00" } ] posts Claim your blog
Back to Hugging Face
Blog · corpus.blog/blogs/huggingface.co/posts

Hugging Face

huggingface.co

2025

SOTA OCR with Core ML and dots.ocroriginal ↗
2 Oct 2025
Introducing RTEB: A New Standard for Retrieval Evaluationoriginal ↗
1 Oct 2025
Accelerating Qwen3-8B Agent on Intel® Core™ Ultra with Depth-Pruned Draft Modelsoriginal ↗
29 Sept 2025
VibeGame: Exploring Vibe Coding Gamesoriginal ↗
29 Sept 2025
Nemotron-Personas-Japan: ソブリン AI のための合成データセットoriginal ↗
26 Sept 2025
Swift Transformers Reaches 1.0 – and Looks to the Futureoriginal ↗
26 Sept 2025
Smol2Operator: Post-Training GUI Agents for Computer Useoriginal ↗
23 Sept 2025
SyGra: The One-Stop Framework for Building Data for LLMs and SLMsoriginal ↗
22 Sept 2025
Gaia2 and ARE: Empowering the community to study agentsoriginal ↗
22 Sept 2025
Scaleway on Hugging Face Inference Providers 🔥original ↗
19 Sept 2025
Democratizing AI Safety with RiskRubric.aioriginal ↗
18 Sept 2025
Public AI on Hugging Face Inference Providers 🔥original ↗
17 Sept 2025
`LeRobotDataset:v3.0`: Bringing large-scale datasets to `lerobot`original ↗
16 Sept 2025
Visible Watermarking with Gradiooriginal ↗
15 Sept 2025
Introducing the Palmyra-mini family: Powerful, lightweight, and ready to reason!original ↗
11 Sept 2025
Tricks from OpenAI gpt-oss YOU 🫵 can use with transformersoriginal ↗
11 Sept 2025
Fine-tune Any LLM from the Hugging Face Hub with Together AIoriginal ↗
10 Sept 2025
Jupyter Agents: training LLMs to reason with notebooksoriginal ↗
10 Sept 2025
mmBERT: ModernBERT goes Multilingualoriginal ↗
9 Sept 2025
Welcome EmbeddingGemma, Google's new efficient embedding modeloriginal ↗
4 Sept 2025
SAIR: Accelerating Pharma R&D with AI-Powered Structural Intelligenceoriginal ↗
2 Sept 2025
Make your ZeroGPU Spaces go brrr with ahead-of-time compilationoriginal ↗
2 Sept 2025
NVIDIA Releases 6 Million Multi-Lingual Reasoning Datasetoriginal ↗
20 Aug 2025
Generate Images with Claude and Hugging Faceoriginal ↗
19 Aug 2025
From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernelsoriginal ↗
18 Aug 2025
MCP for Research: How to Connect AI to Research Toolsoriginal ↗
18 Aug 2025
Kimina-Prover-RLoriginal ↗
14 Aug 2025
Arm & ExecuTorch 0.7: Bringing Generative AI to the massesoriginal ↗
13 Aug 2025
Neural Super Sampling is here!original ↗
12 Aug 2025
TextQuests: How Good are LLMs at Text-Based Video Games?original ↗
12 Aug 2025
🇵🇭 FilBench - Can LLMs Understand and Generate Filipino?original ↗
12 Aug 2025
Introducing AI Sheets: a tool to work with datasets using open AI models!original ↗
8 Aug 2025
Accelerate ND-Parallel: A guide to Efficient Multi-GPU Trainingoriginal ↗
8 Aug 2025
Vision Language Model Alignment in TRL ⚡️original ↗
7 Aug 2025
Welcome GPT OSS, the new open-source model family from OpenAI!original ↗
5 Aug 2025
Measuring Open-Source Llama Nemotron Models on DeepResearch Benchoriginal ↗
4 Aug 2025
📚 3LM: A Benchmark for Arabic LLMs in STEM and Codeoriginal ↗
1 Aug 2025
Implementing MCP Servers in Python: An AI Shopping Assistant with Gradiooriginal ↗
31 Jul 2025
Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Faceoriginal ↗
29 Jul 2025
Say hello to `hf`: a faster, friendlier Hugging Face CLI ✨original ↗
25 Jul 2025
Parquet Content-Defined Chunkingoriginal ↗
25 Jul 2025
TimeScope: How Long Can Your Video Large Multimodal Model Go?original ↗
23 Jul 2025
Fast LoRA inference for Flux with Diffusers and PEFToriginal ↗
23 Jul 2025
Accelerate a World of LLMs on Hugging Face with NVIDIA NIMoriginal ↗
21 Jul 2025
Arc Virtual Cell Challenge: A Primeroriginal ↗
18 Jul 2025
Consilium: When Multiple LLMs Collaborateoriginal ↗
17 Jul 2025
Back to The Future: Evaluating AI Agents on Predicting Future Eventsoriginal ↗
17 Jul 2025
Five Big Improvements to Gradio MCP Serversoriginal ↗
17 Jul 2025
Ettin Suite: SoTA Paired Encoders and Decodersoriginal ↗
16 Jul 2025
Migrating the Hub from Git LFS to Xetoriginal ↗
15 Jul 2025
Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Modelsoriginal ↗
10 Jul 2025
Asynchronous Robot Inference: Decoupling Action Prediction and Executionoriginal ↗
10 Jul 2025
ScreenEnv: Deploy your full stack Desktop Agentoriginal ↗
10 Jul 2025
Building the Hugging Face MCP Serveroriginal ↗
10 Jul 2025
Reachy Mini - The Open-Source Robot for Today's and Tomorrow's AI Buildersoriginal ↗
9 Jul 2025
Creating custom kernels for the AMD MI300original ↗
9 Jul 2025
Upskill your LLMs With Gradio MCP Serversoriginal ↗
9 Jul 2025
SmolLM3: smol, multilingual, long-context reasoneroriginal ↗
8 Jul 2025
Three Mighty Alerts Supporting Hugging Face’s Production Infrastructureoriginal ↗
8 Jul 2025
Efficient MultiModal Data Pipelineoriginal ↗
8 Jul 2025
Announcing NeurIPS 2025 E2LM Competition: Early Training Evaluation of Language Modelsoriginal ↗
4 Jul 2025
Training and Finetuning Sparse Embedding Models with Sentence Transformersoriginal ↗
1 Jul 2025
Welcome the NVIDIA Llama Nemotron Nano VLM to Hugging Face Huboriginal ↗
27 Jun 2025
Gemma 3n fully available in the open-source ecosystem!original ↗
26 Jun 2025
Transformers backend integration in SGLangoriginal ↗
23 Jun 2025
(LoRA) Fine-Tuning FLUX.1-dev on Consumer Hardwareoriginal ↗
19 Jun 2025
Groq on Hugging Face Inference Providers 🔥original ↗
16 Jun 2025
How Long Prompts Block Other Requests - Optimizing LLM Performanceoriginal ↗
12 Jun 2025
Learn the Hugging Face Kernel Hub in 5 Minutesoriginal ↗
12 Jun 2025
Featherless AI on Hugging Face Inference Providers 🔥original ↗
12 Jun 2025
Post-Training Isaac GR00T N1.5 for LeRobot SO-101 Armoriginal ↗
11 Jun 2025
Introducing Training Cluster as a Service - a new collaboration with NVIDIAoriginal ↗
11 Jun 2025
ScreenSuite - The most comprehensive evaluation suite for GUI Agents!original ↗
6 Jun 2025
KV Cache from scratch in nanoVLMoriginal ↗
4 Jun 2025
Real-Time AI Sound Generation on Arm: A Personal Tool for Creative Freedomoriginal ↗
3 Jun 2025
Holo1: New family of GUI automation VLMs powering GUI agent Surfer-Horiginal ↗
3 Jun 2025
SmolVLA: Efficient Vision-Language-Action Model trained on Lerobot Community Dataoriginal ↗
3 Jun 2025
No GPU left behind: Unlocking Efficiency with Co-located vLLM in TRLoriginal ↗
3 Jun 2025
CodeAgents + Structure: A Better Way to Execute Actionsoriginal ↗
28 May 2025
🐯 Liger GRPO meets TRLoriginal ↗
25 May 2025
Dell Enterprise Hub is all you need to build AI on premisesoriginal ↗
23 May 2025
Tiny Agents in Python: a MCP-powered agent in ~70 lines of codeoriginal ↗
23 May 2025
Falcon-H1: A Family of Hybrid-Head Language Models Redefining Efficiency and Performanceoriginal ↗
21 May 2025
Falcon-Arabic: A Breakthrough in Arabic Language Modelsoriginal ↗
21 May 2025
Exploring Quantization Backends in Diffusersoriginal ↗
21 May 2025
nanoVLM: The simplest repository to train your VLM in pure PyTorchoriginal ↗
21 May 2025
Microsoft and Hugging Face expand collaborationoriginal ↗
19 May 2025
Falcon-Edge: A series of powerful, universal, fine-tunable 1.58bit language models.original ↗
15 May 2025
The Transformers Library: standardizing model definitionsoriginal ↗
15 May 2025
Improving Hugging Face Model Access for Kaggle Usersoriginal ↗
14 May 2025
Blazingly fast whisper transcriptions with Inference Endpointsoriginal ↗
13 May 2025
Vision Language Models (Better, faster, stronger)original ↗
12 May 2025
LeRobot Community Datasets: The “ImageNet” of Robotics — When and How?original ↗
11 May 2025
How to Build an MCP Server with Gradiooriginal ↗
30 Apr 2025
The 4 Things Qwen-3’s Chat Template Teaches Usoriginal ↗
30 Apr 2025
Welcoming Llama Guard 4 on Hugging Face Huboriginal ↗
29 Apr 2025
Introducing AutoRound: Intel’s Advanced Quantization for LLMs and VLMsoriginal ↗
29 Apr 2025
PipelineRLoriginal ↗
25 Apr 2025
Tiny Agents: an MCP-powered agent in 50 lines of codeoriginal ↗
25 Apr 2025
Finetuning olmOCR to be a faithful OCR-Engineoriginal ↗
22 Apr 2025
Previous Next