corpus.blog
41554 blogs · [ { "id": "01a0d8d5-10e9-7170-a0a0-ae845acc15a4", "title": "Accelerating vision-language models with LFM2.5-VL-DSpark", "url": "https://huggingface.co/blog/LiquidAI/lfm2-5-vl-dspark", "published_at": "2026-09-24T14:08:57+00:00" }, { "id": "01a0d8d5-10ea-7048-aa79-0396652d69df", "title": "How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows", "url": "https://huggingface.co/blog/nvidia/how-to-use-nvidia-warp-and-mjwarp", "published_at": "2026-09-23T18:41:40+00:00" }, { "id": "01a0d8d5-10ea-7048-aa79-039665436068", "title": "How UK AISI and EvalEval Are Making Benchmark Results Reproducible", "url": "https://huggingface.co/blog/evaleval-aisi", "published_at": "2026-09-22T00:00:00+00:00" }, { "id": "01a0d8d5-10ea-7048-aa79-0396657626dc", "title": "Transformers now runs llama.cpp quants", "url": "https://huggingface.co/blog/transformers-llama-cpp-quants", "published_at": "2026-09-22T00:00:00+00:00" }, { "id": "01a0d8d5-10ea-7048-aa79-03966607b359", "title": "Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community", "url": "https://huggingface.co/blog/omlx", "published_at": "2026-09-22T00:00:00+00:00" }, { "id": "01a0d8d5-10ea-7048-aa79-039666b7d7b4", "title": "Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem", "url": "https://huggingface.co/blog/MultiverseComputingCAI/pruning-llms-like-a-physicist-block-removal-as-an", "published_at": "2026-09-21T13:44:34+00:00" }, { "id": "01a0d8d5-10ea-7048-aa79-039667b5f367", "title": "tokenizers v1: encode, decode and scaling, measured", "url": "https://huggingface.co/blog/tokenizers-v1", "published_at": "2026-09-21T00:00:00+00:00" }, { "id": "01a0b955-0823-717e-a936-82a7571e2bec", "title": "Your Agent Aced the Task. Will It Do It Again?", "url": "https://huggingface.co/blog/ibm-research/altk-evolve-consistency", "published_at": "2026-09-15T16:00:44+00:00" }, { "id": "01a08caa-7484-7010-b1fd-c7001d62b318", "title": "Rebuilding AUTOMATIC1111 with Gradio Workflow", "url": "https://huggingface.co/blog/gradio-workflow-1111", "published_at": "2026-09-10T00:00:00+00:00" }, { "id": "01a0b955-0823-717e-a936-82a757dfe2ab", "title": "Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL", "url": "https://huggingface.co/blog/asyncgrpo-lora-hfjobs", "published_at": "2026-09-10T00:00:00+00:00" }, { "id": "01a08784-866a-73cd-9541-23e5218c3ca9", "title": "IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license", "url": "https://huggingface.co/blog/ibm-research/ibm-releases-sota-granite-time-series", "published_at": "2026-09-09T15:36:24+00:00" }, { "id": "01a08216-f9ec-708d-bff0-8da2ff5180fa", "title": "Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic", "url": "https://huggingface.co/blog/MultiverseComputingCAI/safety-for-whom", "published_at": "2026-09-08T14:23:07+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf0c74b1cd", "title": "NeoMME: an efficient Multimodal-native and Multilingual Encoder", "url": "https://huggingface.co/blog/Hcompany/neomme", "published_at": "2026-09-03T13:13:48+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf0d595aed", "title": "Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps", "url": "https://huggingface.co/blog/grpo-with-trl-ifstruct", "published_at": "2026-09-03T00:00:00+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf0df90342", "title": "Give Your Coding Agents a Memory You Own", "url": "https://huggingface.co/blog/funes", "published_at": "2026-09-03T00:00:00+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf0e91e0b5", "title": "Training a coding model to paint watercolours with TRL and OpenEnv", "url": "https://huggingface.co/blog/train-to-paint-with-code", "published_at": "2026-09-03T00:00:00+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf0ea72ee3", "title": "Real-Time Intelligence with IBM Time Series Models on Confluent", "url": "https://huggingface.co/blog/ibm-research/real-time-intelligence", "published_at": "2026-09-02T13:49:14+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf0f11c7e5", "title": "BenchMIRT: What are LLM benchmarks actually measuring?", "url": "https://huggingface.co/blog/allenai/benchmirt", "published_at": "2026-09-01T21:39:07+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf0fdcfb57", "title": "Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI", "url": "https://huggingface.co/blog/webgpu-kernels", "published_at": "2026-09-01T00:00:00+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf104f4317", "title": "The Open ASR Leaderboard Adds Its First Global South Language", "url": "https://huggingface.co/blog/open-asr-leaderboard-global-south", "published_at": "2026-08-28T00:00:00+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf1071b9ce", "title": "Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers", "url": "https://huggingface.co/blog/train-multi-vector-encoder", "published_at": "2026-08-26T00:00:00+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf114e9037", "title": "Granite 4.2 LLMs: How They're Built", "url": "https://huggingface.co/blog/ibm-granite/granite-4-2", "published_at": "2026-08-25T15:14:14+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf11d5b74e", "title": "Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original", "url": "https://huggingface.co/blog/MultiverseComputingCAI/quantization-aware-healing", "published_at": "2026-08-25T11:39:24+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf12bd20e4", "title": "Wire It, Run It, Deploy It: AI Workflows in Gradio", "url": "https://huggingface.co/blog/gradio-workflow-guide", "published_at": "2026-08-25T00:00:00+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf12dbe689", "title": "How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code", "url": "https://huggingface.co/blog/pwc-search", "published_at": "2026-08-21T00:00:00+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf13091dd5", "title": "Measuring benchmark optimization in speech recognition", "url": "https://huggingface.co/blog/asr-benchmark-optimization", "published_at": "2026-08-21T00:00:00+00:00" }, { "id": "01a07d5d-72e6-7217-9c80-63cf13887c58", "title": "Up to 3.2x Faster Inference with LFM2.5-DSpark", "url": "https://huggingface.co/blog/LiquidAI/lfm25-dspark", "published_at": "2026-08-20T16:52:57+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154bf8ecd7d", "title": "How Much Memory Does Your Agent Actually Need?", "url": "https://huggingface.co/blog/ibm-research/altk-evolve-hmm", "published_at": "2026-08-18T18:09:38+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154bf9f8673", "title": "Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers", "url": "https://huggingface.co/blog/multi-vector-encoder", "published_at": "2026-08-18T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c08d5743", "title": "Same Cluster, 33 Points More Utilization: What Changed Was the Order", "url": "https://huggingface.co/blog/Dharma-AI/gpu-management-pt2", "published_at": "2026-08-17T19:46:21+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c127dea4", "title": "State of Open Models: Summer 2026 Observations", "url": "https://huggingface.co/blog/state-of-open-models-summer-2026", "published_at": "2026-08-14T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c1718c3f", "title": "Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets", "url": "https://huggingface.co/blog/amazon/strands-lerobot-streaming-data-loop", "published_at": "2026-08-13T17:16:04+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c1d65003", "title": "What We Learned by Reproducing 2,200 papers from ICML", "url": "https://huggingface.co/blog/icml-2026-open-reproductions", "published_at": "2026-08-13T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c29ec01a", "title": "Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis", "url": "https://huggingface.co/blog/allenai/olmoearth-embeddings", "published_at": "2026-08-12T16:14:36+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c37dda80", "title": "Thinking of ACE? We Can Do It with Fewer Tokens", "url": "https://huggingface.co/blog/ibm-research/altk-evolve-sldd", "published_at": "2026-08-11T13:37:10+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c3940af6", "title": "Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS", "url": "https://huggingface.co/blog/nvidia/magpie-tts-multilingual-voice-agents", "published_at": "2026-08-10T16:25:36+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c3f1ebc4", "title": "Making Knowledge Distillation Cheap Enough to Run at Scale", "url": "https://huggingface.co/blog/MultiverseComputingCAI/efficient-knowledge-distillation", "published_at": "2026-08-10T10:05:36+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c4a39fc1", "title": "Meta is back with Muse Glimmer: local, agentic, multimodal, and open source", "url": "https://huggingface.co/blog/muse-glimmer", "published_at": "2026-08-10T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c587ad6f", "title": "Baseten on Hugging Face Inference Providers 🔥", "url": "https://huggingface.co/blog/baseten", "published_at": "2026-08-06T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c5c415ed", "title": "GPU Management: Why Idle GPUs Are the New Grounded Aircraft", "url": "https://huggingface.co/blog/Dharma-AI/gpu-management", "published_at": "2026-07-30T15:09:09+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c614d8f3", "title": "NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics", "url": "https://huggingface.co/blog/nvidia/cosmos-h-dreams", "published_at": "2026-07-27T09:32:20+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c70ff64e", "title": "Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident", "url": "https://huggingface.co/blog/agent-intrusion-technical-timeline", "published_at": "2026-07-27T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c77e3701", "title": "Bringing Nunchaku 4-bit Diffusion Inference to Diffusers", "url": "https://huggingface.co/blog/nunchaku-diffusers", "published_at": "2026-07-23T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c7ccba9b", "title": "Grabette: an open system to record robot-manipulation data", "url": "https://huggingface.co/blog/grabette", "published_at": "2026-07-21T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c88e1a13", "title": "Newer Models, Same Advantage", "url": "https://huggingface.co/blog/Dharma-AI/newer-models-same-advantages", "published_at": "2026-07-16T11:49:48+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154c94d46b6", "title": "Security incident disclosure — July 2026", "url": "https://huggingface.co/blog/security-incident-july-2026", "published_at": "2026-07-16T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ca1fb4cf", "title": "Model Routing Is Simple. Until It Isn’t.", "url": "https://huggingface.co/blog/ibm-research/model-routing-is-simple-until-it-isnt", "published_at": "2026-07-15T17:27:01+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ca832010", "title": "Welcome Inkling by Thinking Machines", "url": "https://huggingface.co/blog/thinkingmachines-inkling", "published_at": "2026-07-15T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154cb3506ed", "title": "Introducing Real World VoiceEQ: Measuring the human quality of voice AI", "url": "https://huggingface.co/blog/real-world-voiceeq", "published_at": "2026-07-15T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154cb87306a", "title": "Profiling in PyTorch (Part 3): Attention is all you profile", "url": "https://huggingface.co/blog/torch-attention-profile", "published_at": "2026-07-10T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154cc421bcf", "title": "Native-speed vLLM transformers modeling backend", "url": "https://huggingface.co/blog/native-speed-vllm-transformers-backend", "published_at": "2026-07-08T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154cc9c5cdc", "title": "From Hugging Face to Amazon SageMaker Studio in one click", "url": "https://huggingface.co/blog/amazon/one-click-to-sagemaker-studio", "published_at": "2026-07-07T21:15:33+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154cd92b73c", "title": "Hugging Face Models on Foundry Managed Compute", "url": "https://huggingface.co/blog/microsoft/foundry-managed-compute", "published_at": "2026-07-07T15:20:06+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154cd933bfe", "title": "Run AI workloads on any cloud, store on Hugging Face: zero-egress storage with SkyPilot", "url": "https://huggingface.co/blog/skypilot-hf-storage", "published_at": "2026-07-07T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ce56f6dd", "title": "LeRobot v0.6.0: Imagine, Evaluate, Improve", "url": "https://huggingface.co/blog/lerobot-release-v060", "published_at": "2026-07-07T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154cec1a0dc", "title": "PRX Part 4: Our Data Strategy", "url": "https://huggingface.co/blog/Photoroom/prx-part4-data", "published_at": "2026-07-06T15:30:55+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154cecab42e", "title": "🤗 Kernels: Major Updates", "url": "https://huggingface.co/blog/revamped-kernels", "published_at": "2026-07-06T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154cf590bb1", "title": "Hugging Face and Cerebras bring Gemma 4 to real-time voice AI", "url": "https://huggingface.co/blog/cerebras-gemma4-voice-ai", "published_at": "2026-07-01T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154cfd852d5", "title": "ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration", "url": "https://huggingface.co/blog/ibm-research/scarfbench", "published_at": "2026-06-30T18:32:50+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d0b6d9dc", "title": "Why Specialization Is Inevitable", "url": "https://huggingface.co/blog/Dharma-AI/why-specialization-is-inevitable", "published_at": "2026-06-30T14:39:11+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d176f727", "title": "Featuring Every Eval Ever Results on Hugging Face Model Pages", "url": "https://huggingface.co/blog/eee-community-evals", "published_at": "2026-06-30T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d243928b", "title": "DiScoFormer: One transformer for density and score, across distributions", "url": "https://huggingface.co/blog/allenai/discoformer", "published_at": "2026-06-29T18:02:48+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d2ff175e", "title": "Run a vLLM Server on HF Jobs in One Command", "url": "https://huggingface.co/blog/vllm-jobs", "published_at": "2026-06-26T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d3be76c3", "title": "Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModel", "url": "https://huggingface.co/blog/nvidia/accelerating-fine-tuning-nvidia-nemo-automodel", "published_at": "2026-06-24T16:00:13+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d4bd6561", "title": "Introducing the FFASR Leaderboard: Benchmarking ASR in the Real World", "url": "https://huggingface.co/blog/ffasr-leaderboard", "published_at": "2026-06-24T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d58b58f1", "title": "Shipping huggingface_hub every week with AI, open tools, and a human in the loop", "url": "https://huggingface.co/blog/huggingface-hub-release-ci", "published_at": "2026-06-23T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d66dd4c7", "title": "Experimenting with the proposed Cross-Origin Storage API in Transformers.js", "url": "https://huggingface.co/blog/cross-origin-storage", "published_at": "2026-06-23T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d7152a3e", "title": "PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parameters", "url": "https://huggingface.co/blog/PaddlePaddle/pp-ocrv6", "published_at": "2026-06-22T13:18:56+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d715be50", "title": "We got local models to triage the OpenClaw repo for FREE!*", "url": "https://huggingface.co/blog/local-models-pr-triage", "published_at": "2026-06-22T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d7b93579", "title": "MosaicLeaks: Can your research agent keep a secret?", "url": "https://huggingface.co/blog/ServiceNow/mosaicleaks", "published_at": "2026-06-18T18:13:13+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d88ff920", "title": "Beyond LoRA: Can you beat the most popular fine-tuning technique?", "url": "https://huggingface.co/blog/peft-beyond-lora", "published_at": "2026-06-18T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d8e0a482", "title": "Is it agentic enough? Benchmarking open models on your own tooling", "url": "https://huggingface.co/blog/is-it-agentic-enough", "published_at": "2026-06-18T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d96d8b8e", "title": "From the Hugging Face Hub to robot hardware with Strands Agents and LeRobot", "url": "https://huggingface.co/blog/amazon/strands-lerobot-hub-to-hardware", "published_at": "2026-06-17T10:18:05+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d9830a04", "title": "GLM-5.2: Built for Long-Horizon Tasks", "url": "https://huggingface.co/blog/zai-org/glm-52-blog", "published_at": "2026-06-17T09:01:25+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154d99d0f5c", "title": "Agentic Resource Discovery: Let agents search", "url": "https://huggingface.co/blog/agentic-resource-discovery-launch", "published_at": "2026-06-17T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154da0a2800", "title": "Profiling in PyTorch (Part 2): From nn.Linear to a Fused MLP", "url": "https://huggingface.co/blog/torch-mlp-fusion", "published_at": "2026-06-11T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154daf01ba2", "title": "How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spaces", "url": "https://huggingface.co/blog/mishig/spaces-agents-md", "published_at": "2026-06-09T10:46:19+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154dbcbcfbb", "title": "Migrating Your GitHub CI to Hugging Face Jobs", "url": "https://huggingface.co/blog/github-ci-hf-jobs", "published_at": "2026-06-09T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154dc4cc724", "title": "The Open Source Community is backing OpenEnv for Agentic RL", "url": "https://huggingface.co/blog/openenv-agentic-rl", "published_at": "2026-06-08T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154dcfbf452", "title": "Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AI", "url": "https://huggingface.co/blog/nvidia/nemotron-3-5-content-safety", "published_at": "2026-06-04T18:57:45+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154dd9342b6", "title": "Designing the hf CLI as an agent-optimized way to work with the Hub", "url": "https://huggingface.co/blog/hf-cli-for-agents", "published_at": "2026-06-04T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154ddff44fe", "title": "Direct Preference Optimization Beyond Chatbots", "url": "https://huggingface.co/blog/Dharma-AI/direct-preference-optimization-beyond-chatbots", "published_at": "2026-06-03T12:55:11+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154de0fd276", "title": "Adding MCP Tools to Reachy Mini", "url": "https://huggingface.co/blog/adding-mcp-tools-to-reachy-mini", "published_at": "2026-06-03T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154de794c6a", "title": "Holo3.1: Fast & Local Computer Use Agents", "url": "https://huggingface.co/blog/Hcompany/holo31", "published_at": "2026-06-02T14:13:23+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154de89a980", "title": "Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrains", "url": "https://huggingface.co/blog/JetBrains/mellum2-launch", "published_at": "2026-06-01T15:45:17+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154df56e841", "title": "Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic", "url": "https://huggingface.co/blog/ibm-research/agent-logic-and-scalable-ai-adoption", "published_at": "2026-06-01T13:51:18+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154dff41878", "title": "Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profiler", "url": "https://huggingface.co/blog/torch-profiler", "published_at": "2026-05-29T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e0d21191", "title": "Reachy Mini goes fully local", "url": "https://huggingface.co/blog/local-reachy-mini-conversation", "published_at": "2026-05-27T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e14c4d45", "title": "Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRL", "url": "https://huggingface.co/blog/delta-weight-sync", "published_at": "2026-05-27T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e213f47e", "title": "Harness, Scaffold, and the AI Agent Terms Worth Getting Right", "url": "https://huggingface.co/blog/agent-glossary", "published_at": "2026-05-25T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e2bdafca", "title": "OlmoEarth v1.1: A more efficient family of Earth observation models", "url": "https://huggingface.co/blog/allenai/olmoearth-v1-1", "published_at": "2026-05-19T18:38:09+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e39e0e1b", "title": "Introducing the Ettin Reranker Family", "url": "https://huggingface.co/blog/ettin-reranker", "published_at": "2026-05-19T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e3afcd1a", "title": "PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backend", "url": "https://huggingface.co/blog/PaddlePaddle/paddleocr-transformers", "published_at": "2026-05-18T15:12:46+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e3bf7f66", "title": "Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality", "url": "https://huggingface.co/blog/ibm-granite/granite-embedding-multilingual-r2", "published_at": "2026-05-14T18:55:01+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e49e8ed8", "title": "Unlocking asynchronicity in continuous batching", "url": "https://huggingface.co/blog/continuous_async", "published_at": "2026-05-14T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e4c77123", "title": "Building Blocks for Foundation Model Training and Inference on AWS", "url": "https://huggingface.co/blog/amazon/foundation-model-building-blocks", "published_at": "2026-05-11T23:18:26+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e5a2bcda", "title": "vLLM V0 to V1: Correctness Before Corrections in RL", "url": "https://huggingface.co/blog/ServiceNow-AI/correctness-before-corrections", "published_at": "2026-05-06T19:06:55+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e602797e", "title": "Adding Benchmaxxer Repellant to the Open ASR Leaderboard", "url": "https://huggingface.co/blog/open-asr-leaderboard-private-data", "published_at": "2026-05-06T00:00:00+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e61a12a8", "title": "Granite 4.1 LLMs: How They’re Built", "url": "https://huggingface.co/blog/ibm-granite/granite-4-1", "published_at": "2026-04-29T15:01:48+00:00" }, { "id": "01a07d5d-72e7-7112-bd07-c154e69624dd", "title": "DeepInfra on Hugging Face Inference Providers 🔥", "url": "https://huggingface.co/blog/inference-providers-deepinfra", "published_at": "2026-04-29T00:00:00+00:00" } ] posts Claim your blog
Back to Hugging Face
Blog · corpus.blog/blogs/huggingface.co/posts

Hugging Face

huggingface.co

2026

Accelerating vision-language models with LFM2.5-VL-DSparkoriginal ↗
24 Sept 2026
How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflowsoriginal ↗
23 Sept 2026
How UK AISI and EvalEval Are Making Benchmark Results Reproducibleoriginal ↗
22 Sept 2026
Transformers now runs llama.cpp quantsoriginal ↗
22 Sept 2026
Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX communityoriginal ↗
22 Sept 2026
Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problemoriginal ↗
21 Sept 2026
tokenizers v1: encode, decode and scaling, measuredoriginal ↗
21 Sept 2026
Your Agent Aced the Task. Will It Do It Again?original ↗
15 Sept 2026
Rebuilding AUTOMATIC1111 with Gradio Workfloworiginal ↗
10 Sept 2026
Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCLoriginal ↗
10 Sept 2026
IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly licenseoriginal ↗
9 Sept 2026
Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topicoriginal ↗
8 Sept 2026
NeoMME: an efficient Multimodal-native and Multilingual Encoderoriginal ↗
3 Sept 2026
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Stepsoriginal ↗
3 Sept 2026
Give Your Coding Agents a Memory You Ownoriginal ↗
3 Sept 2026
Training a coding model to paint watercolours with TRL and OpenEnvoriginal ↗
3 Sept 2026
Real-Time Intelligence with IBM Time Series Models on Confluentoriginal ↗
2 Sept 2026
BenchMIRT: What are LLM benchmarks actually measuring?original ↗
1 Sept 2026
Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AIoriginal ↗
1 Sept 2026
The Open ASR Leaderboard Adds Its First Global South Languageoriginal ↗
28 Aug 2026
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformersoriginal ↗
26 Aug 2026
Granite 4.2 LLMs: How They're Builtoriginal ↗
25 Aug 2026
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision originaloriginal ↗
25 Aug 2026
Wire It, Run It, Deploy It: AI Workflows in Gradiooriginal ↗
25 Aug 2026
How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Codeoriginal ↗
21 Aug 2026
Measuring benchmark optimization in speech recognitionoriginal ↗
21 Aug 2026
Up to 3.2x Faster Inference with LFM2.5-DSparkoriginal ↗
20 Aug 2026
How Much Memory Does Your Agent Actually Need?original ↗
18 Aug 2026
Multi-Vector (Late Interaction) Embedding Models with Sentence Transformersoriginal ↗
18 Aug 2026
Same Cluster, 33 Points More Utilization: What Changed Was the Orderoriginal ↗
17 Aug 2026
State of Open Models: Summer 2026 Observationsoriginal ↗
14 Aug 2026
Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Bucketsoriginal ↗
13 Aug 2026
What We Learned by Reproducing 2,200 papers from ICMLoriginal ↗
13 Aug 2026
Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysisoriginal ↗
12 Aug 2026
Thinking of ACE? We Can Do It with Fewer Tokensoriginal ↗
11 Aug 2026
Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTSoriginal ↗
10 Aug 2026
Making Knowledge Distillation Cheap Enough to Run at Scaleoriginal ↗
10 Aug 2026
Meta is back with Muse Glimmer: local, agentic, multimodal, and open sourceoriginal ↗
10 Aug 2026
Baseten on Hugging Face Inference Providers 🔥original ↗
6 Aug 2026
GPU Management: Why Idle GPUs Are the New Grounded Aircraftoriginal ↗
30 Jul 2026
NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Roboticsoriginal ↗
27 Jul 2026
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incidentoriginal ↗
27 Jul 2026
Bringing Nunchaku 4-bit Diffusion Inference to Diffusersoriginal ↗
23 Jul 2026
Grabette: an open system to record robot-manipulation dataoriginal ↗
21 Jul 2026
Newer Models, Same Advantageoriginal ↗
16 Jul 2026
Security incident disclosure — July 2026original ↗
16 Jul 2026
Model Routing Is Simple. Until It Isn’t.original ↗
15 Jul 2026
Welcome Inkling by Thinking Machinesoriginal ↗
15 Jul 2026
Introducing Real World VoiceEQ: Measuring the human quality of voice AIoriginal ↗
15 Jul 2026
Profiling in PyTorch (Part 3): Attention is all you profileoriginal ↗
10 Jul 2026
Native-speed vLLM transformers modeling backendoriginal ↗
8 Jul 2026
From Hugging Face to Amazon SageMaker Studio in one clickoriginal ↗
7 Jul 2026
Hugging Face Models on Foundry Managed Computeoriginal ↗
7 Jul 2026
Run AI workloads on any cloud, store on Hugging Face: zero-egress storage with SkyPilotoriginal ↗
7 Jul 2026
LeRobot v0.6.0: Imagine, Evaluate, Improveoriginal ↗
7 Jul 2026
PRX Part 4: Our Data Strategyoriginal ↗
6 Jul 2026
🤗 Kernels: Major Updatesoriginal ↗
6 Jul 2026
Hugging Face and Cerebras bring Gemma 4 to real-time voice AIoriginal ↗
1 Jul 2026
ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migrationoriginal ↗
30 Jun 2026
Why Specialization Is Inevitableoriginal ↗
30 Jun 2026
Featuring Every Eval Ever Results on Hugging Face Model Pagesoriginal ↗
30 Jun 2026
DiScoFormer: One transformer for density and score, across distributionsoriginal ↗
29 Jun 2026
Run a vLLM Server on HF Jobs in One Commandoriginal ↗
26 Jun 2026
Accelerating Transformers Fine-Tuning with NVIDIA NeMo AutoModeloriginal ↗
24 Jun 2026
Introducing the FFASR Leaderboard: Benchmarking ASR in the Real Worldoriginal ↗
24 Jun 2026
Shipping huggingface_hub every week with AI, open tools, and a human in the looporiginal ↗
23 Jun 2026
Experimenting with the proposed Cross-Origin Storage API in Transformers.jsoriginal ↗
23 Jun 2026
PP-OCRv6 on Hugging Face: 50-Language OCR from 1.5M to 34.5M Parametersoriginal ↗
22 Jun 2026
We got local models to triage the OpenClaw repo for FREE!*original ↗
22 Jun 2026
MosaicLeaks: Can your research agent keep a secret?original ↗
18 Jun 2026
Beyond LoRA: Can you beat the most popular fine-tuning technique?original ↗
18 Jun 2026
Is it agentic enough? Benchmarking open models on your own toolingoriginal ↗
18 Jun 2026
From the Hugging Face Hub to robot hardware with Strands Agents and LeRobotoriginal ↗
17 Jun 2026
GLM-5.2: Built for Long-Horizon Tasksoriginal ↗
17 Jun 2026
Agentic Resource Discovery: Let agents searchoriginal ↗
17 Jun 2026
Profiling in PyTorch (Part 2): From nn.Linear to a Fused MLPoriginal ↗
11 Jun 2026
How an Agent Built a 3D Paris Gallery by Chaining Two Hugging Face Spacesoriginal ↗
9 Jun 2026
Migrating Your GitHub CI to Hugging Face Jobsoriginal ↗
9 Jun 2026
The Open Source Community is backing OpenEnv for Agentic RLoriginal ↗
8 Jun 2026
Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AIoriginal ↗
4 Jun 2026
Designing the hf CLI as an agent-optimized way to work with the Huboriginal ↗
4 Jun 2026
Direct Preference Optimization Beyond Chatbotsoriginal ↗
3 Jun 2026
Adding MCP Tools to Reachy Minioriginal ↗
3 Jun 2026
Holo3.1: Fast & Local Computer Use Agentsoriginal ↗
2 Jun 2026
Introducing Mellum2: A 12B Mixture-of-Experts Model by JetBrainsoriginal ↗
1 Jun 2026
Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logicoriginal ↗
1 Jun 2026
Profiling in PyTorch (Part 1): A Beginner's Guide to torch.profileroriginal ↗
29 May 2026
Reachy Mini goes fully localoriginal ↗
27 May 2026
Shipping a Trillion Parameters With a Hub Bucket: Delta Weight Sync in TRLoriginal ↗
27 May 2026
Harness, Scaffold, and the AI Agent Terms Worth Getting Rightoriginal ↗
25 May 2026
OlmoEarth v1.1: A more efficient family of Earth observation modelsoriginal ↗
19 May 2026
Introducing the Ettin Reranker Familyoriginal ↗
19 May 2026
PaddleOCR 3.5: Running OCR and Document Parsing Tasks with a Transformers Backendoriginal ↗
18 May 2026
Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Qualityoriginal ↗
14 May 2026
Unlocking asynchronicity in continuous batchingoriginal ↗
14 May 2026
Building Blocks for Foundation Model Training and Inference on AWSoriginal ↗
11 May 2026
vLLM V0 to V1: Correctness Before Corrections in RLoriginal ↗
6 May 2026
Adding Benchmaxxer Repellant to the Open ASR Leaderboardoriginal ↗
6 May 2026
Granite 4.1 LLMs: How They’re Builtoriginal ↗
29 Apr 2026
DeepInfra on Hugging Face Inference Providers 🔥original ↗
29 Apr 2026
Next