huggingface4d agoLitPivot: Developing research ideas through dynamic contextualization within the literature landscape
huggingface5d agoTurning Database Grading into RL Rewards: Post-Training Agents with ThinkingBoxRead on huggingface →
huggingface5d agoOlmoEarth v1.3: State-of-the-art embeddings for the whole planetRead on huggingface →
huggingface6d agoNVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training RequiredRead on huggingface →
huggingface6d agoTrain in Simulation, Deploy on a Real Robot: Microduck with Isaac Lab 3.0Read on huggingface →
huggingface6d agoHow Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real ApplicationsRead on huggingface →
huggingface6d agoProfiling TorchNeuron (Part 1): System-level profiling on AWS Trainium.Read on huggingface →
huggingface6d agoGranite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and FasterRead on huggingface →
huggingface6d agoNVIDIA Kumo Forecast Combines Pretrained Time-Series Representations with Historical Pattern Retrieval and InterpretabilityRead on huggingface →
huggingface6d agoAnnouncing SimReady Central: An Open Library of Simulation-Ready 3D Assets for Robotics and AI FactoriesRead on huggingface →
huggingfaceOct 20NVIDIA Cosmos3-H-Dreams: Bringing Clinical Surgery to Life Through Generative SimulationRead on huggingface →
huggingfaceOct 20FairStress: A deeper evaluation of fairness in LLM decision-makingRead on huggingface →
huggingfaceOct 20ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier modelRead on huggingface →
huggingfaceOct 20AnyLanguageModel 1.0: One Year of Local Models on Apple PlatformsRead on huggingface →
huggingfaceOct 19TorchNeuron: running HF models on AWS Trainium is easier than everRead on huggingface →
huggingfaceOct 16Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation PipelineRead on huggingface →
huggingfaceOct 16Welcome Beam: a 501B open model you can own, customize, and scaleRead on huggingface →
huggingfaceOct 15Granite Switch 4.1: Chat, Decisions, and Speech from One EndpointRead on huggingface →
huggingfaceOct 15Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from MetaRead on huggingface →
huggingfaceOct 14HiRO-ACEv2: Simulating extreme weather at 3 km resolution for a fraction of the costRead on huggingface →
huggingfaceOct 7One Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMORead on huggingface →
huggingfaceOct 6Falcon-Emirati: When an LLM Learns the Dialect, the Culture, and the NuanceRead on huggingface →
huggingfaceOct 2Open-sourcing AstaBrief, the fast report-generation model in AstaRead on huggingface →
huggingfaceOct 1Introducing Olmo-core 3: Open, scalable training infrastructure for large MoEsRead on huggingface →
huggingfaceSep 30Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice CloningRead on huggingface →
huggingfaceSep 29NVIDIA Kumo Tabular Sets a New Accuracy-Efficiency Frontier for Tabular PredictionRead on huggingface →
huggingfaceSep 29Getting the Source Right, Not Just the Fact: Source-Aware Verification for MCP AgentsRead on huggingface →
huggingfaceSep 23How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning WorkflowsRead on huggingface →
huggingfaceSep 23**Know Who Spoke When: Build Real-Time, Multi-Speaker AI with NVIDIA Nemotron 3 Diarization**Read on huggingface →
huggingfaceSep 22How UK AISI and EvalEval Are Making Benchmark Results ReproducibleRead on huggingface →
huggingfaceSep 22Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX communityRead on huggingface →
huggingfaceSep 21Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization ProblemRead on huggingface →
huggingfaceSep 10Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCLRead on huggingface →
huggingfaceSep 9IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly licenseRead on huggingface →
huggingfaceSep 8Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole TopicRead on huggingface →
huggingfaceSep 3Training a coding model to paint watercolours with TRL and OpenEnvRead on huggingface →
huggingfaceSep 3Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO StepsRead on huggingface →
huggingfaceSep 1Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AIRead on huggingface →
huggingfaceAug 26Training and Finetuning Multi-Vector Embedding Models with Sentence TransformersRead on huggingface →
huggingfaceAug 25Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision originalRead on huggingface →
huggingfaceAug 21How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with CodeRead on huggingface →
huggingfaceAug 18Multi-Vector (Late Interaction) Embedding Models with Sentence TransformersRead on huggingface →
huggingfaceAug 17Same Cluster, 33 Points More Utilization: What Changed Was the OrderRead on huggingface →
huggingfaceAug 13Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage BucketsRead on huggingface →
huggingfaceAug 12Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysisRead on huggingface →
huggingfaceAug 10Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTSRead on huggingface →
huggingfaceAug 10Meta is back with Muse Glimmer: local, agentic, multimodal, and open sourceRead on huggingface →
huggingfaceJul 28The OlmoEarth Platform: Geospatial inference at planetary scaleRead on huggingface →
huggingfaceJul 27NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical RoboticsRead on huggingface →
huggingfaceJul 27Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 IncidentRead on huggingface →
huggingfaceJul 17Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 DiffusersRead on huggingface →
huggingfaceJul 16bullishNVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic RetrievalNENENE3 models#retrieval#embeddings#open-sourceRead on huggingface →