▶ hugging face·
items50 latest
▶ hugging face·
Rebuilding AUTOMATIC1111 with Gradio Workflow
▶ hugging face·
Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL
▶ hugging face·
IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license
▶ hugging face·
Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic
▶ hugging face·
NeoMME: an efficient Multimodal-native and Multilingual Encoder
▶ hugging face·
Training a coding model to paint watercolours with TRL and OpenEnv
▶ hugging face·
Give Your Coding Agents a Memory You Own
▶ hugging face·
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps
▶ hugging face·
Real-Time Intelligence with IBM Time Series Models on Confluent
▶ hugging face·
BenchMIRT: What are LLM benchmarks actually measuring?
▶ hugging face·
Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI
▶ hugging face·
The Open ASR Leaderboard Adds Its First Global South Language
▶ hugging face·
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers
▶ hugging face·
Granite 4.2 LLMs: How They're Built
▶ hugging face·
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original
▶ hugging face·
Wire It, Run It, Deploy It: AI Workflows in Gradio
▶ hugging face·
Measuring benchmark optimization in speech recognition
▶ hugging face·
How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code
▶ hugging face·
Up to 3.2x Faster Inference with LFM2.5-DSpark
▶ hugging face·
LFM2.5 Q4\_0 Checkpoints from Quantization-Aware Distillation
▶ hugging face·
How Much Memory Does Your Agent Actually Need?
▶ hugging face·
Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
▶ hugging face·
Same Cluster, 33 Points More Utilization: What Changed Was the Order
▶ hugging face·
State of Open Models: Summer 2026 Observations
▶ hugging face·
Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage Buckets
▶ hugging face·
What We Learned by Reproducing 2,200 papers from ICML
▶ hugging face·
Introducing OlmoEarth embeddings: Custom embedding exports from OlmoEarth Studio for downstream analysis
▶ hugging face·
LFM2.5-VL-3B for Better and Faster Vision Capabilities for the Edge
▶ hugging face·
Thinking of ACE? We Can Do It with Fewer Tokens
▶ hugging face·
Build Low-Latency Multilingual Voice Agents: Open Weights & Full Deployment Control with NVIDIA Magpie TTS
▶ hugging face·
Making Knowledge Distillation Cheap Enough to Run at Scale
▶ hugging face·
Meta is back with Muse Glimmer: local, agentic, multimodal, and open source
▶ hugging face·
TutorMoments: Do AI tutors know when to help and when to hold back?
▶ hugging face·
Baseten on Hugging Face Inference Providers 🔥
▶ hugging face·
Deploy local agents everywhere with LFM2.5-2.6B
▶ hugging face·
GPU Management: Why Idle GPUs Are the New Grounded Aircraft
▶ hugging face·
The OlmoEarth Platform: Geospatial inference at planetary scale
▶ hugging face·
LFM2.5-Encoders for Fast Long-Context Inference on CPU
▶ hugging face·
NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics
▶ hugging face·
Anatomy of a Frontier Lab Agent Intrusion: A Technical Timeline of the July 2026 Incident
▶ hugging face·
Bringing Nunchaku 4-bit Diffusion Inference to Diffusers
▶ hugging face·
The State of Simulation for Physical AI: An Overview
▶ hugging face·
Grabette: an open system to record robot-manipulation data
▶ hugging face·
Introducing Cosmos 3 Edge
▶ hugging face·
Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers
▶ nemotron·
NVIDIA Nemotron 3 Embed Ranks #1 Overall on RTEB, Advancing Agentic Retrieval
▶ hugging face·
Newer Models, Same Advantage
▶ hugging face·
Security incident disclosure
▶ hugging face·