IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license IA IBM releases SOTA Granite Time Series PatchTST-FM-r2 model with commercial-friendly license 9 septembre 2026 Hugging Face Lire
Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic IA Safety for Whom? Refusing the Right Subset of a Topic, Not the Whole Topic 8 septembre 2026 Hugging Face Lire
NeoMME: an efficient Multimodal-native and Multilingual Encoder IA NeoMME: an efficient Multimodal-native and Multilingual Encoder 3 septembre 2026 Hugging Face Lire
Training a coding model to paint watercolours with TRL and OpenEnv IA Training a coding model to paint watercolours with TRL and OpenEnv 3 septembre 2026 Hugging Face Lire
Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps IA Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps 3 septembre 2026 Hugging Face Lire
Give Your Coding Agents a Memory You Own IA Give Your Coding Agents a Memory You Own 3 septembre 2026 Hugging Face Lire
Real-Time Intelligence with IBM Time Series Models on Confluent IA Real-Time Intelligence with IBM Time Series Models on Confluent 2 septembre 2026 Hugging Face Lire
BenchMIRT: What are LLM benchmarks actually measuring? IA BenchMIRT: What are LLM benchmarks actually measuring? 1 septembre 2026 Hugging Face Lire
Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI IA Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI 1 septembre 2026 Hugging Face Lire
The Open ASR Leaderboard Adds Its First Global South Language IA The Open ASR Leaderboard Adds Its First Global South Language 28 août 2026 Hugging Face Lire
Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers IA Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers 26 août 2026 Hugging Face Lire
Granite 4.2 LLMs: How They're Built IA Granite 4.2 LLMs: How They're Built 25 août 2026 Hugging Face Lire
Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original IA Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original 25 août 2026 Hugging Face Lire
Wire It, Run It, Deploy It: AI Workflows in Gradio IA Wire It, Run It, Deploy It: AI Workflows in Gradio 25 août 2026 Hugging Face Lire
Measuring benchmark optimization in speech recognition IA Measuring benchmark optimization in speech recognition 21 août 2026 Hugging Face Lire
