Ensemble forecasting with IBM Granite time-series models Nouveau IA Ensemble forecasting with IBM Granite time-series models 22 octobre 2026 Hugging Face Lire
NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required Nouveau IA NVIDIA Kumo Relational Outperforms Supervised Machine Learning on Relational Data, No Training Required 21 octobre 2026 Hugging Face Lire
How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications Nouveau IA How Specializing the Vocabulary of SLMs Can Cut Inference Cost by 77% in Real Applications 21 octobre 2026 Hugging Face Lire
Profiling TorchNeuron (Part 1): System-level profiling on AWS Trainium. Nouveau IA Profiling TorchNeuron (Part 1): System-level profiling on AWS Trainium. 21 octobre 2026 Hugging Face Lire
Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster Nouveau IA Granite Speech 5.0: Transcribe, Translate, and Attribute more Accurately and Faster 21 octobre 2026 Hugging Face Lire
NVIDIA Cosmos3-H-Dreams: Bringing Clinical Surgery to Life Through Generative Simulation Récent IA NVIDIA Cosmos3-H-Dreams: Bringing Clinical Surgery to Life Through Generative Simulation 20 octobre 2026 Hugging Face Lire
FairStress: A deeper evaluation of fairness in LLM decision-making Récent IA FairStress: A deeper evaluation of fairness in LLM decision-making 20 octobre 2026 Hugging Face Lire
ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model Récent IA ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model 20 octobre 2026 Hugging Face Lire
Hugging Face ❤️ TorchTPU: TPUs, Natively Récent IA Hugging Face ❤️ TorchTPU: TPUs, Natively 20 octobre 2026 Hugging Face Lire
AnyLanguageModel 1.0: One Year of Local Models on Apple Platforms Récent IA AnyLanguageModel 1.0: One Year of Local Models on Apple Platforms 20 octobre 2026 Hugging Face Lire
TorchNeuron: running HF models on AWS Trainium is easier than ever IA TorchNeuron: running HF models on AWS Trainium is easier than ever 19 octobre 2026 Hugging Face Lire
Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline IA Scaling Indic Pretraining: 2.8 Trillion Tokens and an Open Data Generation Pipeline 16 octobre 2026 Hugging Face Lire
Welcome Beam: a 501B open model you can own, customize, and scale IA Welcome Beam: a 501B open model you can own, customize, and scale 16 octobre 2026 Hugging Face Lire
Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint IA Granite Switch 4.1: Chat, Decisions, and Speech from One Endpoint 15 octobre 2026 Hugging Face Lire
Nouveau 
