IBM Granite time-series models enable ensemble forecasting
Hugging Face: Ensemble forecasting with IBM Granite time-series models
Combining multiple specialized models could improve accuracy for predicting trends in weather, finance, and other time-sensitive domains.
Get smart on it
Ensemble forecasting combines multiple time-series models to make predictions about future values, similar to how weather forecasting combines different models for seasonal predictions. IBM has released four pre-trained Granite time-series models with different architectures that can be combined through an ensemble interface without requiring retraining or fitted weights. The ensemble approach matters because individual models perform differently depending on the data characteristics: a model handling smooth industrial signals well may struggle with noisy retail demand or long seasonal horizons, so combining complementary models reduces guesswork about which single model to choose. Two combination methods are available: a Probabilistic Ensemble that gives each model equal influence, and an IQR Ensemble that weights models based on their forecast spread.
Relevant courses
Want to go deeper than the news? Explore live, cohort-based AI courses taught by practitioners.
Browse AI courses on MavenRelated news
Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time
Mistral AI launched Voxtral 3, a new family of language models built for real-time voice agents. The system combines speech-to-text, text-to-speech, and a voice agent SDK, supports more than 50 languages, and lets agents tap into external tools during live conversations. It can run on your own infrastructure or through EU-hosted APIs to keep data under your control. The article Mistral AI launches Voxtral 3, a full voice agent stack that listens, thinks, and talks in real time appeared
Also reported by MarkTechPost
Hugging Face’s New AI Biology Model Lets You Chat With DNA
The new open-source model speaks the language of DNA and can help researchers understand the effects of any changes on gene activity and health.
Recursive launches Flint, a laptop coding model it says was largely built by AI
Startup Recursive has released Flint, a free, laptop-sized coding model built largely by its own AI research system, as an early test of AI that improves itself.
Also reported by Wired AI and MarkTechPost
Voxtral 3
Voxtral 3: Mistral's voice agent SDK for real-time speech in 50+ languages — accurate transcription, emotional TTS, deep tool use. EU-hosted or self-deployed.
Perplexity and NVIDIA Researchers Introduce JOLT: a Joint Teacher-Student Reinforcement Learning Method
Perplexity, along with NVIDIA team, has introduced JOLT, a new post-training method for language models. JOLT stands for Joint On-policy Learning and Teaching. It trains a single model in 2 roles. The teacher sees privileged information; the student does not. The key change is that the teacher is trained too, so its feedback stays usable. On MATH, JOLT matched GRPO’s accuracy with 6.5x fewer processed training tokens. For teams running RL post-training, that is a direct compute question.
NVIDIA Cosmos Opens New Tools to Train, Evaluate and Deploy World Models
To help developers rapidly build world models, which help physical AI systems understand and simulate the real world, NVIDIA has expanded the Cosmos platform with new training tools, simulation checkpoints and Cosmos Data Factory blueprints. Ranking top five on six different open models leaderboards, the NVIDIA Cosmos platform gives world model builders the frontier open models — as well as data, training and optimization tools and recipes — to scale training data, adapt models, test behavior a