Google Releases TimesFM-3, a Zero-Shot Foundation Model for Multivariate Forecasting
aigclink · x · 2026-09-01
Google Research introduces TimesFM-3, a state-of-the-art zero-shot foundation model designed for multivariate time series forecasting. With 330 million parameters, the model is pre-trained on a corpus of over 1 trillion time points from both real-world and synthetic data. Unlike its predecessors limited to univariate forecasting, TimesFM-3 natively supports multivariate scenarios, jointly predicting multiple co-evolving time series to capture dependencies, significantly outperforming other models on major benchmarks.
More from Models
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Argon edges out astra as daily driver, but Claude still wins heavy coding work — iruletheworldmo · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- RoboVista benchmark: Gemini-4 Argon hits 81.9% on robotics understanding — berkeley_ai · 2026-10-16
- Dev reports decision model jev beats gpt-6-luna on quality in real training pipeline — genmon · 2026-10-16
- Google won't publish Argon 4 limits in AI Pro—users compare experiences — Consistent-Text-2662 · 2026-10-16