GEM-3让你用一套权重随时切换1到24小时预报时间步，跑得稳还实用，比固定时间步的模型灵活多了。
GEM-3是面向全球天气预报的概率模型，通过显式多时间步推理解决固定时间步的权衡。它用一组训练权重在推理时配置模型时间步，混合时间步训练比时间步专用模型更稳定。该模型是轻量邻域注意力Transformer，约134M参数，架构相对GEM-2有多项改进。它在中期概率预测上接近当前最优水平，并支持稳定扩展的长时间滚动预报。
Timestep-Conditioned Transformers for Global Weather Forecasting
Existing machine-learning weather forecasting models rely on predetermined and fixed autoregressive timesteps. The choice of model timestep involves a fundamental trade-off: shorter timesteps (e.g. 1 to 6 hours) finely resolve atmospheric dynamics within the diurnal cycle but increase error accumulation for a given forecast horizon, while longer timesteps (e.g. 24 hours) reduce error accumulation but limit the usability of short-range forecasts where sub-daily predictability is high. In this work, we present GEM-3, a probabilistic global weather model that addresses this trade-off through explicit multi-timestep inference. With a single set of trained weights, the model timestep can be configured at inference time to balance predictability and usability across a broad forecast horizon. Additionally, we find that mixed-timestep training consistently improves rollout stability relative to timestep-specialist models. Under the hood, GEM-3 is a lightweight neighborhood-attention transformer with ~134M parameters on an equirectangular grid with a number of architectural advancements beyond its predecessor GEM-2. The result is a practical forecasting system that couples near-SOTA medium-range probabilistic skill, stable extended-range rollouts, efficient training and inference, and decision-relevant diagnostics.