Skip to main content
Search

# Non-Autoregressive Multi-Step Forecasting

1 related articles

Subscribe to updates
  1. arXiv

    RWKV fades on long horizons: alternating in attention blocks lets a 36M model match a 1B forecaster on GIFT long-horizon MASE

    HART alternates Transformer and RWKV blocks so prediction positions can retrieve history directly, beating pure RWKV at medium and long horizons on GIFT-Eval and TIME-Benchmark and matching Toto-2.0-1B's long-horizon MASE on GIFT with 36M parameters.

    Huawei Technologies (China)Shantou UniversityGuangdong University of TechnologyUniversité Paris Cité
    Qingwen Lin（First author）
    Hybrid Attention-RWKV Time-Series Foundation ModelPlaceholder Idling DecayNon-Autoregressive Multi-Step ForecastingTime-Series Foundation ModelRecurrent Neural Networks

You’re all caught up