Researchers have investigated the stability of autoregressive sequence models when forecasting long-horizon physical wavefields, such as seismograms. Their study, using a model called SeismoGPT on synthetic seismograms, found that multi-token prediction significantly stabilizes the forecasting process. Additional gains were observed with a horizon-embedding hybrid prediction head and a cross-horizon STFT-magnitude coherence loss, though performance critically depends on a specific context-ratio threshold. AI
IMPACT Identifies key architectural choices for improving the stability of autoregressive models in long-horizon forecasting of physical signals.
RANK_REASON The cluster contains a research paper detailing a controlled study on autoregressive sequence models for forecasting physical wavefields.
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →