New paper proposes self-supervised latent action-conditioned world modeling for time series
An arXiv paper introduces a self-supervised latent action-conditioned world modeling approach for time-series data, targeting tasks such as weather forecasting, web traffic analysis, and speech recognition.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-10-30 04:00 · arXiv cs.LG
Self-Supervised Latent Action-Conditioned World Modeling for Time Series