ForecastingCo's first paper shows how to train transformers on real temporal data
fpedregosa · x · 2026-09-27
ForecastingCo's first paper is getting strong praise for explaining in depth how to teach transformers to handle real-world temporal data and forecasting.
Key ideas: temporal data is multi-stream and information cutoffs matter; known future signals such as holidays and weather forecasts should be fed into the model.
More from Research
- Philosophy paper argues mech interp makes the stochastic parrot picture untenable — burny_tech · 2026-09-27
- First PhD paper accepted at NeurIPS 2026: Sparse layers key to scaling looped LMs — burny_tech · 2026-09-27
- Colored Noise Sampling: dyeing injected noise to boost diffusion sample quality — serrjoa · 2026-09-27
- Researcher: within months, submitting proofs without AI verification will be malpractice — RexDouglass · 2026-09-27
- JevBench evaluator: most models lose to fixable settings and calibration — airesearch12 · 2026-09-27
- "Mathematics is Effectively Dead": essay extends Daniel Litt on AI and the future of math — burny_tech · 2026-09-27