Auto-Regressive Next-Token Predictors Are Universal Learners (arxiv.org) | HN Screenshots

YHacker Newsscreenshots

Screenshot of arxiv.org: Auto-Regressive Next-Token Predictors Are Universal Learners

First screen, captured 3 years ago.

Looks similar

Screenshot of arxiv.org: Learning Universal Predictors

Learning Universal Predictors (arxiv.org)

52 points by jandrewrogers 2 years ago | 14 comments

Screenshot of arxiv.org: Physics in Next-Token Prediction

Physics in Next-Token Prediction (arxiv.org)

17 points by Anon84 1 year ago | 3 comments

Screenshot of arxiv.org: σ-GPTs: A new approach to autoregressive models

σ-GPTs: A new approach to autoregressive models (arxiv.org)

258 points by mehulashah 2 years ago | 70 comments

Screenshot of arxiv.org: Matryoshka Representation Learning

Matryoshka Representation Learning (arxiv.org)

71 points by fzliu 2 years ago | 10 comments

Screenshot of arxiv.org: TimeGPT-1

TimeGPT-1 (arxiv.org)

373 points by PaulHoule 3 years ago | 114 comments

arXiv paper introducing TimeGPT, a foundation model for time series forecasting that performs zero-shot predictions on unseen datasets.

timegpt time-series foundation-models forecasting

Screenshot of arxiv.org: XLSTMTime: Long-Term Time Series Forecasting with xLSTM

XLSTMTime: Long-Term Time Series Forecasting with xLSTM (arxiv.org)

215 points by beefman 2 years ago | 49 comments