Reproduce “Test-Time Forecasting: Recurrent Depth Enables In-Context Dynamics Prediction” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jeffrey B. Lai, John Quinn, Anthony Bao, William Gilpin
The authors present test-time forecasting, repeatedly fitting a one-step predictor to trajectory context to forecast unfamiliar dynamics. For linear systems, implicit updates connect linear attention with DMD; nonlinear models fit propagators in learned features or update fast weights. On selected synthetic ODE and PDE families, added iterations improve out-of-distribution rollouts, as in Duffing, but do not establish real-world foundation-model performance.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.