Test-Time Forecasting: Recurrent Depth Enables In-Context Dynamics Prediction

cs.LG

Submitted: 2026-10-14

Updated: 2026-10-14

Code: https://github.com/HomebrewML/HeavyBall

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• GIFT-Eval: A Benchmark For General Time Series Forecasting Model Evaluation
• Chronos-2: From Univariate to Universal Forecasting
• Transformers for dynamical systems learn transfer operators in-context
• Applied Koopmanism
• Gaussian Error Linear Units (GELUs)
• On Convergence of Extended Dynamic Mode Decomposition to the Koopman Operator
• AIFS -- ECMWF's data-driven forecasting system
• In-context Learning and Induction Heads
• Parcae: Scaling Laws For Stable Looped Language Models
• Gated Linear Attention Transformers with Hardware-Efficient Training
• ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs
• Neural Networks Fail to Learn Periodic Functions and How to Fix It

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks