Rethinking Expressivity and Efficiency in Test-Time Training

arXiv:2608.21308 · cs.LG · Submitted 2026-08-21 · Read on arXiv

cs.LG

Submitted: 2026-08-21

Updated: 2026-08-26

Code: https://github.com/zeyun-zhong/E2-TTT

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

Terminology

• Test-Time Training — 2× in this paper
• Accuracy — 1× in this paper · explained in 1 episode

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks