EVA-0 is a zeroth-order test-time adaptation method that uses scale-invariant loss, anchor-guided optimization, and symmetric two-sided perturbations to enable inference and adaptation in two forward passes, outperforming prior methods on ImageNet-C with ViT-Base.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A cross-environment transformer estimator learns common physical structures in channel-gain maps to achieve accurate 6D estimation from five times fewer measurements in unseen environments.
JEPA-Indexed Local Expert Growth adds local action corrections for detected shift clusters and yields statistically significant OOD gains on four shift conditions while keeping in-distribution performance intact.
citing papers explorer
-
EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample
EVA-0 is a zeroth-order test-time adaptation method that uses scale-invariant loss, anchor-guided optimization, and symmetric two-sided perturbations to enable inference and adaptation in two forward passes, outperforming prior methods on ImageNet-C with ViT-Base.
-
Learning the Channel Gain from Anywhere to Anywhere via Cross-environment Transformer Estimators
A cross-environment transformer estimator learns common physical structures in channel-gain maps to achieve accurate 6D estimation from five times fewer measurements in unseen environments.
-
Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift
JEPA-Indexed Local Expert Growth adds local action corrections for detected shift clusters and yields statistically significant OOD gains on four shift conditions while keeping in-distribution performance intact.