ZeroSiam is an asymmetric architecture using a learnable predictor and stop-gradient that prevents collapse in test-time entropy minimization while also regularizing biased signals for improved performance.
Adapt in the wild: Test-time entropy minimization with sharpness and feature regulariza- tion.CoRR, abs/2509.04977
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
verdicts
UNVERDICTED 3representative citing papers
Ramen enables robust test-time adaptation of vision-language models under mixed-domain shifts by actively selecting domain-consistent and prediction-balanced samples via an embedding-gradient cache.
DASP decouples each modality adapter into stable and plastic parts and uses asymmetric updates—plastic for biased modalities, regularized stable for unbiased ones—to balance adaptation and knowledge preservation.
citing papers explorer
-
ZeroSiam: An Efficient Asymmetry for Test-Time Entropy Optimization without Collapse
ZeroSiam is an asymmetric architecture using a learnable predictor and stop-gradient that prevents collapse in test-time entropy minimization while also regularizing biased signals for improved performance.
-
Ramen: Robust Test-Time Adaptation of Vision-Language Models with Active Sample Selection
Ramen enables robust test-time adaptation of vision-language models under mixed-domain shifts by actively selecting domain-consistent and prediction-balanced samples via an embedding-gradient cache.
-
Decoupling Stability and Plasticity for Multi-Modal Test-Time Adaptation
DASP decouples each modality adapter into stable and plastic parts and uses asymmetric updates—plastic for biased modalities, regularized stable for unbiased ones—to balance adaptation and knowledge preservation.