2 papers
cs.LG2026
Reliability-Guided Adaptive Ensembling for Robust Test-Time Adaptation
Adam Koziak, Yuhong Guo
Test-time adaptation (TTA) can mitigate domain shift without source data, but it is highly brittle under adversarially contaminated test streams, where corrupted inputs also destab…
cs.LG2026
Select-to-Act: Hierarchical Reinforcement Learning via Adaptive Language Guidance
Hanping Zhang, Adam Koziak, Yuhong Guo
Reinforcement Learning (RL) has been widely applied to sequential decision-making, yet it often suffers from poor sample efficiency due to costly interactions with the environment.…