5 papers
Multi-Hypothesis Test-Time Adaptation to Mitigate Underspecification
Afshar Shamsi, Xiao-Yu Guo, Hamid Alinejad-Rokny +3
Test-Time Adaptation (TTA) seeks to improve model robustness under distribution shifts by adapting parameters using unlabeled target data. However, in the absence of supervision, e…
Truth as a Trajectory: What Internal Representations Reveal About Large Language Model Reasoning
Hamed Damirchi, Ignacio Meza De la Jara, Ehsan Abbasnejad +3
Existing explainability methods for Large Language Models (LLMs) typically treat hidden states as static points in activation space, assuming that correct and incorrect inferences…
Enhancing Monte Carlo Dropout Performance for Uncertainty Quantification
Hamzeh Asgharnezhad, Afshar Shamsi, Roohallah Alizadehsani +2
Knowing the uncertainty associated with the output of a deep neural network is of paramount importance in making trustworthy decisions, particularly in high-stakes fields like medi…
Bayesian Low-Rank LeArning (Bella): A Practical Approach to Bayesian Neural Networks
Bao Gia Doan, Afshar Shamsi, Xiao-Yu Guo +6
Computational complexity of Bayesian learning is impeding its adoption in practical, large-scale tasks. Despite demonstrations of significant merits such as improved robustness and…
ETAGE: Enhanced Test Time Adaptation with Integrated Entropy and Gradient Norms for Robust Model Performance
Afshar Shamsi, Rejisa Becirovic, Ahmadreza Argha +3
Test time adaptation (TTA) equips deep learning models to handle unseen test data that deviates from the training distribution, even when source data is inaccessible. While traditi…