3 papers
cs.LG2025
Deep Model Merging: The Sister of Neural Network Interpretability -- A Survey
Arham Khan, Todd Nief, Nathaniel Hudson +6
We survey the model merging literature through the lens of loss landscape geometry to connect observations from empirical studies on model merging and loss landscape analysis to ph…
cs.LG2025
Causal Discovery over High-Dimensional Structured Hypothesis Spaces with Causal Graph Partitioning
Ashka Shah, Adela DePavia, Nathaniel Hudson +2
The aim in many sciences is to understand the mechanisms that underlie the observed distribution of variables, starting from a set of initial hypotheses. Causal discovery allows us…
cs.LG2025
Mitigating Memorization In Language Models
Mansi Sakarvadia, Aswathy Ajith, Arham Khan +6
Language models (LMs) can "memorize" information, i.e., encode training data in their weights in such a way that inference-time queries can lead to verbatim regurgitation of that d…