Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Problem/AI Alignment/Explainable AI/Interpretable AI/Mechanistic interpretability/Universality Hypothesis/Model Diffing/
ModelDiff
Search

ModelDiff

Creator
Creator
Seonglae Cho
Created
Created
2025 Feb 27 14:49
Editor
Editor
Seonglae Cho
Edited
Edited
2025 Feb 27 15:0
Refs
Refs
developing an approach to it based on dataset transformations that do or don't affect a model's learning process
 
 
 
 
modeldiff
MadryLab • Updated 2025 Jan 31 19:15
arxiv.org
https://arxiv.org/pdf/2211.12491
 
 
 

Recommendations

Texonom
Texonom
/
Engineering
Engineering
/Data Engineering/Artificial Intelligence/AI Problem/AI Alignment/Explainable AI/Interpretable AI/Mechanistic interpretability/Universality Hypothesis/Model Diffing/
ModelDiff
Copyright Seonglae Cho