About
People
Publications
Open Source
Demos
Events
Blog
Careers
Contact
English
English
Français
ServiceNow
ServiceNow AI Research
Tags
Disentanglement
ServiceNow AI Research
Disentanglement
Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning
Language model activations entangle concepts that mediate their behavior, making it difficult to interpret these factors, which has …
Navita Goyal
,
Hal Daumé III
,
Alexandre Drouin
,
Dhanya Sridhar
Neural Information Processing Systems (NeurIPS), 2025.
Cite
Monotonicity Regularization: Improved Penalties and Novel Applications to Disentangled Representation Learning and Robust Classification
We study settings where gradient penalties are used alongside risk minimization with the goal of obtaining predictors satisfying …
João Monteiro
,
Mohamed Osama Ahmed
,
Hossein Hajimirsadeghi
,
Greg Mori
Conference on Uncertainty in Artificial Intelligence (UAI), 2022.
PDF
Cite
Code
Disentangling the independently controllable factors of variation by interacting with the world
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it …
Valentin Thomas
,
Emmanuel Bengio
,
William Fedus
,
Jules Pondard
,
Philippe Beaudoin
,
Hugo Larochelle
,
Joelle Pineau
,
Doina Precup
,
Yoshua Bengio
Workshop at the Neural Information Processing Systems (NeurIPS), 2017.
PDF
Cite
Cite
×