ServiceNow AI Research

Disentanglement

Causal Differentiating Concepts: Interpreting LM Behavior via Causal Representation Learning
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 …
Neural Information Processing Systems (NeurIPS),  2025.
Cite
Monotonicity Regularization: Improved Penalties and Novel Applications to Disentangled Representation Learning and Robust Classification
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 …
Conference on Uncertainty in Artificial Intelligence (UAI),  2022.
PDF Cite Code
Disentangling the independently controllable factors of variation by interacting with the world
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 …
Workshop at the Neural Information Processing Systems (NeurIPS),  2017.
PDF Cite