Paper
Publication
Fair Normalizing Flows
Paper
Publication
Why Fair Labels Can Yield Unfair Predictions: Graphical Conditions for Introduced Unfairness
Paper
Publication
Overcoming the Convex Barrier for Simplex Inputs
Paper
Publication
Challenges in Detoxifying Language Models
Paper
Publication
Enabling certification of verification-agnostic networks via memory-efficient semidefinite programming
Paper
Publication
IReEn: Iterative Reverse-Engineering of Black-Box Functions via Neural Program Synthesis
Paper
Publication
Lagrangian Decomposition for Neural Network Verification
Paper
Publication
The Incentives that Shape Behaviour
Paper
Publication
Reducing Sentiment Bias in Language Models via Counterfactual Evaluation
Paper
Publication
An Alternative Surrogate Loss for PGD-based Adversarial Testing
Paper
Publication
Achieving Verified Robustness to Symbol Substitutions via Interval Bound Propagation
Paper
Publication
Wasserstein Fair Classification
Paper
Publication
A Causal Bayesian Networks Viewpoint on Fairness
Paper
Publication
Learning Dynamic Polynomial Proofs
Paper
Publication
A Bayesian Approach to Robust Reinforcement Learning
Paper
Publication
Knowing When to Stop: Evaluation and Verification of Conformity to Output-size Specifications
Paper
Publication
Degenerate Feedback Loops in Recommender Systems
Paper
Publication
Understanding Agent Incentives using Causal Influence Diagrams. Part I: Single Action Settings
Paper
Publication
Scaling shared model governance via model splitting
Paper
Publication
Verification of deep probabilistic models
Paper
Publication
Robustness via curvature regularization, and vice versa
Paper
Publication
Verification of Non-Linear Specifications for Neural Networks
Paper
Publication
Clinically applicable deep learning for diagnosis and referral in retinal disease
Paper
Publication
Modeling Friends and Foes
Paper
Publication
Learned Deformation Stability in Convolutional Neural Networks