-
Northeastern University
Highlights
- Pro
Stars
Curate, Annotate, and Manage Your Data in LightlyStudio.
Code for "DISCO: Disentangled Communication Steering for Large Language Models" (NeurIPS 2025) https://openreview.net/pdf?id=c8AjdgdHnD
Source code for the Wasserstein Globalness method
Shapley Interactions and Shapley Values for Machine Learning
Implementation of GPEC and related experiment code, as described in "Boundary-Aware Uncertainty for Feature Attribution Explainers"
This is the code for the publication titled "Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functions" at AISTATS'24.
Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations
Refine high-quality datasets and visual AI models
Code for our NeurIPS 2023 Paper: SmoothHess: ReLU Network Feature Interactions via Stein’s Lemma
Train ImageNet *fast* in 500 lines of code with FFCV
Riemannian metrics to measure distances in latent space of VAEs
Estimating and plotting the decision boundary (decision surface) of machine learning classifiers in higher dimensions (scikit-learn compatible)
Bivariate Shapley is a Shapley-based method of identifying directional feature interactions and feature redundancy
This is code for paper published in neurips 2020