Drainage: A Unifying Framework for Addressing Class Uncertainty

Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation (ICCV 2021)

Pixi is cool, apptainer is cool, let's make them both work together !

Pytorch implementation of PatternNet.

A basic implementation of the FastCAV classifier to compute concept activation vectors in Captum.

Code for the article "What if Neural Networks had SVDs?", to be presented as a spotlight paper at NeurIPS 2020.

Official implementation of Diffusion Autoencoders

Decom-Renorm-Merge: Merging deep learning models through shared representation space.

Transform your favorite cities into beautiful, minimalist designs. MapToPoster lets you create and export visually striking map posters with code.

Normalizing flows in PyTorch

Code for the NeurIPS'21 paper "Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows"

Code for the NeurIPS'21 paper "Rectangular Flows for Manifold Learning"

Manifold-learning flows (ℳ-flows)

Free-form flows are a generative model training a pair of neural networks via maximum likelihood

NotesTeX (or its nickname NoTeX) is a simple LaTeX notes taking package for students.

A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editing

Official implementation of "ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression" (Oral at NeurIPS 2025)

Live Python Notebooks with any Editor

Minimal implementation of D-Flow: Differentiating through Flows for Controlled Generation

Code for the NeurIPS 2025 paper "Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations"

Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains