DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphic…

An efficient pure-PyTorch implementation of Kolmogorov-Arnold Network (KAN).

Release for Improved Denoising Diffusion Probabilistic Models

Automated deep learning algorithms implemented in PyTorch.

A PyTorch toolbox for domain generalization, domain adaptation and semi-supervised learning.

The PyTorch implementation of Generative Pre-trained Transformers (GPTs) using Kolmogorov-Arnold Networks (KANs) for language modeling

NASBench: A Neural Architecture Search Dataset and Benchmark

This is the official code release for Bayesian Flow Networks.

Detecting Deepfakes Without Seeing Any

[ECCV 2022 & IJCV 2025] PyTorch code for SeqDeepFake: Detecting and Recovering Sequential DeepFake Manipulation

Official implementation of "Holmes-VAD: Towards Unbiased and Explainable Video Anomaly Detection via Multi-modal LLM"

An amortized approach for calculating local Shapley value explanations

Counterfactual-inference-based Text-classification Debiasing Framework.

Code for the paper "A Whac-A-Mole Dilemma Shortcuts Come in Multiples Where Mitigating One Amplifies Others"

A PyTorch implementation of Bayesian flow networks (Graves et al., 2023).

Official code of "Discover and Mitigate Unknown Biases with Debiasing Alternate Networks" (ECCV 2022)

Unofficial Implementation of Bayesian Flow Network in easy PyTorch for didactic purposes

Visualizing weights and feature maps of VGG-16

Temporal code repo for "Mitigating poisoning attack by Shapley value"