There are 6 repositories under score-matching topic.
A collection of resources and papers on Diffusion Models
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
PyTorch implementation for Score-Based Generative Modeling through Stochastic Differential Equations (ICLR 2021, Oral)
Diffusion Models in Medical Imaging (Published in Medical Image Analysis Journal)
PyTorch implementation for SDEdit: Image Synthesis and Editing with Stochastic Differential Equations
Noise Conditional Score Networks (NeurIPS 2019, Oral)
The official PyTorch implementation for NCSNv2 (NeurIPS 2020)
Collecting research materials on EBM/EBL (Energy Based Models, Energy Based Learning)
Code for reproducing results in the sliced score matching paper (UAI 2019)
Official code for "Maximum Likelihood Training of Score-Based Diffusion Models", NeurIPS 2021 (spotlight)
Official implementation of pre-training via denoising for TorchMD-NET
PyTorch Implementation of Google Brain's WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis
Implementation of DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing
Some toy examples of score matching algorithms written in PyTorch
A demo shows how to combine Langevin dynamics with score matching for generative models.
Deterministic particle dynamics for simulating Fokker-Planck probability flows
Minimal unofficial implementation of Consistency Trajectory models on a 1D toy task.
Repository for Deterministic Particle Flow Control framework
This repository implements time series diffusion in the frequency domain.
Noise-conditional score networks for music composition by annealed Langevin dynamics
[ICLR 2022] Denoising Likelihood Score Matching for Conditional Score-based Data Generation
[ICLR 2022] Toy Experiments for Denoising Likelihood Score Matching for Conditional Score-based Data Generation
A collection of resources and papers on Diffusion Models.
[NeurIPS 2023] Training Energy-Based Normalizing Flow with Score-Matching Objectives
A collection of interesting papers on Diffusion Models
Repository for inference method for stochastic processes through geometric path augmentation
A Python 3 package for identifying distribution shifts (a.k.a feature-shifts) between datasets. Official implementation of the paper: "iSCAN: Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models".
This repository contains my final submission for the COMP3547 Deep Learning module assignment at Durham University in the academic year 2022/2023. The project focuses on diffusion-based models and their application in synthesising new, unique images, which could plausibly come from a training data set. Final grade received was 71/100.
Quickest Change Detection for Unnormalized Statistical Models
Score-based Hypothesis Testing for Unnormalized Models
[ICML 2023] On Investigating the Conservative Property of Score-Based Generative Models