Score Based Generative

Score-based generative models (SBMs) are a class of deep generative models that learn the data distribution by modeling the score function—the gradient of the log-probability density—of a perturbed data distribution. Current research focuses on improving SBM efficiency and robustness through novel training objectives, algorithms like Langevin dynamics and probability flow ODEs, and architectural innovations such as incorporating symmetries and handling high-cardinality data. SBMs are proving valuable across diverse fields, from image generation and speech enhancement to solving inverse problems in medical imaging and astrophysics, offering a powerful tool for both data generation and inference tasks.

Papers

September 29, 2023

Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning
Zihan Ding, Chi Jin
Reinforcement Learning Generative Model Score Based Generative Actor Critic Algorithm Consistency Model Generating Rich Expressive Policy

August 31, 2023

Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints
Davide Scassola, Sebastiano Saccani, Ginevra Carbone, Luca Bortolussi
Generative Model Neuro Symbolic Score Based Generative Conditional Generation Consistent Conditioning Conditional Sampling Conditional Model Unconditional Generation

August 29, 2023

MadSGM: Multivariate Anomaly Detection with Score-based Generative Models
Haksoo Lim, Sewon Park, Minjung Kim, Jaehoon Lee, Seonkyu Lim, Noseong Park
Anomaly Detection Score Based Generative Time Series Anomaly Detection Multivariate Time Series Anomaly Detection

August 28, 2023

Data-iterative Optimization Score Model for Stable Ultra-Sparse-View CT Reconstruction
Weiwen Wu, Yanyang Wang
Sparse View Score Based Generative Score Based Diffusion Model Score Based Model Learning Based Reconstruction Sparse View CT Reconstruction

August 27, 2023

Score-Based Generative Models for PET Image Reconstruction
Imraj RD Singh, Alexander Denker, Riccardo Barbano, Željko Kereta, Bangti Jin, Kris Thielemans, Peter Maass, Simon Arridge
Generative Model Image Reconstruction Score Based Generative Positron Emission Tomography

August 22, 2023

Convergence guarantee for consistency models
Junlong Lyu, Zhitang Chen, Shoubo Feng
Strong Consistency Score Based Generative Convergence Guarantee Consistency Model

August 15, 2023

Monte Carlo guided Diffusion for Bayesian linear inverse problems
Gabriel Cardoso, Yazid Janati El Idrissi, Sylvain Le Corff, Eric Moulines
Inverse Problem Diffusion Explainer Score Based Generative Monte Carlo Ill Posed Inverse Problem Linear Inverse Problem Bayesian Inverse Problem

July 9, 2023

Score-based Conditional Generation with Fewer Labeled Data by Self-calibrating Classifier Guidance
Paul Kuo-Ming Huang, Si-An Chen, Hsuan-Tien Lin
Generative Modeling Score Based Generative Conditional Generation Unbiased SGG Classifier Guidance

June 27, 2023

Anomaly Detection in Networks via Score-Based Generative Models
Dmitrii Gavrilev, Evgeny Burnaev
Generative Model Anomaly Detection Generative Modeling Network Programming Outlier Detection Score Based Generative Score Based Model Small Graph

June 24, 2023

Score-based Generative Models for Photoacoustic Image Reconstruction with Rotation Consistency Constraints
Shangqing Tong, Hengrong Lan, Liming Nie, Jianwen Luo, Fei Gao
Generative Modeling Score Based Generative Photoacoustic Imaging Consistency Constraint

June 2, 2023

May 26, 2023

May 23, 2023

Improved Convergence of Score-Based Diffusion Models via Prediction-Correction
Francesco Pedrotti, Jan Maas, Marco Mondelli
Langevin Dynamic Convergence Rate Score Based Generative Convergence Guarantee Score Based Diffusion Model Subgaussian Assumption

May 19, 2023

The probability flow ODE is provably fast
Sitan Chen, Sinho Chewi, Holden Lee, Yuanzhi Li, Jianfeng Lu, Adil Salim
Langevin Dynamic Score Based Generative Probability Flow ODE ODE Net

May 2, 2023

Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data
Asad Aali, Marius Arvinte, Sidharth Kumar, Jonathan I. Tamir
Generative Model Inverse Problem Score Based Generative Noisy Data Ill Posed Inverse Problem Human Score

April 26, 2023

Score-based Generative Modeling Through Backward Stochastic Differential Equations: Inversion and Generation
Zihao Wang
Diffusion Model Faithful Generation Score Based Generative Stochastic Differential Equation Conditional Diffusion Eta Inversion Backward Stochastic Differential Equation

March 10, 2023

Score-Based Generative Models for Medical Image Segmentation using Signed Distance Functions
Lea Bogensperger, Dominik Narnhofer, Filip Ilic, Thomas Pock
Generative Model Medical Image Segmentation Segmentation Mask Score Based Generative Signed Distance Function

March 3, 2023

A Complete Recipe for Diffusion Generative Models
Kushagra Pandey, Stephan Mandt
Langevin Dynamic Score Based Generative Complete Recipe Score Based Model Forward Diffusion Synthesis Quality

Score Based Generative

Papers

Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning

Zero-Shot Conditioning of Score-Based Diffusion Models by Neuro-Symbolic Constraints

MadSGM: Multivariate Anomaly Detection with Score-based Generative Models

Data-iterative Optimization Score Model for Stable Ultra-Sparse-View CT Reconstruction

Score-Based Generative Models for PET Image Reconstruction

Convergence guarantee for consistency models

Monte Carlo guided Diffusion for Bayesian linear inverse problems

Score-based Conditional Generation with Fewer Labeled Data by Self-calibrating Classifier Guidance

Anomaly Detection in Networks via Score-Based Generative Models

Score-based Generative Models for Photoacoustic Image Reconstruction with Rotation Consistency Constraints

Audio-Visual Speech Enhancement with Score-Based Generative Models

Quantifying Sample Anonymity in Score-Based Generative Models with Adversarial Fingerprinting

High-Fidelity Image Compression with Score-based Generative Models

Error Bounds for Flow Matching Methods

Improved Convergence of Score-Based Diffusion Models via Prediction-Correction

The probability flow ODE is provably fast

Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data

Score-based Generative Modeling Through Backward Stochastic Differential Equations: Inversion and Generation

Score-Based Generative Models for Medical Image Segmentation using Signed Distance Functions

A Complete Recipe for Diffusion Generative Models