Generative Model

Generative models are artificial intelligence systems designed to create new data instances that resemble a training dataset, aiming to learn and replicate the underlying data distribution. Current research emphasizes improving efficiency and controllability, focusing on architectures like diffusion models, autoregressive models, and generative flow networks, as well as refining training algorithms and loss functions. These advancements have significant implications across diverse fields, enabling applications such as realistic image and music generation, protein design, and improved data augmentation techniques for various machine learning tasks.

Papers

November 4, 2024

Pricing and Competition for Generative AI
Rafid Mahmood
Generative Model Generative AI Competition Platform Curious Price Price Optimization
Generative Unfolding with Distribution Mapping
Anja Butter, Sascha Diefenbacher, Nathan Huetsch, Vinicius Mikuni, Benjamin Nachman, Sofia Palacios Schweitzer, Tilman Plehn
Generative Model Deep Unfolding Schr\"odinger Bridge Phase Space Cross Section Jet Substructure
LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation
Mufei Li, Viraj Shitole, Eli Chien, Changhai Man, Zhaodong Wang, Srinivas Sridharan, Ying Zhang, Tushar Krishna, Pan Li
Generative Model Multi Layer Directed Acyclic Graph Flow Network AutoRegressive Diffusion Intelligent Director
Counterfactual Explanations via Riemannian Latent Space Traversal
Paraskevas Pegios, Aasa Feragen, Andreas Abildtrup Hansen, Georgios Arvanitidis
Generative Model Counterfactual Explanation Complex Deep Counterfactual Explanation Method
Generating the Traces You Need: A Conditional Generative Model for Process Mining Data
Riccardo Graziosi, Massimiliano Ronzani, Andrei Buliga, Chiara Di Francescomarino, Francesco Folino, Chiara Ghidini, Francesca Meneghello, Luigi Pontieri
Generative Model Conditional Generative Process Mining Conditional Generation Conditional Variational Autoencoder Fuzzy Trace Finite Trace
Exploring the Landscape for Generative Sequence Models for Specialized Data Synthesis
Mohammad Zbeeb, Mohammad Ghorayeb, Mariam Salman
Generative Model Synthetic Data Landscape Image Data Synthesis State of the Art Generative Generative Time Series

November 2, 2024

Supervised Score-Based Modeling by Gradient Boosting
Changyuan Zhao, Hongyang Du, Guangyuan Liu, Dusit Niyato
Generative Model Gradient Boosting Score Based Model Boosted Tree

November 1, 2024

Evaluation Metric for Quality Control and Generative Models in Histopathology Images
Pranav Jeevan, Neeraj Nixon, Abhijeet Patil, Amit Sethi
Generative Model Image Quality Evaluation Metric Histopathology Image Histopathology Datasets Quality Control
Diffusion Models as Network Optimizers: Explorations and Analysis
Ruihuai Liang, Bo Yang, Pengyu Chen, Xianjin Li, Yifan Xue, Zhiwen Yu, Xuelin Cao, Yan Zhang, Mérouane Debbah, H. Vincent Poor, Chau Yuen
Diffusion Model Generative Model General Analysis Environment Exploration Probabilistic Model Generative Diffusion Model Network Optimization

October 31, 2024

A Geometric Framework for Understanding Memorization in Generative Models
Brendan Leigh Ross, Hamidreza Kamkari, Tongzi Wu, Rasa Hosseinzadeh, Zhaoyan Liu, George Stein, Jesse C. Cresswell, Gabriel Loaiza-Ganem
Generative Model Full Model Generative Question Limited Memorization Memorization Effect Manifold Hypothesis Geometric Framework
Learning Visual Parkour from Generated Images
Alan Yu, Ge Yang, Ran Choi, Yajvan Ravan, John Leonard, Phillip Isola
Generative Model Simulation Study AI Generated Image Robot Dog Direct Numerical Simulation
Counterfactual MRI Data Augmentation using Conditional Denoising Diffusion Generative Models
Pedro Morão, Joao Santinha, Yasna Forghani, Nuno Loução, Pedro Gouveia, Mario A. T. Figueiredo
Generative Model Medical Imaging Denoising Diffusion Counterfactual Image Counterfactual Data Augmentation
How Do Flow Matching Models Memorize and Generalize in Sample Data Subspaces?
Weiguo Gao, Ming Li
Generative Model Data Set Flow Matching Deep Subspace Proper Orthogonal Decomposition

October 30, 2024

FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions
Anuroop Sriram, Benjamin Kurt Miller, Ricky T. Q. Chen, Brandon M. Wood
Generative Model Large Language Flow Matching Material Discovery Material Generation Unconventional Crystal
Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models
Arash Marioriyad, Parham Rezaei, Mahdieh Soleymani Baghshah, Mohammad Hossein Rohban
Generative Model Global Evaluation Image Generation Faithful Generation Text to Image Model Compositional Ability Diffusion Based Model Compositional Generation AutoRegressive Diffusion

October 29, 2024

AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts
Vishal Kumar, Zeyi Liao, Jaylen Jones, Huan Sun
Large Language Model Generative Model Adversarial Suffix Suffix Prediction
Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
Zheyuan Liu, Guangyao Dou, Mengzhao Jia, Zhaoxuan Tan, Qingkai Zeng, Yongle Yuan, Meng Jiang
Language Model Generative Model Multimodal Large Language Model Web Corpus Protecting Privacy ML Agent Bench
SimSiam Naming Game: A Unified Approach for Representation Learning and Emergent Communication
Nguyen Le Hoang, Tadahiro Taniguchi, Fang Tianwei, Akira Taniguchi
Generative Model Representation Learning Variational Inference Variational Autoencoder Unified Framework Emergent Communication Emergent Language
On the Statistical Complexity of Estimating VENDI Scores from Empirical Data
Azim Ospanov, Farzan Farnia
Generative Model Raw Data Empirical Study Statistical Complexity Truncated Linear Matrix Based Entropy Vendi Score
Generating Realistic Tabular Data with Large Language Models
Dang Nguyen, Sunil Gupta, Kien Do, Thin Nguyen, Svetha Venkatesh
Language Model Generative Model Synthetic Data Tabular Data Data Generation Synthetic Tabular Data Generation

Generative Model

Papers

Pricing and Competition for Generative AI

Generative Unfolding with Distribution Mapping

LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation

Counterfactual Explanations via Riemannian Latent Space Traversal

Generating the Traces You Need: A Conditional Generative Model for Process Mining Data

Exploring the Landscape for Generative Sequence Models for Specialized Data Synthesis

Supervised Score-Based Modeling by Gradient Boosting

Evaluation Metric for Quality Control and Generative Models in Histopathology Images

Diffusion Models as Network Optimizers: Explorations and Analysis

A Geometric Framework for Understanding Memorization in Generative Models

Learning Visual Parkour from Generated Images

Counterfactual MRI Data Augmentation using Conditional Denoising Diffusion Generative Models

How Do Flow Matching Models Memorize and Generalize in Sample Data Subspaces?

FlowLLM: Flow Matching for Material Generation with Large Language Models as Base Distributions

Diffusion Beats Autoregressive: An Evaluation of Compositional Generation in Text-to-Image Models

AmpleGCG-Plus: A Strong Generative Model of Adversarial Suffixes to Jailbreak LLMs with Higher Success Rates in Fewer Attempts

Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench

SimSiam Naming Game: A Unified Approach for Representation Learning and Emergent Communication

On the Statistical Complexity of Estimating VENDI Scores from Empirical Data

Generating Realistic Tabular Data with Large Language Models