Towards Theoretical Understandings of Self-Consuming Generative Models
Authors: Shi Fu, Sen Zhang, Yingjie Wang, Xinmei Tian, Dacheng Tao
ICML 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, we present some experimental results. Specifically, we trained a diffusion model on the MNIST dataset. |
| Researcher Affiliation | Academia | 1University of Science and Technology of China, Hefei, China 2The University of Sydney, Sydney, Australia 3College of Control Science and Engineering, China University of Petroleum (East China), Qingdao, China 4Engineering Research Center of Intelligent Technology for Agriculture, Ministry of Education, China 5Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, China 6Nanyang Technological University, Singapore. |
| Pseudocode | Yes | Algorithm 1 Self-Consuming Loop of Generative Models |
| Open Source Code | No | The paper does not provide a statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | Specifically, we trained a diffusion model on the MNIST dataset. |
| Dataset Splits | No | The paper states it trained a diffusion model on the MNIST dataset but does not provide specific details on training, validation, or test dataset splits (e.g., percentages or counts). |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU/GPU models, memory, or cloud instance types) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific software dependencies with version numbers (e.g., libraries, frameworks, or solvers) used for the experiments. |
| Experiment Setup | No | The paper mentions training a diffusion model on MNIST and varying the amount of synthetic data, but it does not provide specific experimental setup details such as hyperparameters (e.g., learning rate, batch size, epochs) or optimizer settings. |