Yihan Cao — Page 2 | Search arXiv

arXiv2023

A Comprehensive Survey of AI-Generated Content (AIGC): A History of Generative AI from GAN to ChatGPT

Recently, ChatGPT, along with DALL-E-2 and Codex,has been gaining significant attention from society. As a result, many individuals have become interested in related resources and are seeking to uncover the background and secrets behind its impressive performance. In fact, ChatGPT and other Generative AI (GAI) techniques belong to the category of Artificial Intelligence Generated Content (AIGC), which involves the creation of digital content, such as images, music, and natural language, through AI models. The goal of AIGC is to make the content creation process more efficient and accessible, allowing for the production of high-quality content at a faster pace. AIGC is achieved by extracting and understanding intent information from instructions provided by human, and generating the content according to its knowledge and the intent information. In recent years, large-scale models have become increasingly important in AIGC as they provide better intent extraction and thus, improved generation results. With the growth of data and the size of the models, the distribution that the model can learn becomes more comprehensive and closer to reality, leading to more realistic and high-quality content generation. This survey provides a comprehensive review on the history of generative models, and basic components, recent advances in AIGC from unimodal interaction and multimodal interaction. From the perspective of unimodality, we introduce the generation tasks and relative models of text and image. From the perspective of multimodality, we introduce the cross-application between the modalities mentioned above. Finally, we discuss the existing open problems and future challenges in AIGC.

cs.AI↗

arXiv2021

Bayesian inference with tmbstan for a state-space model with VAR(1) state equation

When using R package tmbstan for Bayesian inference, the built-in feature Laplace approximation to the marginal likelihood with random effects integrated out can be switched on and off. There exists no guideline on whether Laplace approximation should be used to achieve better efficiency especially when the statistical model for estimating selection is complicated. To answer this question, we conducted simulation studies under different scenarios with a state-space model employing a VAR(1) state equation. We found that turning on Laplace approximation in tmbstan would probably lower the computational efficiency, and only when there is a good amount of data, both tmbstan with and without Laplace approximation are worth trying since in this case, Laplace approximation is more likely to be accurate and may also lead to slightly higher computational efficiency. The transition parameters and scale parameters in a VAR(1) process are hard to be estimated accurately and increasing the sample size at each time point do not help in the estimation, only more time points in the data contain more information on these parameters and make the likelihood dominate the posterior likelihood, thus lead to accurate estimates for them.

stat.ME↗