On the Challenges and Opportunities in Generative AI

TMLR Paper4413 Authors

Abstract: The field of deep generative modeling has grown rapidly in the last few years. With the availability of massive amounts of training data coupled with advances in scalable unsupervised learning paradigms, recent large-scale generative models show tremendous promise in synthesizing high-resolution images and text, as well as structured data such as videos and molecules. However, we argue that current large-scale generative AI models exhibit several fundamental shortcomings that hinder their widespread adoption across domains. In this work, our objective is to identify these issues and highlight key unresolved challenges in modern generative AI paradigms that should be addressed to further enhance their capabilities, versatility, and reliability. By identifying these challenges, we aim to provide researchers with insights for exploring fruitful research directions, thus fostering the development of more robust and accessible generative AI solutions.

Submission Length: Long submission (more than 12 pages of main content)

Changes Since Last Submission:

Addressed reviewer feedback (representative but non-comprehensive list):
* Added a set of structured tables, which summarize some key points in each section, present key references to topic-specific surveys and foundational works, and offer actionable points for future research
* Clarified ambiguous statements
* Added brief statements on environmental impact and security concerns
* Fixed typos and stylistic issues

Assigned Action Editor: ~Bamdev_Mishra1

Submission Number: 4413