ChatGPT is not all you need. A State of the Art Review of large Generative AI models
generative-ailarge-language-modelsfoundation-modelssurveytext-to-image
Abstraction: Taxonomy of 2022-2023 generative AI models across all major modalities
Key points:
- Covers text-to-image (DALL-E 2, Stable Diffusion), text-to-3D (DreamFusion), image-to-text (Flamingo), text-to-video (Phenaki), text-to-audio (AudioLM), text-to-text (ChatGPT), text-to-code (Codex), text-to-science (Galactica), and algorithm generation (AlphaTensor)
- Published January 2023 as a concise taxonomy surveying the rapidly expanding landscape beyond ChatGPT
- Argues generative AI will transform multiple industry sectors and transform several job categories
- Provides a structured classification to help researchers and practitioners navigate the proliferating model landscape
Connections: Chatgpt · Openai · Generative AI · Large Language Models · Foundation Models
Source: https://arxiv.org/abs/2301.04655