NOTE
Foundation Models
Understand foundation models and survey representative models for text, images, speech, and other modalities.
Foundation Models
Categories
- Images
- Image Understanding
- ViT
- DINOv2
- SAM
- Image Generation
- Stable Diffusion
- DiT
- Image Understanding
- Text
- Large Language Models (LLM)
- GPT
- Qwen
- Large Language Models (LLM)
- Speech and Audio
- Speech Recognition
- Whisper
- Speech Generation
- VALL-E
- Speech Recognition
- Video
- Video Understanding
- VideoMAE
- Video Generation
- Sora
- Video Understanding
- Multimodal
- Multimodal Foundation Models
- GPT-4o
- Gemini
- Multimodal Foundation Models
What Is a Foundation Model?
- A general-purpose model pretrained on broad datasets that can be reused or adapted for a wide range of downstream tasks.
Drag to pan, scroll to zoom, and click a node to expand or collapse it. Large maps start with deeper levels collapsed; click nodes to expand them.
Discussion
Sign in with GitHub to comment. Discussions are stored as GitHub Issues.View on GitHub