6
6
Foundation Topics:
- Written Resources:
- Jay Alammar's blog "The Illustrated Transformer"
- Hugging Face Transformers course (free)
- "The Annotated Transformer" by Harvard NLP
- Hands-on Implementation:
- minGPT by Andrej Karpathy (GitHub)
- Hugging Face Transformers library documentation
- PyTorch Transformer tutorial
2. Diffusion Models
- Video Resources:
- Stanford CS236G lectures on diffusion models
- Outlier's "Diffusion Models from Scratch" course
- Written Resources:
- Lilian Weng's blog post on diffusion models
- AssemblyAI's diffusion model tutorial series
- HuggingFace Diffusers documentation
- Implementation Resources:
- Diffusers library by Hugging Face
- lucidrains' denoising-diffusion-pytorch (GitHub)
- CompVis/stable-diffusion repositories
Advanced Topics:
- Implementations:
- TRL library by Hugging Face
- TRLX repository
- CarperAI's RLHF tools
Specialized Tracks:
5. Multimodal Models
- Papers & Implementations:
- CLIP paper and OpenAI blog
- Stable Diffusion explanation series
- Microsoft's Florence paper
- Practical Resources:
- MultiModal Deep Learning course by UMich (YouTube)
- LAION AI's resources
- OpenAI's DALLE papers
6. Audio Generation
- Primary Resources:
- AudioCraft by Meta
- Tortoise TTS repository
- MusicGen documentation
- Tutorials:
- Hugging Face Audio course
- Stanford's CS224S course
- AudioLDM paper and code
7. 3D Generation
- Core Resources:
- NeRF paper and tutorial
- Instant NGP implementation
- Point-E by OpenAI
- Learning Materials:
- Nvidia's Kaolin library tutorials
- Get3D paper and resources