# Computer Vision Study Group | |
This is a collection of all past sessions that have been held as part of the Hugging Face Computer Vision Study Group. | |
| |Session Name | Session Link | | |
|--- |--- | --- | | |
|โ|How Do Vision Transformers Work? | [Session Sheet](Sessions/HowDoVisionTransformersWork.md) | | |
|๐ |Polarized Self-Attention | [Session Sheet](Sessions/PolarizedSelfAttention.md)| | |
|๐|Swin Transformer | [Session Sheet](Sessions/SwinTransformer.md)| | |
|๐ฎ|Introduction to Neural Radiance Fields | [Session Sheet](Sessions/NeuralRadianceFields.md)| | |
|๐|Hugging Face Vision Ecosystem Overview (June 2022) | [Session Sheet](Sessions/HFVisionEcosystem.md)| | |
|๐ช|Masked Autoencoders Are Scalable Vision Learners | [Session Sheet](Sessions/MaskedAutoEncoders.md)| | |
|๐ฆ|Fiber: Coarse-to-Fine Vision-Language Pre-Training | [Session Sheet](Sessions/Fiber.md)| | |
|โ๏ธ |FlexiViT: One Model for All Patch Sizes| [Session Sheet](Sessions/FlexiViT.md)| | |
|๐ค|BLIP-2: Bootstrapping Language-Image Pre-training| [Session Sheet](Sessions/Blip2.md)| | |