# Week 12: Self-Supervised and Vision-Language Models

Contrastive and self-supervised learning, CLIP and its successors, and the path from vision-language models to multimodal LLMs.

## Lectures

1. [Contrastive Learning, Part 1](<../notebooks/Week 12/W12_L1_Contrastive_Learning_Part1.ipynb>)
2. [Contrastive Learning, Part 2](<../notebooks/Week 12/W12_L2_Contrastive_Learning_Part2.ipynb>)
3. [Self-Supervised Learning: SimCLR](<../notebooks/Week 12/W12_L3_Self_Supervised_Learning_SimCLR.ipynb>)
4. [Vision-Language Models: Introduction and History](<../notebooks/Week 12/W12_L4_VLMs_Introduction_and_History.ipynb>)
5. [CLIP](<../notebooks/Week 12/W12_L5_CLIP.ipynb>)
6. [Beyond CLIP: BLIP, BLIP-2 and CoCa](<../notebooks/Week 12/W12_L6_Beyond_CLIP_BLIP_and_CoCa.ipynb>)
7. [From VLMs to Multimodal LLMs](<../notebooks/Week 12/W12_L7_From_VLMs_to_Multimodal_LLMs.ipynb>)
8. [Course Conclusion](<../notebooks/Week 12/W12_L8_Course_Conclusion.ipynb>)