- Uni-directional attention in GPT language model vs bi-direction attention in VisualBert multi-modality model. Screenshot from 2024-08-04 19-28-39.png ie .. SurgicalGPT : Index
- Implement ⇒ seemore: Implement a Vision Language Model from Scratch : https://huggingface.co/blog/AviSoori1x/seemore-vision-language-model
- Tryout ⇒ https://blog.lancedb.com/zero-shot-image-classification-with-vector-search/
- # Privacy Backdoors: Stealing Data with Corrupted Pretrained Models (Paper Explained)(https://www.youtube.com/@YannicKilcher) Github : https://github.com/ShanglunFengatETHZ/PrivacyBackdoor
- [ ]
