S23 Reading Group Session 2 - ViT & Brain Scans to Text
👩🏻💻 Have you been getting excited about all the fast paced world of Large Language Models (LLMs) and Transformers? 🤖
📖 Come drop in to the LLM & Transformers reading group this summer to learn about recent advances in the field and discuss them with your new friends! There will only be 3 sessions this term so don't miss it 🫵
📚 In our second session your reading group leads will be presenting on some 🔥 papers :
1️⃣ "An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale" - A paper written by researchers at Google which introduces the model of Vision Transformers (Image Classification using Transformers).
🔗 Link to slides: https://bit.ly/47sCT8g
2️⃣ "Semantic reconstruction of continuous language from non-invasive brain recordings" - The idea behind this paper is can we go from brain scans to pictures? Can A.I. read our thoughts?
🔗 Link to slides: https://bit.ly/3O4XrdV