Author: Rachit Narang

Understanding Large Language Models (LLMs) like LLaMa by Meta (Part 1)

Highlights: Large Language Models (LLMs) have become essential tools in Natural Language Processing, powering applications from chatbots to complex data analysis. In today’s post, we’ll dive into the fascinating world of Large Language Models (LLMs) as explained in a lecture by Andrej Karpathy. We’ll study a notable model in this space, i.e., LLaMA (Large Language Model Meta AI), a groundbreaking LLM developed by Meta (formerly Facebook). We’ll also learn how LLMs in general and this…
Read more

Understanding Large Language Models (LLMs): Scaling, Applications & The Future (Part 2)

Highlights: Large Language Models (LLMs) have become essential tools in Natural Language Processing, powering applications from chatbots to complex data analysis. This is Part 2 of the post we posted earlier where we discussed the LLM by Meta called the LLaMa (Large Language Model Meta AI). We also learned how LLaMa was trained and how models like ChatGPT are trained. In today’s post, we’ll continue to discuss LLMs touching upon scaling laws, real-life applications of…
Read more

#003 Deepfakes – Monocular 3D Face Reconstruction, Tracking, and Applications

Highlights: There has been significant progress, in the past few years, when it comes to developing techniques and algorithms for reconstructing, tracking, and analyzing human faces. The Computer Vision communities across the globe are working hard to improve the speed, accuracy, and user-friendliness of these models. As a result, many impressive case studies have presented amazing results in the most challenging problems. Today, through this blog post, we’ll try to learn about the reconstruction and…
Read more

#002 Deepfakes – The Creation and Detection of Deepfakes: A Survey

Highlights: What is real, really? The ‘Deepfake’ technology has made advances into the mainstream and made it difficult to prove the authenticity of videos and faces. Even though the technology itself isn’t all that bad, its unethical use has victimized many across the globe. In this blog post, we will learn about the underlying algorithms of these so-called Deepfakes, based on Generative Adversarial Networks (GANs). We will also explore the creation and detection of Deepfakes…
Read more

#001 Deepfakes – Understanding Generative Learning

Highlights: The evolution of Generative Adversarial Networks (GANs) has brought about a change in how researchers solve certain Computer Vision problems such as conditional image generation, 3D object generation, video synthesis, and more. In this tutorial blog post, we will go into detail about the fundamentals of generative learning, its categories, and the different types of GANs that are popular in the Computer Vision field of research. So let’s begin! Tutorial Overview: Generative Learning Vanilla GAN…
Read more