Vision Language Models
LLMs are boring but VLMs are awesome, let’s see why.
Posts
All of Johann’s posts
Retrieval-Augmented Text Generation (RAG)
A short intro to Retrieval-Augmented Text Generation, what is it, why is it useful and how does it work.
A Peek into Deep Reinforcement Learning - Part II
Second part of the Introduction to the world of Reinforcement Learning, where I cover some more advanced deep RL algorithms and ideas in the space.
A Peek into Deep Reinforcement Learning - Part I
Introduction to the world of Reinforcement Learning, where I cover the basics and some algorithms.
Object Detection - Faster Models
One-Stage Object Detection Models.
Object Detection - From R-CNN to Mask R-CNN
Two-Stage Object Detection Models.
Overview - Human Pose Estimation
Overview of Human Pose Estimation Algorithms, Datasets and Benchmarks.