Browsing: Yannic Kilcher
BERT is a giant model. Turns out you can prune away many of its components and it still works. This…
For the first time, all authors submitting to the NeurIPS conference are forced to write a statement about the broader…
Can you plan with a learned model of the world? Yes, but there’s a catch: The better your planning algorithm…
Can you peek into people’s brains? Reading human thoughts is a long-standing dream of the AI field. This paper reads…
Does self-supervision really need a lot of data? How low can you go? This paper shows that a single image…
Neural Networks often draw hard boundaries in high-dimensional space, which makes them very brittle. Mixup is a technique that linearly…
Object detection in images is a notoriously hard task! Objects can be of a wide variety of classes, can be…
#gpt3 #openai #gpt-3 How far can you go with ONLY language modeling? Can a large enough language model perform NLP…
Watch my as I struggle my way up the glorious path of using the DETR object detection model in PyTorch.…
Do we really need dot-product attention? The attention mechanism is a central part of modern Transformers, mainly due to the…